korchasa
377 verified skills678 total stars
setup-ai-ide-devcontainer
Generate a .devcontainer (devcontainer.json plus optional Dockerfile) for AI-IDE development with AI CLI integration, skill mounting, and security hardening. Use when the user wants to set up or containerize a dev environment for Claude Code, OpenCode, or flowai.
tools3
fix-tests
Fix failing or broken tests by finding the root cause and correcting the source code (not the test). Use when tests fail, a suite is red, or the user asks to fix or repair tests or a CI test failure.
development3
fix-tests
Fix failing or broken tests by finding the root cause and correcting the source code (not the test). Use when tests fail, a suite is red, or the user asks to fix or repair tests or a CI test failure.
development3
engineer-plugin-marketplace
Design AI-IDE plugin marketplaces - requirements, host-specific payloads, local dogfood, release sync, and validation. Use when the user wants to create or publish a plugin marketplace.
tools3
engineer-skill
Guide for creating effective Agent Skills (SKILL.md packages). Use when users want to create a new skill, write a skill, author a SKILL.md, or ask about skill structure, best practices, or skill file format. Works across IDEs (Cursor, Claude Code, OpenCode).
development3
engineer-ai-ide-plugin
Design and build plugins for AI IDEs (skills, MCP tools, hooks, packaging, manifests, marketplaces, per-IDE validation). Use when the user wants to create, design, or package an AI-IDE plugin.
tools3
engineer-ai-ide-plugin
Design and build plugins for AI IDEs (skills, MCP tools, hooks, packaging, manifests, marketplaces, per-IDE validation). Use when the user wants to create, design, or package an AI-IDE plugin.
tools3
write-agent-benchmarks
Create, maintain, and run evidence-based benchmarks for AI agents. Use when setting up testing infrastructure, writing new test scenarios, or evaluating agent performance.
testing3
analyze-context
Estimate total token usage and cost across conversation history, system prompts, and active rules. Use when the user asks how much context or how many tokens are in use, to audit context size, or to estimate session cost.
testing3
maintenance
Use when the user asks for a project health audit, maintenance sweep, or multi-category lead-engineer scan followed by interactive issue-by-issue resolution with user approval. Do NOT trigger on routine lint/test runs, single-file cleanups, or standard "check project" requests.
development3
write-in-informational-style
Rewrite text in a dense, factual informational style with no fluff or marketing. Use when the user asks to write or rewrite docs or notes concisely or to apply a neutral informational tone.
development3
write-prd
Produce a comprehensive Product Requirements Document (PRD). Use when the user asks to write a PRD or formalize a feature's scope, goals, and success metrics.
development3
engineer-plugin-hooks
Build AI-IDE plugin hook elements - shared policies plus Claude Code/Codex/OpenCode/Cursor adapters for lifecycle events, blocking, audit, and context injection. Use when adding or configuring plugin hooks.
tools3
delegate-to-ide
Delegate a task to another AI IDE's CLI (codex / claude / opencode / cursor-agent) through an isolated-context subagent. Triggers on "delegate to <ide>", "have <ide> do <task>", "execute <task> in <ide>", "offload to <ide>". For one-shot relay or fan-out comparison use `ai-ide-runner` instead.
tools3
delegate-to-ide
Delegate a task to another AI IDE's CLI (codex / claude / opencode / cursor-agent) through an isolated-context subagent. Triggers on "delegate to <ide>", "have <ide> do <task>", "execute <task> in <ide>", "offload to <ide>". For one-shot relay or fan-out comparison use `ai-ide-runner` instead.
tools3
ai-ide-runner
Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from the current session — pick one IDE, fan out across several, or compare models. You are a courier that relays the other runtime's stdout verbatim, do not synthesise your own answer. Use on "run in <ide>", "compare <ide> vs <ide>", "try on <model>", "which IDE handles X better", "run across models".
tools3
ai-ide-runner
Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from the current session — pick one IDE, fan out across several, or compare models. You are a courier that relays the other runtime's stdout verbatim, do not synthesise your own answer. Use on "run in <ide>", "compare <ide> vs <ide>", "try on <model>", "which IDE handles X better", "run across models".
tools3
engineer-prompts-for-instant
Guide to writing stable prompts for instant/fast models (Gemini Flash, GPT-4o Mini, Haiku). Use when the user is writing or tuning prompts for a fast or cheap model.
documentation3
engineer-skill
Guide for creating effective Agent Skills (SKILL.md packages). Use when users want to create a new skill, write a skill, author a SKILL.md, or ask about skill structure, best practices, or skill file format. Works across IDEs (Cursor, Claude Code, OpenCode).
development3
select-llm-model
Recommend which LLM model to use for a task. Use when asked "which model / best LLM for X", "pick a model for this task", or for a model shortlist ranked by live leaderboard evidence (coding, reasoning, agentic, tool-use, price, speed). Live-fetches public leaderboards and ranks models with per-axis rationale and citations.
tools3
setup-ai-ide-devcontainer
Generate a .devcontainer (devcontainer.json plus optional Dockerfile) for AI-IDE development with AI CLI integration, skill mounting, and security hardening. Use when the user wants to set up or containerize a dev environment for Claude Code, OpenCode, or flowai.
tools3
engineer-plugin-marketplace
Design AI-IDE plugin marketplaces - requirements, host-specific payloads, local dogfood, release sync, and validation. Use when the user wants to create or publish a plugin marketplace.
tools3
select-llm-model
Recommend which LLM model to use for a task. Use when asked "which model / best LLM for X", "pick a model for this task", or for a model shortlist ranked by live leaderboard evidence (coding, reasoning, agentic, tool-use, price, speed). Live-fetches public leaderboards and ranks models with per-axis rationale and citations.
tools3
write-gods-tasks
Author task files in the GODS framework (Goal, Overview, Definition of Done, Solution). Use when the user asks to write, structure, or break down a task or plan in GODS format.
development3
engineer-prompts-for-reasoning
Guide to writing prompts for reasoning models (Gemini Pro, GPT-4o, Claude Sonnet), focused on structure and context. Use when the user is writing or tuning prompts for a reasoning or smart model.
documentation3
maintenance
Use when the user asks for a project health audit, maintenance sweep, or multi-category lead-engineer scan followed by interactive issue-by-issue resolution with user approval. Do NOT trigger on routine lint/test runs, single-file cleanups, or standard "check project" requests.
development3
write-agent-benchmarks
Create, maintain, and run evidence-based benchmarks for AI agents. Use when setting up testing infrastructure, writing new test scenarios, or evaluating agent performance.
testing3
write-prd
Produce a comprehensive Product Requirements Document (PRD). Use when the user asks to write a PRD or formalize a feature's scope, goals, and success metrics.
development3
engineer-prompts-for-reasoning
Guide to writing prompts for reasoning models (Gemini Pro, GPT-4o, Claude Sonnet), focused on structure and context. Use when the user is writing or tuning prompts for a reasoning or smart model.
documentation3
engineer-plugin-mcp
Build AI-IDE plugin MCP elements - stdio JSON-RPC servers, tool schemas, host wiring for Claude Code/Codex, event-name mapping, and validation. Use when adding an MCP server to a plugin.
tools3
engineer-plugin-hooks
Build AI-IDE plugin hook elements - shared policies plus Claude Code/Codex/OpenCode/Cursor adapters for lifecycle events, blocking, audit, and context injection. Use when adding or configuring plugin hooks.
tools3
write-gods-tasks
Author task files in the GODS framework (Goal, Overview, Definition of Done, Solution). Use when the user asks to write, structure, or break down a task or plan in GODS format.
development3
write-dep
Write a Development Enhancement Proposal (DEP) for a technical improvement. Use when the user wants to propose, document, or formalize a technical change for review.
development3
analyze-context
Estimate total token usage and cost across conversation history, system prompts, and active rules. Use when the user asks how much context or how many tokens are in use, to audit context size, or to estimate session cost.
testing3
write-in-informational-style
Rewrite text in a dense, factual informational style with no fluff or marketing. Use when the user asks to write or rewrite docs or notes concisely or to apply a neutral informational tone.
development3
engineer-prompts-for-instant
Guide to writing stable prompts for instant/fast models (Gemini Flash, GPT-4o Mini, Haiku). Use when the user is writing or tuning prompts for a fast or cheap model.
documentation3
engineer-plugin-mcp
Build AI-IDE plugin MCP elements - stdio JSON-RPC servers, tool schemas, host wiring for Claude Code/Codex, event-name mapping, and validation. Use when adding an MCP server to a plugin.
tools3
write-dep
Write a Development Enhancement Proposal (DEP) for a technical improvement. Use when the user wants to propose, document, or formalize a technical change for review.
development3
flowai-interactive-teaching-materials
Creates interactive HTML teaching materials with clickable state diagrams. Use when the user asks to produce an explorable tutorial artifact, not to answer a question.
tools2
flowai-conduct-qa-session
How to conduct a Q&A session with the user. Canonical reference for FR-UNIVERSAL.QA-FORMAT.
development2
flowai-engineer-prompts-for-reasoning
Guide for writing prompts for reasoning/smart models (Gemini Pro, GPT-4o, Claude 3.5 Sonnet), focused on structure and context.
documentation2
flowai-fix-tests
How to fix tests
testing2
flowai-write-in-informational-style
How to write in informational style
development2
flowai-write-dep
Writing a Development Enhancement Proposal (DEP) - a document for proposing technical improvements
development2
flowai-memex-ask
Use when the user asks a question to be answered from the project's memex (long-term knowledge bank for AI agents) rather than training data or the live web. Reads the index, opens relevant pages, follows one wikilink hop, synthesises a cited answer, files it back. Do NOT trigger on source-code or live-session questions.
development2
flowai-diagnose-benchmark-failure
Use when a flowai benchmark fails and you need the cause from run artifacts before editing. Reads judge-evidence.md, the sandbox SKILL.md, and scenario mod.ts; classifies the failure against a known taxonomy; produces an evidence-grounded report (no fixes). Do NOT trigger for passing benchmarks or generic skill iteration.
data-ai2
flowai-memex-ask
Use when the user asks a question to be answered from the project's memex (long-term knowledge bank for AI agents) rather than training data or the live web. Reads the index, opens relevant pages, follows one wikilink hop, synthesises a cited answer, files it back. Do NOT trigger on source-code or live-session questions.
development2
flowai-write-dep
Writing a Development Enhancement Proposal (DEP) - a document for proposing technical improvements
development2
flowai-browser-automation
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
tools2
flowai-skill-deep-research
Multi-directional deep research with sub-agents, scoring, source verification, and cited synthesis. Use for comprehensive research, deep analysis, or evidence-backed answers. Produces executive summary + markdown report. Supports search tools, playwright-cli, and MCP.
tools2
bench-all
Run all framework benchmarks. Default is sequential (single `deno task bench`). Use `--parallel` for 5-subagent parallel mode. Triggers on "run all benchmarks", "bench all", "/bench-all".
development2
flowai-commit-beta
Streamlined commit workflow — fewer tool calls, targeted doc sync
tools2
django-migrations
Manage Django database migrations (makemigrations, migrate, squash).
development2
ai-skel-ts-usage
Scaffold a complete AI agent application skeleton with LLM integration, tool calling, observability, cost tracking, session management, and content fetching using @korchasa/ai-skel-ts. Use when the user asks to create an AI agent, add LLM integration, scaffold an AI application, or mentions "ai-skel", "agent skeleton", or "AI scaffold". Works with any programming language.
tools2
ai-skel-ts-usage
Scaffold a complete AI agent application skeleton with LLM integration, tool calling, observability, cost tracking, session management, and content fetching using @korchasa/ai-skel-ts. Use when the user asks to create an AI agent, add LLM integration, scaffold an AI application, or mentions "ai-skel", "agent skeleton", or "AI scaffold". Works with any programming language.
tools2
flowai-skill-conduct-qa-session
How to conduct a Q&A session with the user
testing2
flowai-skill-conduct-qa-session
How to conduct a Q&A session with the user
testing2
save
Use when the user provides a source (URL, file path, or free text) to save into the project's memex — a long-term knowledge bank for AI agents. Stores the raw source, extracts entities into cross-linked pages, runs a backlink audit, and updates the index and activity log. Do NOT trigger on casual reads; only when the intent is to persist a source into the memex.
testing2
update
Reconcile project-owned AGENTS.md, CLAUDE.md, and scaffolded artifacts with the current flowai framework templates.
development2
engineer-rule
Guide for creating persistent AI rules (coding standards, project conventions, file-specific patterns). Use when users want to create a rule, add coding standards, set up project conventions, configure file-specific patterns, or ask about rules placement. Works across IDEs (Cursor, Claude Code, OpenCode).
development2
conduct-qa-session
How to conduct a Q&A session with the user. Canonical reference for FR-UNIVERSAL.QA-FORMAT.
development2
draw-mermaid-diagrams
Draw and edit Mermaid diagrams in Markdown. Use when the user wants to visualize processes, flows, sequences, or asks for diagrams.
data-ai2
flowai-epic
Create structured epic for large features using phased decomposition. Produces documents/tasks/epic-{name}.md with dependency-ordered phases, atomic tasks, explicit boundaries, and per-phase status tracking.
testing2
init
Initialize project with AGENTS.md and rules, handling both Greenfield (new) and Brownfield (existing) projects.
data-ai2
interactive-teaching-materials
Creates interactive HTML teaching materials with clickable state diagrams. Use when the user asks to produce an explorable tutorial artifact, not to answer a question.
tools2
browser-automation
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
tools2
engineer-subagent
Guide for creating effective Subagents (custom agent definitions). Use when users want to create a new subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants. Works across IDEs (Cursor, OpenCode).
development2
delegate-to-ide
Delegate a task to another AI IDE's CLI (codex / claude / opencode / cursor-agent) through an isolated-context subagent. Triggers on "delegate to <ide>", "have <ide> do <task>", "execute <task> in <ide>", "offload to <ide>". For one-shot relay or fan-out comparison use `ai-ide-runner` instead.
tools2
reflect
Use when the user asks to reflect on the CURRENT session, analyze the agent's own process, audit context usage in this conversation, or extract lessons from how the current task was executed. Do NOT trigger for historical multi-session analysis — use reflect-by-history for that. Do NOT trigger on plain "what did you do?" style recaps.
testing2
engineer-rule
Guide for creating persistent AI rules (coding standards, project conventions, file-specific patterns). Use when users want to create a rule, add coding standards, set up project conventions, configure file-specific patterns, or ask about rules placement. Works across IDEs (Cursor, Claude Code, OpenCode).
development2
engineer-subagent
Guide for creating effective Subagents (custom agent definitions). Use when users want to create a new subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants. Works across IDEs (Cursor, OpenCode).
development2
deep-research
Multi-directional deep research with sub-agents, scoring, source verification, and cited synthesis. Use for comprehensive research, deep analysis, or evidence-backed answers. Produces executive summary + markdown report. Supports search tools, playwright-cli, and MCP.
tools2
diagnose-benchmark-failure
Use when a flowai benchmark fails and you need the cause from run artifacts before editing. Reads judge-evidence.md, the sandbox SKILL.md, and scenario mod.ts; classifies the failure against a known taxonomy; produces an evidence-grounded report (no fixes). Do NOT trigger for passing benchmarks or generic skill iteration.
data-ai2
manage-github-tickets
Create and manage GitHub issues using the GODS framework. Use when creating, updating, or triaging GitHub issues.
development2
epic
Use when the user asks to plan a LARGE feature that spans multiple sessions or phases — produces an epic under the `tasks` role from AGENTS.md with dependency-ordered phases, atomic tasks, and per-phase status tracking. Use plan for single-session tasks. Do NOT trigger on generic planning, roadmap, or brainstorming requests.
data-ai2
reflect
Use when the user asks to reflect on the CURRENT session, analyze the agent's own process, audit context usage in this conversation, or extract lessons from how the current task was executed. Do NOT trigger for historical multi-session analysis — use reflect-by-history for that. Do NOT trigger on plain "what did you do?" style recaps.
testing2
deep-research
Multi-directional deep research with sub-agents, scoring, source verification, and cited synthesis. Use for comprehensive research, deep analysis, or evidence-backed answers. Produces executive summary + markdown report. Supports search tools, playwright-cli, and MCP.
tools2
conduct-qa-session
How to conduct a Q&A session with the user. Canonical reference for FR-UNIVERSAL.QA-FORMAT.
development2
draw-mermaid-diagrams
Draw and edit Mermaid diagrams in Markdown. Use when the user wants to visualize processes, flows, sequences, or asks for diagrams.
data-ai2
interactive-teaching-materials
Creates interactive HTML teaching materials with clickable state diagrams. Use when the user asks to produce an explorable tutorial artifact, not to answer a question.
tools2
manage-github-tickets
Create and manage GitHub issues using the GODS framework. Use when creating, updating, or triaging GitHub issues.
development2
engineer-hook
Creation and configuration of event hooks/plugins to manage agent behavior, command filtering, auditing, and automation. Works across IDEs (Cursor, Claude Code, OpenCode). Use when you need to: (1) Create a new hook (e.g., for formatting or security checks), (2) Configure hooks/plugins, (3) Implement logic for blocking or modifying agent actions via scripts.
tools2
flowai-deep-research
Multi-directional deep research with sub-agents, scoring, source verification, and cited synthesis. Use for comprehensive research, deep analysis, or evidence-backed answers. Produces executive summary + markdown report. Supports search tools, playwright-cli, and MCP.
tools2
flowai-memex-audit
Use when the user asks to audit a memex (long-term knowledge bank for AI agents) for orphans, dead wikilinks, missing sections, contradictions, or index drift. Runs a deterministic structural check, layers LLM-judgement findings, optionally auto-fixes trivial issues with `--fix`. Do NOT trigger on general code linting.
development2
flowai-skill-analyze-context
Analyze total token usage including conversation history, system prompts, and active rules to estimate cost.
data-ai2
flowai-setup-agent-code-style-ts-strict
Adds TypeScript strict mode code style rules to project AGENTS.md. Use when setting up TypeScript projects with strict mode or establishing coding standards.
development2
cli
Manage all Deno capabilities via CLI (run, test, fmt, lint, task, add, etc.). Use this skill when you need to execute Deno commands, manage dependencies, run tests, or handle local development workflows.
tools2
setup-agent-code-style-deno
Use when the user asks to add Deno/TypeScript code-style rules to AGENTS.md, or during initial Deno project setup when code-style guidelines need to be established. Do NOT trigger for non-Deno TypeScript projects (use setup-agent-code-style-strict), or for runtime-agnostic style advice.
development2
flowai-epic
Use when the user asks to plan a LARGE feature that spans multiple sessions or phases — produces documents/tasks/<YYYY>/<MM>/epic-<name>.md with dependency-ordered phases, atomic tasks, and per-phase status tracking. Use flowai-plan for single-session tasks. Do NOT trigger on generic planning, roadmap, or brainstorming requests.
documentation2
flowai-draw-mermaid-diagrams
Draw and edit Mermaid diagrams in Markdown. Use when the user wants to visualize processes, flows, sequences, or asks for diagrams.
data-ai2
flowai-commit
Automated commit workflow with atomic grouping
data-ai2
flowai-skill-setup-ai-ide-devcontainer
Set up .devcontainer for AI IDE development. Generates devcontainer.json and optional Dockerfile for project tech stack, AI CLI integration (Claude Code, OpenCode, flowai), skill mounting, and security hardening.
tools2
flowai-conduct-qa-session
How to conduct a Q&A session with the user. Canonical reference for FR-UNIVERSAL.QA-FORMAT.
development2
flowai-setup-agent-code-style-ts-deno
Use when the user asks to add Deno/TypeScript code-style rules to AGENTS.md, or during initial Deno project setup when code-style guidelines need to be established. Do NOT trigger for non-Deno TypeScript projects (use flowai-setup-agent-code-style-ts-strict), or for runtime-agnostic style advice.
development2
flowai-adapt
Adapt project-local flowai primitives (skills, agents, AGENTS.md artifacts, hooks) to project specifics. Standalone adaptation — independent of flowai-update.
testing2
flowai-setup-agent-code-style-ts-strict
Adds TypeScript strict mode code style rules to project AGENTS.md. Use when setting up TypeScript projects with strict mode or establishing coding standards.
development2
flowai-write-agent-benchmarks
Create, maintain, and run evidence-based benchmarks for AI agents. Use when setting up testing infrastructure, writing new test scenarios, or evaluating agent performance.
testing2
flowai-write-agent-benchmarks
Create, maintain, and run evidence-based benchmarks for AI agents. Use when setting up testing infrastructure, writing new test scenarios, or evaluating agent performance.
testing2
flowai-setup-agent-code-style-ts-strict
Use when the user asks to add TypeScript strict-mode code-style rules to AGENTS.md for a TypeScript project using strict mode. Do NOT trigger for Deno projects (use flowai-setup-agent-code-style-ts-deno) or non-strict TS configurations.
development2
flowai-delegate-to-ide
Delegate a task to another AI IDE's CLI (codex / claude / opencode / cursor-agent) through an isolated-context subagent. Triggers on "delegate to <ide>", "have <ide> do <task>", "execute <task> in <ide>", "offload to <ide>". For one-shot relay or fan-out comparison use `flowai-ai-ide-runner` instead.
tools2
flowai-ai-ide-runner
Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from the current session — pick one IDE, fan out across several, or compare models. You are a courier that relays the other runtime's stdout verbatim, do not synthesise your own answer. Use on "run in <ide>", "compare <ide> vs <ide>", "try on <model>", "which IDE handles X better", "run across models".
tools2
flowai-ai-ide-runner
Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from the current session — pick one IDE, fan out across several, or compare models. You are a courier that relays the other runtime's stdout verbatim, do not synthesise your own answer. Use on "run in <ide>", "compare <ide> vs <ide>", "try on <model>", "which IDE handles X better", "run across models".
tools2
flowai-review-and-commit-beta
Streamlined two-phase workflow: review, then commit. Verdict gate between phases. Self-contained — execute the inlined steps directly, do NOT invoke other skills via the Skill tool.
tools2
flowai-skill-review
Use when the user asks to review CURRENT uncommitted changes (staged, unstaged, or branch diff) as QA + lead engineer before committing — verdict on task completion, code quality, architecture, cleanup. Requires an existing diff. Do NOT trigger on generic "is this code good?" questions without a diff, or on post-merge code review of historical commits.
development2
ask
Use when the user asks a question to be answered from the project's memex (long-term knowledge bank for AI agents) rather than training data or the live web. Reads the index, opens relevant pages, follows one SALP-REF hop, synthesises a cited answer, files it back. Do NOT trigger on source-code or live-session questions.
development2
init
Initialize project with AGENTS.md and rules, handling both Greenfield (new) and Brownfield (existing) projects.
data-ai2
audit
Use when the user asks to audit a memex (long-term knowledge bank for AI agents) for orphans, dead SALP REFs, missing sections, contradictions, or index drift. Runs a deterministic structural check, layers LLM-judgement findings, optionally auto-fixes trivial issues with `--fix`. Do NOT trigger on general code linting.
development2
setup-agent-code-style-deno
Use when the user asks to add Deno/TypeScript code-style rules to AGENTS.md, or during initial Deno project setup when code-style guidelines need to be established. Do NOT trigger for non-Deno TypeScript projects (use setup-agent-code-style-strict), or for runtime-agnostic style advice.
development2
flowai-skill-configure-deno-commands
Configure and maintain Deno development commands (check, test, dev, prod). Use when the user wants to set up or update the standard command interface in deno.json and scripts/ directory.
development2
flowai-skill-reflect
Use when the user asks to reflect on the CURRENT session, analyze the agent's own process, audit context usage in this conversation, or extract lessons from how the current task was executed. Do NOT trigger for historical multi-session analysis — use flowai-skill-reflect-by-history for that. Do NOT trigger on plain "what did you do?" style recaps.
testing2
flowai-skill-maintenance
Use when the user asks for a project health audit, maintenance sweep, or multi-category lead-engineer scan followed by interactive issue-by-issue resolution with user approval. Do NOT trigger on routine lint/test runs, single-file cleanups, or standard "check project" requests.
development2
flowai-skill-engineer-subagent
Guide for creating effective Subagents (custom agent definitions). Use when users want to create a new subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants. Works across IDEs (Cursor, OpenCode).
development2
flowai-skill-configure-deno-commands
Configure and maintain Deno development commands (check, test, dev, prod). Use when the user wants to set up or update the standard command interface in deno.json and scripts/ directory.
development2
save
Use when the user provides a source (URL, file path, or free text) to save into the project's memex — a long-term knowledge bank for AI agents. Stores the raw source, extracts entities into cross-linked pages, runs a backlink audit, and updates the index and activity log. Do NOT trigger on casual reads; only when the intent is to persist a source into the memex.
testing2
setup-agent-code-style-strict
Use when the user asks to add TypeScript strict-mode code-style rules to AGENTS.md for a TypeScript project using strict mode. Do NOT trigger for Deno projects (use setup-agent-code-style-deno) or non-strict TS configurations.
development2
flowai-skill-reflect-by-history
Use when the user asks to review PAST sessions (not the current one), find recurring patterns across multiple sessions, or improve project primitives (rules, skills, hooks, docs) based on historical IDE transcripts. Do NOT trigger on current-session self-review — use flowai-skill-reflect instead.
documentation2
flowai-skill-investigate
Use when the user asks to diagnose a bug, find the root cause of a failing behavior, or run a controlled hypothesis-by-hypothesis investigation with experiments and evidence. Produces a diagnostic report with a recommended fix (but does not apply the fix). Do NOT trigger on "fix this bug" when the cause is obvious, or on simple error-message lookups.
data-ai2
flowai-skill-deno-deploy
Manage Deno Deploy cloud services using both `deno deploy` and `deployctl`. Use this skill for deploying projects, managing cloud environments (Build/Dev/Prod contexts), monitoring logs, and troubleshooting deployment issues (like private npm dependencies).
development2
flowai-skill-deno-cli
Manage all Deno capabilities via CLI (run, test, fmt, lint, task, add, etc.). Use this skill when you need to execute Deno commands, manage dependencies, run tests, or handle local development workflows.
tools2
flowai-skill-engineer-rule
Guide for creating persistent AI rules (coding standards, project conventions, file-specific patterns). Use when users want to create a rule, add coding standards, set up project conventions, configure file-specific patterns, or ask about rules placement. Works across IDEs (Cursor, Claude Code, OpenCode).
development2
flowai-skill-engineer-rule
Guide for creating persistent AI rules (coding standards, project conventions, file-specific patterns). Use when users want to create a rule, add coding standards, set up project conventions, configure file-specific patterns, or ask about rules placement. Works across IDEs (Cursor, Claude Code, OpenCode).
development2
flowai-skill-epic
Use when the user asks to plan a LARGE feature that spans multiple sessions or phases — produces documents/tasks/<YYYY>/<MM>/epic-<name>.md with dependency-ordered phases, atomic tasks, and per-phase status tracking. Use flowai-skill-plan for single-session tasks. Do NOT trigger on generic planning, roadmap, or brainstorming requests.
documentation2
flowai-skill-investigate
Use when the user asks to diagnose a bug, find the root cause of a failing behavior, or run a controlled hypothesis-by-hypothesis investigation with experiments and evidence. Produces a diagnostic report with a recommended fix (but does not apply the fix). Do NOT trigger on "fix this bug" when the cause is obvious, or on simple error-message lookups.
data-ai2
flowai-skill-ai-ide-runner
Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from the current session — pick one IDE, fan out across several, or compare models. You are a courier that relays the other runtime's stdout verbatim, do not synthesise your own answer. Use on "run in <ide>", "compare <ide> vs <ide>", "try on <model>", "which IDE handles X better", "run across models".
tools2
flowai-skill-plan
Use ONLY when the user explicitly asks to plan a task, create a task file in documents/tasks/, produce a GODS-format breakdown, or prepare a critiqued implementation strategy before coding. Do NOT trigger on brief design discussion, ad-hoc code suggestions, or casual "how would you approach X?" questions.
development2
flowai-skill-deno-deploy
Manage Deno Deploy cloud services using both `deno deploy` and `deployctl`. Use this skill for deploying projects, managing cloud environments (Build/Dev/Prod contexts), monitoring logs, and troubleshooting deployment issues (like private npm dependencies).
development2
flowai-skill-setup-ai-ide-devcontainer
Set up .devcontainer for AI IDE development. Generates devcontainer.json and optional Dockerfile for project tech stack, AI CLI integration (Claude Code, OpenCode, flowai), skill mounting, and security hardening.
tools2
flowai-skill-engineer-skill
Guide for creating effective Agent Skills (SKILL.md packages). Use when users want to create a new skill, write a skill, author a SKILL.md, or ask about skill structure, best practices, or skill file format. Works across IDEs (Cursor, Claude Code, OpenCode).
development2
flowai-skill-analyze-context
Analyze total token usage including conversation history, system prompts, and active rules to estimate cost.
data-ai2
flowai-skill-fix-tests
How to fix tests
testing2
flowai-skill-deep-research
Multi-directional deep research with sub-agents, scoring, source verification, and cited synthesis. Use for comprehensive research, deep analysis, or evidence-backed answers. Produces executive summary + markdown report. Supports search tools, playwright-cli, and MCP.
tools2
flowai-skill-memex-ask
Use when the user asks a question to be answered from the project's memex (long-term knowledge bank for AI agents) rather than training data or the live web. Reads the index, opens relevant pages, follows one wikilink hop, synthesises a cited answer, files it back. Do NOT trigger on source-code or live-session questions.
development2
flowai-skill-engineer-prompts-for-instant
Guide for writing stable, effective prompts for instant/fast models (Gemini Flash, GPT-4o Mini, Haiku), suitable for beginners.
documentation2
flowai-skill-engineer-prompts-for-reasoning
Guide for writing prompts for reasoning/smart models (Gemini Pro, GPT-4o, Claude 3.5 Sonnet), focused on structure and context.
documentation2
flowai-skill-write-dep
Writing a Development Enhancement Proposal (DEP) - a document for proposing technical improvements
development2
flowai-skill-write-dep
Writing a Development Enhancement Proposal (DEP) - a document for proposing technical improvements
development2
flowai-skill-write-prd
Guidelines for writing comprehensive Product Requirements Documents (PRD)
documentation2
flowai-skill-browser-automation
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
tools2
flowai-skill-interactive-teaching-materials
Creates interactive HTML teaching materials with clickable state diagrams. Use when the user asks to produce an explorable tutorial artifact, not to answer a question.
tools2
flowai-skill-browser-automation
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
tools2
flowai-skill-engineer-prompts-for-instant
Guide for writing stable, effective prompts for instant/fast models (Gemini Flash, GPT-4o Mini, Haiku), suitable for beginners.
documentation2
flowai-skill-engineer-prompts-for-reasoning
Guide for writing prompts for reasoning/smart models (Gemini Pro, GPT-4o, Claude 3.5 Sonnet), focused on structure and context.
documentation2
flowai-skill-write-in-informational-style
How to write in informational style
development2
flowai-skill-write-prd
Guidelines for writing comprehensive Product Requirements Documents (PRD)
documentation2
flowai-skill-write-in-informational-style
How to write in informational style
development2
flowai-skill-setup-agent-code-style-ts-deno
Use when the user asks to add Deno/TypeScript code-style rules to AGENTS.md, or during initial Deno project setup when code-style guidelines need to be established. Do NOT trigger for non-Deno TypeScript projects (use flowai-skill-setup-agent-code-style-ts-strict), or for runtime-agnostic style advice.
development2
flowai-skill-diagnose-benchmark-failure
Use when a flowai benchmark fails and you need the cause from run artifacts before editing. Reads judge-evidence.md, the sandbox SKILL.md, and scenario mod.ts; classifies the failure against a known taxonomy; produces an evidence-grounded report (no fixes). Do NOT trigger for passing benchmarks or generic skill iteration.
data-ai2
flowai-skill-memex-audit
Use when the user asks to audit a memex (long-term knowledge bank for AI agents) for orphans, dead wikilinks, missing sections, contradictions, or index drift. Runs a deterministic structural check, layers LLM-judgement findings, optionally auto-fixes trivial issues with `--fix`. Do NOT trigger on general code linting.
development2
flowai-skill-memex-save
Use when the user provides a source (URL, file path, or free text) to save into the project's memex — a long-term knowledge bank for AI agents. Stores the raw source, extracts entities into cross-linked pages, runs a backlink audit, and updates the index and activity log. Do NOT trigger on casual reads; only when the intent is to persist a source into the memex.
testing2
flowai-skill-setup-agent-code-style-ts-strict
Use when the user asks to add TypeScript strict-mode code-style rules to AGENTS.md for a TypeScript project using strict mode. Do NOT trigger for Deno projects (use flowai-skill-setup-agent-code-style-ts-deno) or non-strict TS configurations.
development2
flowai-skill-manage-github-tickets
Create and manage GitHub issues using the GODS framework. Use when creating, updating, or triaging GitHub issues.
development2
flowai-skill-setup-agent-code-style-ts-strict
Use when the user asks to add TypeScript strict-mode code-style rules to AGENTS.md for a TypeScript project using strict mode. Do NOT trigger for Deno projects (use flowai-skill-setup-agent-code-style-ts-deno) or non-strict TS configurations.
development2
flowai-skill-memex-ask
Use when the user asks a question to be answered from the project's memex (long-term knowledge bank for AI agents) rather than training data or the live web. Reads the index, opens relevant pages, follows one wikilink hop, synthesises a cited answer, files it back. Do NOT trigger on source-code or live-session questions.
development2
flowai-skill-memex-audit
Use when the user asks to audit a memex (long-term knowledge bank for AI agents) for orphans, dead wikilinks, missing sections, contradictions, or index drift. Runs a deterministic structural check, layers LLM-judgement findings, optionally auto-fixes trivial issues with `--fix`. Do NOT trigger on general code linting.
development2
flowai-investigate
Iterative issue investigation with user-controlled hypothesis selection
data-ai2
audit
Use when the user asks to audit a memex (long-term knowledge bank for AI agents) for orphans, dead SALP REFs, missing sections, contradictions, or index drift. Runs a deterministic structural check, layers LLM-judgement findings, optionally auto-fixes trivial issues with `--fix`. Do NOT trigger on general code linting.
development2
flowai-jit-review
Use when the user asks for a JIT review, wants to catch hidden regressions in a staged/unstaged diff or commit range, or says "check my changes for hidden bugs". Synthesizes ephemeral Catching JiTTests (pass on parent, fail on diff). Not for fixing known failing tests (see flowai-fix-tests) or general code review (flowai-review).
development2
flowai-init
Initialize project with AGENTS.md and rules, handling both Greenfield (new) and Brownfield (existing) projects.
data-ai2
flowai-skill-plan
Use ONLY when the user explicitly asks to plan a task, create a task file in documents/tasks/, produce a GODS-format breakdown, or prepare a critiqued implementation strategy before coding. Do NOT trigger on brief design discussion, ad-hoc code suggestions, or casual "how would you approach X?" questions.
development2
flowai-skill-plan-adr
Record an architectural decision (chosen path + rejected alternatives + rationale) as a persistent MADR-style ADR in documents/adr/. Triggers — "record this decision", "write an ADR", "capture our rationale for picking X", "запиши ADR". Do NOT use for regular task planning (use flowai-skill-plan), already-decided trivial choices, or simple bug fixes.
testing2
flowai-skill-conduct-qa-session
How to conduct a Q&A session with the user. Canonical reference for FR-UNIVERSAL.QA-FORMAT.
development2
write-agent-benchmarks
Create, maintain, and run evidence-based benchmarks for AI agents. Use when setting up testing infrastructure, writing new test scenarios, or evaluating agent performance.
testing2
flowai-plan
Create critiqued plan in documents/tasks/ using GODS framework with proactive uncertainty resolution
development2
flowai-reflect-by-history
Analyze previous IDE session history to find recurring patterns in agent behavior, identify systemic issues, and propose improvements to project primitives (rules, skills, hooks). Use when the user asks to review past sessions, find recurring problems, or improve development workflow based on historical data.
development2
flowai-review
Review current changes as QA engineer and lead engineer simultaneously: verify task completion, code quality, architecture, and cleanup.
development2
flowai-review
Review current changes as QA engineer and lead engineer simultaneously: verify task completion, code quality, architecture, and cleanup.
development2
flowai-answer
Analyze and answer user questions in Autonomous Mode by reading documentation and inspecting codebase
development2
flowai-answer
Analyze and answer user questions in Autonomous Mode by reading documentation and inspecting codebase
development2
flowai-reflect
Analyze agent's process, logic, technical decisions, context usage, and undocumented discoveries to find behavioral errors, poor engineering choices, inefficiencies, and missing knowledge in project instructions.
testing2
flowai-do-with-plan
Self-contained — execute the inlined steps directly. Three-phase full-cycle workflow: write a committed plan, implement under TDD, then review and commit with a verdict gate. Do NOT invoke other skills via the Skill tool.
tools2
investigate
Use when the user asks to diagnose a bug, find the root cause of a failing behavior, or run a controlled hypothesis-by-hypothesis investigation with experiments and evidence. Produces a diagnostic report with a recommended fix (but does not apply the fix). Do NOT trigger on "fix this bug" when the cause is obvious, or on simple error-message lookups.
data-ai2
configure-deno-commands
Configure and maintain Deno development commands (check, test, dev, prod). Use when the user wants to set up or update the standard command interface in deno.json and scripts/ directory.
development2
reflect-by-history
Use when the user asks to review PAST sessions (not the current one), find recurring patterns across multiple sessions, or improve project primitives (rules, skills, hooks, docs) based on historical IDE transcripts. Do NOT trigger on current-session self-review — use reflect instead.
documentation2
configure-deno-commands
Configure and maintain Deno development commands (check, test, dev, prod). Use when the user wants to set up or update the standard command interface in deno.json and scripts/ directory.
development2
plan
Use ONLY when the user explicitly asks to plan a task, create a task file in documents/tasks/, produce a GODS-format breakdown, or prepare a critiqued implementation strategy before coding. Do NOT trigger on brief design discussion, ad-hoc code suggestions, or casual "how would you approach X?" questions.
development2
investigate
Use when the user asks to diagnose a bug, find the root cause of a failing behavior, or run a controlled hypothesis-by-hypothesis investigation with experiments and evidence. Produces a diagnostic report with a recommended fix (but does not apply the fix). Do NOT trigger on "fix this bug" when the cause is obvious, or on simple error-message lookups.
data-ai2
cli
Manage all Deno capabilities via CLI (run, test, fmt, lint, task, add, etc.). Use this skill when you need to execute Deno commands, manage dependencies, run tests, or handle local development workflows.
tools2
deploy
Manage Deno Deploy cloud services using both `deno deploy` and `deployctl`. Use this skill for deploying projects, managing cloud environments (Build/Dev/Prod contexts), monitoring logs, and troubleshooting deployment issues (like private npm dependencies).
development2
engineer-command
Guide for creating effective flowai commands. This skill should be used when users want to create a new command (or update an existing command) that extends flowai's capabilities with specialized knowledge, workflows, or tool integrations. Works across IDEs (Cursor, Claude Code, OpenCode).
tools2
flowai-maintenance
Two-phase "Lead Engineer" audit: full scan across 8 categories, then interactive issue-by-issue resolution with the user.
development2
extract-claude-code-prompt
Extract Claude Code system prompt from its compiled binary or JS bundle into a structured template file. Produces a document mirroring the real API request with exact prompt text, ant-only variants, feature-gated sections, and minified-variable mappings. Use when extracting, documenting, or comparing Claude Code prompt versions.
development2
flowai-engineer-hook
Creation and configuration of event hooks/plugins to manage agent behavior, command filtering, auditing, and automation. Works across IDEs (Cursor, Claude Code, OpenCode). Use when you need to: (1) Create a new hook (e.g., for formatting or security checks), (2) Configure hooks/plugins, (3) Implement logic for blocking or modifying agent actions via scripts.
tools2
flowai-setup-agent-code-style-ts-deno
Adds TypeScript/Deno code style rules to project AGENTS.md. Use when setting up new Deno projects or when user needs to establish code style guidelines.
development2
adapt
Adapt project-local flowai primitives (skills, agents, AGENTS.md artifacts, hooks) to project specifics. Standalone adaptation — independent of update.
testing2
flowai-write-prd
Guidelines for writing comprehensive Product Requirements Documents (PRD)
documentation2
flowai-memex-save
Use when the user provides a source (URL, file path, or free text) to save into the project's memex — a long-term knowledge bank for AI agents. Stores the raw source, extracts entities into cross-linked pages, runs a backlink audit, and updates the index and activity log. Do NOT trigger on casual reads; only when the intent is to persist a source into the memex.
testing2
flowai-write-gods-tasks
How to write tasks using GODS framework
development2
flowai-interactive-teaching-materials
Creates interactive HTML teaching materials with clickable state diagrams. Use when the user asks to produce an explorable tutorial artifact, not to answer a question.
tools2
flowai-manage-github-tickets
Create and manage GitHub issues using the GODS framework. Use when creating, updating, or triaging GitHub issues.
development2
flowai-write-prd
Guidelines for writing comprehensive Product Requirements Documents (PRD)
documentation2
flowai-analyze-context
Analyze total token usage including conversation history, system prompts, and active rules to estimate cost.
data-ai2
flowai-browser-automation
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
tools2
flowai-deep-research
Multi-directional deep research with sub-agents, scoring, source verification, and cited synthesis. Use for comprehensive research, deep analysis, or evidence-backed answers. Produces executive summary + markdown report. Supports search tools, playwright-cli, and MCP.
tools2
flowai-scaffold
Scaffold flowai-workflow in a project. Runs `flowai-workflow init` to copy a bundled workflow (github-inbox, autonomous-sdlc, etc.) into .flowai-workflow/<name>/, then adapts workflow.yaml and agents/agent-*.md to project specifics. Use when asked to add flowai-workflow, scaffold a new DAG workflow, or create an agent pipeline.
testing2
adapt
Adapt project-local flowai primitives (skills, agents, AGENTS.md artifacts, hooks) to project specifics. Standalone adaptation — independent of update.
testing2
flowai-scaffold
Scaffold flowai-workflow in a project. Runs `flowai-workflow init` to copy a bundled workflow (github-inbox, autonomous-sdlc, etc.) into .flowai-workflow/<name>/, then adapts workflow.yaml and agents/agent-*.md to project specifics. Use when asked to add flowai-workflow, scaffold a new DAG workflow, or create an agent pipeline.
testing2
flowai-supervise
Supervise a flowai-workflow run. Launches `flowai-workflow run <workflow>`, polls runs/<run-id>/state.json every 30 s, and on node failure or stall diagnoses the root cause from artifacts, applies a fix to workflow.yaml or an agent prompt, then resumes via --resume. Use when asked to babysit a flowai-workflow run or iterate fix-and-resume autonomously.
data-ai2
flowai-engineer-rule
Guide for creating persistent AI rules (coding standards, project conventions, file-specific patterns). Use when users want to create a rule, add coding standards, set up project conventions, configure file-specific patterns, or ask about rules placement. Works across IDEs (Cursor, Claude Code, OpenCode).
development2
flowai-engineer-skill
Guide for creating effective Agent Skills (SKILL.md packages). Use when users want to create a new skill, write a skill, author a SKILL.md, or ask about skill structure, best practices, or skill file format. Works across IDEs (Cursor, Claude Code, OpenCode).
development2
flowai-engineer-prompts-for-reasoning
Guide for writing prompts for reasoning/smart models (Gemini Pro, GPT-4o, Claude 3.5 Sonnet), focused on structure and context.
documentation2
flowai-fix-tests
How to fix tests
testing2
flowai-jit-review
Use when the user asks for a JIT review, wants to catch hidden regressions in a staged/unstaged diff or commit range, or says "check my changes for hidden bugs". Synthesizes ephemeral Catching JiTTests (pass on parent, fail on diff). Not for fixing known failing tests (see flowai-fix-tests) or general code review (flowai-review).
development2
flowai-engineer-subagent
Guide for creating effective Subagents (custom agent definitions). Use when users want to create a new subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants. Works across IDEs (Cursor, OpenCode).
development2
flowai-engineer-prompts-for-instant
Guide for writing stable, effective prompts for instant/fast models (Gemini Flash, GPT-4o Mini, Haiku), suitable for beginners.
documentation2
flowai-engineer-rule
Guide for creating persistent AI rules (coding standards, project conventions, file-specific patterns). Use when users want to create a rule, add coding standards, set up project conventions, configure file-specific patterns, or ask about rules placement. Works across IDEs (Cursor, Claude Code, OpenCode).
development2
flowai-engineer-skill
Guide for creating effective Agent Skills (SKILL.md packages). Use when users want to create a new skill, write a skill, author a SKILL.md, or ask about skill structure, best practices, or skill file format. Works across IDEs (Cursor, Claude Code, OpenCode).
development2
flowai-ai-ide-runner
Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from the current session — pick one IDE, fan out across several, or compare models. You are a courier that relays the other runtime's stdout verbatim, do not synthesise your own answer. Use on "run in <ide>", "compare <ide> vs <ide>", "try on <model>", "which IDE handles X better", "run across models".
tools2
flowai-analyze-context
Analyze total token usage including conversation history, system prompts, and active rules to estimate cost.
data-ai2
flowai-review
Use when the user asks to review CURRENT uncommitted changes (staged, unstaged, or branch diff) as QA + lead engineer before committing — verdict on task completion, code quality, architecture, cleanup. Requires an existing diff. Do NOT trigger on generic "is this code good?" questions without a diff, or on post-merge code review of historical commits.
development2
django-migrations
Manage Django database migrations (makemigrations, migrate, squash).
development2
flowai-reflect-by-history
Analyze previous IDE session history to find recurring patterns in agent behavior, identify systemic issues, and propose improvements to project primitives (rules, skills, hooks). Use when the user asks to review past sessions, find recurring problems, or improve development workflow based on historical data.
development2
flowai-write-gods-tasks
How to write tasks using GODS framework
development2
flowai-skill-reflect-by-history
Use when the user asks to review PAST sessions (not the current one), find recurring patterns across multiple sessions, or improve project primitives (rules, skills, hooks, docs) based on historical IDE transcripts. Do NOT trigger on current-session self-review — use flowai-skill-reflect instead.
documentation2
flowai-engineer-subagent
Guide for creating effective Subagents (custom agent definitions). Use when users want to create a new subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants. Works across IDEs (Cursor, OpenCode).
development2
flowai-skill-adapt-instructions
Use when AGENTS.md is out of sync with the installed template (after `flowai sync` reports it changed, or user asks to re-adapt/realign AGENTS.md). Reads {ide}/assets/AGENTS.template.md, proposes a merge preserving project sections, writes on approval. Do NOT trigger on small edits.
documentation2
flowai-review-and-commit
Streamlined two-phase workflow: review, then commit. Verdict gate between phases. Self-contained — execute the inlined steps directly, do NOT invoke other skills via the Skill tool.
tools2
flowai-delegate-to-ide
Delegate a task to another AI IDE's CLI (codex / claude / opencode / cursor-agent) through an isolated-context subagent. Triggers on "delegate to <ide>", "have <ide> do <task>", "execute <task> in <ide>", "offload to <ide>". For one-shot relay or fan-out comparison use `flowai-ai-ide-runner` instead.
tools2
flowai-skill-engineer-skill
Guide for creating effective Agent Skills (SKILL.md packages). Use when users want to create a new skill, write a skill, author a SKILL.md, or ask about skill structure, best practices, or skill file format. Works across IDEs (Cursor, Claude Code, OpenCode).
development2
engineer-command
Guide for creating effective flowai commands. This skill should be used when users want to create a new command (or update an existing command) that extends flowai's capabilities with specialized knowledge, workflows, or tool integrations. Works across IDEs (Cursor, Claude Code, OpenCode).
tools2
flowai-skill-manage-github-tickets
Create and manage GitHub issues using the GODS framework. Use when creating, updating, or triaging GitHub issues.
development2
write-agent-benchmarks
Create, maintain, and run evidence-based benchmarks for AI agents. Use when setting up testing infrastructure, writing new test scenarios, or evaluating agent performance.
testing2
flowai-write-in-informational-style
How to write in informational style
development2
flowai-skill-reflect
Use when the user asks to reflect on the CURRENT session, analyze the agent's own process, audit context usage in this conversation, or extract lessons from how the current task was executed. Do NOT trigger for historical multi-session analysis — use flowai-skill-reflect-by-history for that. Do NOT trigger on plain "what did you do?" style recaps.
testing2
flowai-skill-fix-tests
How to fix tests
testing2
flowai-ai-ide-runner
Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from the current session — pick one IDE, fan out across several, or compare models. You are a courier that relays the other runtime's stdout verbatim, do not synthesise your own answer. Use on "run in <ide>", "compare <ide> vs <ide>", "try on <model>", "which IDE handles X better", "run across models".
tools2
flowai-skill-epic
Use when the user asks to plan a LARGE feature that spans multiple sessions or phases — produces documents/tasks/<YYYY>/<MM>/epic-<name>.md with dependency-ordered phases, atomic tasks, and per-phase status tracking. Use flowai-skill-plan for single-session tasks. Do NOT trigger on generic planning, roadmap, or brainstorming requests.
documentation2
ai-skel-ts-usage
Scaffold a complete AI agent application skeleton with LLM integration, tool calling, observability, cost tracking, session management, and content fetching using @korchasa/ai-skel-ts. Use when the user asks to create an AI agent, add LLM integration, scaffold an AI application, or mentions "ai-skel", "agent skeleton", or "AI scaffold". Works with any programming language.
tools2
flowai-skill-review
Use when the user asks to review CURRENT uncommitted changes (staged, unstaged, or branch diff) as QA + lead engineer before committing — verdict on task completion, code quality, architecture, cleanup. Requires an existing diff. Do NOT trigger on generic "is this code good?" questions without a diff, or on post-merge code review of historical commits.
development2
epic
Use when the user asks to plan a LARGE feature that spans multiple sessions or phases — produces an epic under the `tasks` role from AGENTS.md with dependency-ordered phases, atomic tasks, and per-phase status tracking. Use plan for single-session tasks. Do NOT trigger on generic planning, roadmap, or brainstorming requests.
data-ai2
flowai-review-and-commit-beta
Streamlined two-phase workflow: review, then commit. Verdict gate between phases. Self-contained — execute the inlined steps directly, do NOT invoke other skills via the Skill tool.
tools2
flowai-skill-jit-review
Use when the user asks for a JIT review, wants to catch hidden regressions in a staged/unstaged diff or commit range, or says "check my changes for hidden bugs". Synthesizes ephemeral Catching JiTTests (pass on parent, fail on diff). Not for fixing known failing tests (see flowai-skill-fix-tests) or general code review (flowai-skill-review).
development2
flowai-skill-write-gods-tasks
How to write tasks using GODS framework
development2
flowai-adapt-instructions
Use when AGENTS.md is out of sync with the installed template (after `flowai sync` reports it changed, or user asks to re-adapt/realign AGENTS.md). Reads {ide}/assets/AGENTS.template.md, proposes a merge preserving project sections, writes on approval. Do NOT trigger on small edits.
documentation2
flowai-maintenance
Use when the user asks for a project health audit, maintenance sweep, or multi-category lead-engineer scan followed by interactive issue-by-issue resolution with user approval. Do NOT trigger on routine lint/test runs, single-file cleanups, or standard "check project" requests.
development2
flowai-setup-agent-code-style-ts-deno
Use when the user asks to add Deno/TypeScript code-style rules to AGENTS.md, or during initial Deno project setup when code-style guidelines need to be established. Do NOT trigger for non-Deno TypeScript projects (use flowai-setup-agent-code-style-ts-strict), or for runtime-agnostic style advice.
development2
flowai-investigate
Use when the user asks to diagnose a bug, find the root cause of a failing behavior, or run a controlled hypothesis-by-hypothesis investigation with experiments and evidence. Produces a diagnostic report with a recommended fix (but does not apply the fix). Do NOT trigger on "fix this bug" when the cause is obvious, or on simple error-message lookups.
data-ai2
flowai-skill-engineer-command
Guide for creating effective flowai commands. This skill should be used when users want to create a new command (or update an existing command) that extends flowai's capabilities with specialized knowledge, workflows, or tool integrations. Works across IDEs (Cursor, Claude Code, OpenCode).
tools2
flowai-deno-cli
Manage all Deno capabilities via CLI (run, test, fmt, lint, task, add, etc.). Use this skill when you need to execute Deno commands, manage dependencies, run tests, or handle local development workflows.
tools2
flowai-memex-audit
Use when the user asks to audit a memex (long-term knowledge bank for AI agents) for orphans, dead wikilinks, missing sections, contradictions, or index drift. Runs a deterministic structural check, layers LLM-judgement findings, optionally auto-fixes trivial issues with `--fix`. Do NOT trigger on general code linting.
development2
bench-all
Run all framework benchmarks. Default is sequential (single `deno task bench`). Use `--parallel` for 5-subagent parallel mode. Triggers on "run all benchmarks", "bench all", "/bench-all".
development2
plan
Use ONLY when the user explicitly asks to plan a task, create a task file in documents/tasks/, produce a GODS-format breakdown, or prepare a critiqued implementation strategy before coding. Do NOT trigger on brief design discussion, ad-hoc code suggestions, or casual "how would you approach X?" questions.
development2
flowai-setup-agent-code-style-ts-strict
Use when the user asks to add TypeScript strict-mode code-style rules to AGENTS.md for a TypeScript project using strict mode. Do NOT trigger for Deno projects (use flowai-setup-agent-code-style-ts-deno) or non-strict TS configurations.
development2
ai-ide-runner
Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from the current session — pick one IDE, fan out across several, or compare models. You are a courier that relays the other runtime's stdout verbatim, do not synthesise your own answer. Use on "run in <ide>", "compare <ide> vs <ide>", "try on <model>", "which IDE handles X better", "run across models".
tools2
flowai-engineer-command
Guide for creating effective flowai commands. This skill should be used when users want to create a new command (or update an existing command) that extends flowai's capabilities with specialized knowledge, workflows, or tool integrations. Works across IDEs (Cursor, Claude Code, OpenCode).
tools2
flowai-supervise
Supervise a flowai-workflow run. Launches `flowai-workflow run <workflow>`, polls runs/<run-id>/state.json every 30 s, and on node failure or stall diagnoses the root cause from artifacts, applies a fix to workflow.yaml or an agent prompt, then resumes via --resume. Use when asked to babysit a flowai-workflow run or iterate fix-and-resume autonomously.
data-ai2
flowai-skill-setup-agent-code-style-ts-deno
Use when the user asks to add Deno/TypeScript code-style rules to AGENTS.md, or during initial Deno project setup when code-style guidelines need to be established. Do NOT trigger for non-Deno TypeScript projects (use flowai-skill-setup-agent-code-style-ts-strict), or for runtime-agnostic style advice.
development2
flowai-draw-mermaid-diagrams
Draw and edit Mermaid diagrams in Markdown. Use when the user wants to visualize processes, flows, sequences, or asks for diagrams.
data-ai2
flowai-update
Reconcile project-owned AGENTS.md, CLAUDE.md, and scaffolded artifacts with the current flowai framework templates.
development2
flowai-memex-save
Use when the user provides a source (URL, file path, or free text) to save into the project's memex — a long-term knowledge bank for AI agents. Stores the raw source, extracts entities into cross-linked pages, runs a backlink audit, and updates the index and activity log. Do NOT trigger on casual reads; only when the intent is to persist a source into the memex.
testing2
flowai-skill-engineer-subagent
Guide for creating effective Subagents (custom agent definitions). Use when users want to create a new subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants. Works across IDEs (Cursor, OpenCode).
development2
flowai-adapt-instructions
Use when AGENTS.md is out of sync with the installed template (after `flowai sync` reports it changed, or user asks to re-adapt/realign AGENTS.md). Reads {ide}/assets/AGENTS.template.md, proposes a merge preserving project sections, writes on approval. Do NOT trigger on small edits.
documentation2
flowai-manage-github-tickets
Create and manage GitHub issues using the GODS framework. Use when creating, updating, or triaging GitHub issues.
development2
browser-automation
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
tools2
flowai-plan-exp-permanent-tasks
Experimental committed-tasks variant of flowai-plan. User-invoked. Writes tasks at documents/tasks/<YYYY>/<MM>/<slug>.md with extended frontmatter (date, status, implements, tags, related_tasks).
documentation2
flowai-skill-memex-save
Use when the user provides a source (URL, file path, or free text) to save into the project's memex — a long-term knowledge bank for AI agents. Stores the raw source, extracts entities into cross-linked pages, runs a backlink audit, and updates the index and activity log. Do NOT trigger on casual reads; only when the intent is to persist a source into the memex.
testing2
flowai-skill-interactive-teaching-materials
Creates interactive HTML teaching materials with clickable state diagrams. Use when the user asks to produce an explorable tutorial artifact, not to answer a question.
tools2
flowai-investigate
Iterative issue investigation with user-controlled hypothesis selection
data-ai2
flowai-skill-engineer-hook
Creation and configuration of event hooks/plugins to manage agent behavior, command filtering, auditing, and automation. Works across IDEs (Cursor, Claude Code, OpenCode). Use when you need to: (1) Create a new hook (e.g., for formatting or security checks), (2) Configure hooks/plugins, (3) Implement logic for blocking or modifying agent actions via scripts.
tools2
flowai-skill-write-agent-benchmarks
Create, maintain, and run evidence-based benchmarks for AI agents. Use when setting up testing infrastructure, writing new test scenarios, or evaluating agent performance.
testing2
flowai-skill-ai-ide-runner
Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from the current session — pick one IDE, fan out across several, or compare models. You are a courier that relays the other runtime's stdout verbatim, do not synthesise your own answer. Use on "run in <ide>", "compare <ide> vs <ide>", "try on <model>", "which IDE handles X better", "run across models".
tools2
ask
Use when the user asks a question to be answered from the project's memex (long-term knowledge bank for AI agents) rather than training data or the live web. Reads the index, opens relevant pages, follows one SALP-REF hop, synthesises a cited answer, files it back. Do NOT trigger on source-code or live-session questions.
development2
flowai-epic
Create structured epic for large features using phased decomposition. Produces documents/tasks/epic-{name}.md with dependency-ordered phases, atomic tasks, explicit boundaries, and per-phase status tracking.
testing2
delegate-to-ide
Delegate a task to another AI IDE's CLI (codex / claude / opencode / cursor-agent) through an isolated-context subagent. Triggers on "delegate to <ide>", "have <ide> do <task>", "execute <task> in <ide>", "offload to <ide>". For one-shot relay or fan-out comparison use `ai-ide-runner` instead.
tools2
deploy
Manage Deno Deploy cloud services using both `deno deploy` and `deployctl`. Use this skill for deploying projects, managing cloud environments (Build/Dev/Prod contexts), monitoring logs, and troubleshooting deployment issues (like private npm dependencies).
development2
flowai-skill-conduct-qa-session
How to conduct a Q&A session with the user. Canonical reference for FR-UNIVERSAL.QA-FORMAT.
development2
flowai-engineer-hook
Creation and configuration of event hooks/plugins to manage agent behavior, command filtering, auditing, and automation. Works across IDEs (Cursor, Claude Code, OpenCode). Use when you need to: (1) Create a new hook (e.g., for formatting or security checks), (2) Configure hooks/plugins, (3) Implement logic for blocking or modifying agent actions via scripts.
tools2
ai-ide-runner
Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from the current session — pick one IDE, fan out across several, or compare models. You are a courier that relays the other runtime's stdout verbatim, do not synthesise your own answer. Use on "run in <ide>", "compare <ide> vs <ide>", "try on <model>", "which IDE handles X better", "run across models".
tools2
flowai-maintenance
Use when the user asks for a project health audit, maintenance sweep, or multi-category lead-engineer scan followed by interactive issue-by-issue resolution with user approval. Do NOT trigger on routine lint/test runs, single-file cleanups, or standard "check project" requests.
development2
engineer-hook
Creation and configuration of event hooks/plugins to manage agent behavior, command filtering, auditing, and automation. Works across IDEs (Cursor, Claude Code, OpenCode). Use when you need to: (1) Create a new hook (e.g., for formatting or security checks), (2) Configure hooks/plugins, (3) Implement logic for blocking or modifying agent actions via scripts.
tools2
flowai-adapt-instructions
Re-adapt AGENTS.md when the installed template changed. Reads {ide}/assets/AGENTS.template.md, diffs it against the project AGENTS.md, proposes a merge preserving project-specific sections, asks for confirmation, writes on approval. Use after `flowai sync` reports AGENTS.template.md changed.
testing2
flowai-adapt-instructions
Re-adapt AGENTS.md when the installed template changed. Reads {ide}/assets/AGENTS.template.md, diffs it against the project AGENTS.md, proposes a merge preserving project-specific sections, asks for confirmation, writes on approval. Use after `flowai sync` reports AGENTS.template.md changed.
testing2
flowai-plan-exp-permanent-tasks
Experimental committed-tasks variant of flowai-plan. User-invoked. Writes tasks at documents/tasks/<YYYY>/<MM>/<slug>.md with extended frontmatter (date, status, implements, tags, related_tasks).
documentation2
flowai-configure-deno-commands
Configure and maintain Deno development commands (check, test, dev, prod). Use when the user wants to set up or update the standard command interface in deno.json and scripts/ directory.
development2
flowai-init
Initialize project with AGENTS.md and rules, handling both Greenfield (new) and Brownfield (existing) projects.
data-ai2
flowai-commit
Automated commit workflow with atomic grouping
data-ai2
flowai-review
Use when the user asks to review CURRENT uncommitted changes (staged, unstaged, or branch diff) as QA + lead engineer before committing — verdict on task completion, code quality, architecture, cleanup. Requires an existing diff. Do NOT trigger on generic "is this code good?" questions without a diff, or on post-merge code review of historical commits.
development2
flowai-reflect
Use when the user asks to reflect on the CURRENT session, analyze the agent's own process, audit context usage in this conversation, or extract lessons from how the current task was executed. Do NOT trigger for historical multi-session analysis — use flowai-reflect-by-history for that. Do NOT trigger on plain "what did you do?" style recaps.
testing2
flowai-review-and-commit
Streamlined two-phase workflow: review, then commit. Verdict gate between phases. Self-contained — execute the inlined steps directly, do NOT invoke other skills via the Skill tool.
tools2
flowai-adapt
Adapt project-local flowai primitives (skills, agents, AGENTS.md artifacts, hooks) to project specifics. Standalone adaptation — independent of flowai-update.
testing2
flowai-plan
Use ONLY when the user explicitly asks to plan a task, create a task file in documents/tasks/, produce a GODS-format breakdown, or prepare a critiqued implementation strategy before coding. Do NOT trigger on brief design discussion, ad-hoc code suggestions, or casual "how would you approach X?" questions.
development2
flowai-reflect-by-history
Use when the user asks to review PAST sessions (not the current one), find recurring patterns across multiple sessions, or improve project primitives (rules, skills, hooks, docs) based on historical IDE transcripts. Do NOT trigger on current-session self-review — use flowai-reflect instead.
documentation2
flowai-plan
Use ONLY when the user explicitly asks to plan a task, create a task file in documents/tasks/, produce a GODS-format breakdown, or prepare a critiqued implementation strategy before coding. Do NOT trigger on brief design discussion, ad-hoc code suggestions, or casual "how would you approach X?" questions.
development2
flowai-deno-deploy
Manage Deno Deploy cloud services using both `deno deploy` and `deployctl`. Use this skill for deploying projects, managing cloud environments (Build/Dev/Prod contexts), monitoring logs, and troubleshooting deployment issues (like private npm dependencies).
development2
flowai-commit-beta
Streamlined commit workflow — fewer tool calls, targeted doc sync
tools2
flowai-do-with-plan
Self-contained — execute the inlined steps directly. Three-phase full-cycle workflow: write a committed plan, implement under TDD, then review and commit with a verdict gate. Do NOT invoke other skills via the Skill tool.
tools2
ai-skel-ts-usage
Scaffold a complete AI agent application skeleton with LLM integration, tool calling, observability, cost tracking, session management, and content fetching using @korchasa/ai-skel-ts. Use when the user asks to create an AI agent, add LLM integration, scaffold an AI application, or mentions "ai-skel", "agent skeleton", or "AI scaffold". Works with any programming language.
tools2
flowai-update
Reconcile project-owned AGENTS.md, CLAUDE.md, and scaffolded artifacts with the current flowai framework templates.
development2
flowai-reflect
Analyze agent's process, logic, technical decisions, context usage, and undocumented discoveries to find behavioral errors, poor engineering choices, inefficiencies, and missing knowledge in project instructions.
testing2
flowai-configure-deno-commands
Configure and maintain Deno development commands (check, test, dev, prod). Use when the user wants to set up or update the standard command interface in deno.json and scripts/ directory.
development2
flowai-setup-ai-ide-devcontainer
Set up .devcontainer for AI IDE development. Generates devcontainer.json and optional Dockerfile for project tech stack, AI CLI integration (Claude Code, OpenCode, flowai), skill mounting, and security hardening.
tools2
flowai-epic
Use when the user asks to plan a LARGE feature that spans multiple sessions or phases — produces documents/tasks/<YYYY>/<MM>/epic-<name>.md with dependency-ordered phases, atomic tasks, and per-phase status tracking. Use flowai-plan for single-session tasks. Do NOT trigger on generic planning, roadmap, or brainstorming requests.
documentation2
flowai-setup-ai-ide-devcontainer
Set up .devcontainer for AI IDE development. Generates devcontainer.json and optional Dockerfile for project tech stack, AI CLI integration (Claude Code, OpenCode, flowai), skill mounting, and security hardening.
tools2
flowai-reflect-by-history
Use when the user asks to review PAST sessions (not the current one), find recurring patterns across multiple sessions, or improve project primitives (rules, skills, hooks, docs) based on historical IDE transcripts. Do NOT trigger on current-session self-review — use flowai-reflect instead.
documentation2
flowai-reflect
Use when the user asks to reflect on the CURRENT session, analyze the agent's own process, audit context usage in this conversation, or extract lessons from how the current task was executed. Do NOT trigger for historical multi-session analysis — use flowai-reflect-by-history for that. Do NOT trigger on plain "what did you do?" style recaps.
testing2
flowai-investigate
Use when the user asks to diagnose a bug, find the root cause of a failing behavior, or run a controlled hypothesis-by-hypothesis investigation with experiments and evidence. Produces a diagnostic report with a recommended fix (but does not apply the fix). Do NOT trigger on "fix this bug" when the cause is obvious, or on simple error-message lookups.
data-ai2
flowai-engineer-command
Guide for creating effective flowai commands. This skill should be used when users want to create a new command (or update an existing command) that extends flowai's capabilities with specialized knowledge, workflows, or tool integrations. Works across IDEs (Cursor, Claude Code, OpenCode).
tools2
setup-agent-code-style-strict
Use when the user asks to add TypeScript strict-mode code-style rules to AGENTS.md for a TypeScript project using strict mode. Do NOT trigger for Deno projects (use setup-agent-code-style-deno) or non-strict TS configurations.
development2
flowai-skill-write-agent-benchmarks
Create, maintain, and run evidence-based benchmarks for AI agents. Use when setting up testing infrastructure, writing new test scenarios, or evaluating agent performance.
testing2
flowai-skill-draw-mermaid-diagrams
Draw and edit Mermaid diagrams in Markdown. Use when the user wants to visualize processes, flows, sequences, or asks for diagrams.
data-ai2
flowai-deno-cli
Manage all Deno capabilities via CLI (run, test, fmt, lint, task, add, etc.). Use this skill when you need to execute Deno commands, manage dependencies, run tests, or handle local development workflows.
tools2
flowai-skill-maintenance
Use when the user asks for a project health audit, maintenance sweep, or multi-category lead-engineer scan followed by interactive issue-by-issue resolution with user approval. Do NOT trigger on routine lint/test runs, single-file cleanups, or standard "check project" requests.
development2
flowai-maintenance
Two-phase "Lead Engineer" audit: full scan across 8 categories, then interactive issue-by-issue resolution with the user.
development2
flowai-skill-plan-adr
Record an architectural decision (chosen path + rejected alternatives + rationale) as a persistent MADR-style ADR in documents/adr/. Triggers — "record this decision", "write an ADR", "capture our rationale for picking X", "запиши ADR". Do NOT use for regular task planning (use flowai-skill-plan), already-decided trivial choices, or simple bug fixes.
testing2
flowai-skill-deno-cli
Manage all Deno capabilities via CLI (run, test, fmt, lint, task, add, etc.). Use this skill when you need to execute Deno commands, manage dependencies, run tests, or handle local development workflows.
tools2
flowai-skill-engineer-hook
Creation and configuration of event hooks/plugins to manage agent behavior, command filtering, auditing, and automation. Works across IDEs (Cursor, Claude Code, OpenCode). Use when you need to: (1) Create a new hook (e.g., for formatting or security checks), (2) Configure hooks/plugins, (3) Implement logic for blocking or modifying agent actions via scripts.
tools2
flowai-skill-draw-mermaid-diagrams
Draw and edit Mermaid diagrams in Markdown. Use when the user wants to visualize processes, flows, sequences, or asks for diagrams.
data-ai2
flowai-plan
Create critiqued plan in documents/tasks/ using GODS framework with proactive uncertainty resolution
development2
reflect-by-history
Use when the user asks to review PAST sessions (not the current one), find recurring patterns across multiple sessions, or improve project primitives (rules, skills, hooks, docs) based on historical IDE transcripts. Do NOT trigger on current-session self-review — use reflect instead.
documentation2
flowai-deno-deploy
Manage Deno Deploy cloud services using both `deno deploy` and `deployctl`. Use this skill for deploying projects, managing cloud environments (Build/Dev/Prod contexts), monitoring logs, and troubleshooting deployment issues (like private npm dependencies).
development2
update
Reconcile project-owned AGENTS.md, CLAUDE.md, and scaffolded artifacts with the current flowai framework templates.
development2
flowai-skill-engineer-command
Guide for creating effective flowai commands. This skill should be used when users want to create a new command (or update an existing command) that extends flowai's capabilities with specialized knowledge, workflows, or tool integrations. Works across IDEs (Cursor, Claude Code, OpenCode).
tools2
flowai-skill-jit-review
Use when the user asks for a JIT review, wants to catch hidden regressions in a staged/unstaged diff or commit range, or says "check my changes for hidden bugs". Synthesizes ephemeral Catching JiTTests (pass on parent, fail on diff). Not for fixing known failing tests (see flowai-skill-fix-tests) or general code review (flowai-skill-review).
development2
flowai-engineer-prompts-for-instant
Guide for writing stable, effective prompts for instant/fast models (Gemini Flash, GPT-4o Mini, Haiku), suitable for beginners.
documentation2
flowai-setup-agent-code-style-ts-deno
Adds TypeScript/Deno code style rules to project AGENTS.md. Use when setting up new Deno projects or when user needs to establish code style guidelines.
development2
flowai-skill-diagnose-benchmark-failure
Use when a flowai benchmark fails and you need the cause from run artifacts before editing. Reads judge-evidence.md, the sandbox SKILL.md, and scenario mod.ts; classifies the failure against a known taxonomy; produces an evidence-grounded report (no fixes). Do NOT trigger for passing benchmarks or generic skill iteration.
data-ai2
flowai-skill-write-gods-tasks
How to write tasks using GODS framework
development2
diagnose-benchmark-failure
Use when a flowai benchmark fails and you need the cause from run artifacts before editing. Reads judge-evidence.md, the sandbox SKILL.md, and scenario mod.ts; classifies the failure against a known taxonomy; produces an evidence-grounded report (no fixes). Do NOT trigger for passing benchmarks or generic skill iteration.
data-ai2
flowai-skill-adapt-instructions
Use when AGENTS.md is out of sync with the installed template (after `flowai sync` reports it changed, or user asks to re-adapt/realign AGENTS.md). Reads {ide}/assets/AGENTS.template.md, proposes a merge preserving project sections, writes on approval. Do NOT trigger on small edits.
documentation2
flowai-diagnose-benchmark-failure
Use when a flowai benchmark fails and you need the cause from run artifacts before editing. Reads judge-evidence.md, the sandbox SKILL.md, and scenario mod.ts; classifies the failure against a known taxonomy; produces an evidence-grounded report (no fixes). Do NOT trigger for passing benchmarks or generic skill iteration.
data-ai2
extract-claude-code-prompt
Extract Claude Code system prompt from its compiled binary or JS bundle into a structured template file. Produces a document mirroring the real API request with exact prompt text, ant-only variants, feature-gated sections, and minified-variable mappings. Use when extracting, documenting, or comparing Claude Code prompt versions.
development2
flowai-workflow-init
Initialize a new flowai-workflow project. Analyzes the codebase to detect project settings, asks the user to confirm or adjust, then scaffolds the .flowai-workflow/ directory.
development
orchestrate
Run the flowai-workflow orchestration policy loop. Delegates policy execution to the workflow orchestrator agent, which selects workflows from ORCHESTRATION.md and supervisor summaries.
data-ai
flow-answer
Analyze and answer user questions in Autonomous Mode by reading documentation and inspecting codebase
development
flow-skill-deno-deploy
Manage Deno Deploy cloud services using both `deno deploy` and `deployctl`. Use this skill for deploying projects, managing cloud environments (Build/Dev/Prod contexts), monitoring logs, and troubleshooting deployment issues (like private npm dependencies).
development
flow-skill-deep-research
Multi-directional deep research with sub-agents, scoring, source verification, and cited synthesis. Use for comprehensive research, deep analysis, or evidence-backed answers. Produces executive summary + markdown report. Supports search tools, playwright-cli, and MCP.
tools
flow-skill-write-in-informational-style
How to write in informational style
development
run
Execute a bundled or project-local flowai-workflow DAG. Use to launch a workflow run from inside the host IDE.
data-ai
init
Copy a bundled flowai-workflow into the user's project so they can adapt and run it locally. Use when the user wants to start using flowai-workflow in a new repo.
data-ai
flow-skill-engineer-prompts-for-reasoning
Guide for writing prompts for reasoning/smart models (Gemini Pro, GPT-4o, Claude 3.5 Sonnet), focused on structure and context.
documentation
flow-skill-engineer-subagent
Guide for creating effective Subagents (custom agent definitions). Use when users want to create a new subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants. Works across IDEs (Cursor, OpenCode).
development
flow-setup-agent-code-style-ts-deno
Adds TypeScript/Deno code style rules to project AGENTS.md. Use when setting up new Deno projects or when user needs to establish code style guidelines.
development
flowai-workflow-init
Initialize a new flowai-workflow project. Analyzes the codebase to detect project settings, asks the user to confirm or adjust, then scaffolds the .flowai-workflow/ directory.
development
ai-skel-ts-usage
Scaffold a complete AI agent application skeleton with LLM integration, tool calling, observability, cost tracking, session management, and content fetching using @korchasa/ai-skel-ts. Use when the user asks to create an AI agent, add LLM integration, scaffold an AI application, or mentions "ai-skel", "agent skeleton", or "AI scaffold". Works with any programming language.
tools
flow-review-and-commit
Composite command: review changes then commit only if approved. Inlines flow-review and flow-commit with a verdict gate between them.
tools
flow-skill-fix-tests
How to fix tests
testing
flowai-workflow-init
Initialize a new flowai-workflow project. Analyzes the codebase to detect project settings, asks the user to confirm or adjust, then scaffolds the .flowai-workflow/ directory.
development
flowai-workflow-adapt-agents
Adapt flowai-workflow agents to the current project after a framework update. Merges upstream agent changes with project-specific customizations.
development
flow-spec
Create structured specification for large features using phased decomposition. Produces documents/spec-{name}.md with dependency-ordered phases, atomic tasks, explicit boundaries, and per-phase status tracking.
testing
flow-skill-setup-ai-ide-devcontainer
Set up .devcontainer for AI IDE development. Generates devcontainer.json and optional Dockerfile for project tech stack, AI CLI integration (Claude Code, OpenCode), secrets, skill mounting, and security hardening. Use for AI-assisted devcontainer setup or flow-init delegation.
tools
flow-skill-engineer-prompts-for-instant
Guide for writing stable, effective prompts for instant/fast models (Gemini Flash, GPT-4o Mini, Haiku), suitable for beginners.
documentation
flow-skill-analyze-context
Analyze total token usage including conversation history, system prompts, and active rules to estimate cost.
data-ai
flow-skill-conduct-qa-session
How to conduct a Q&A session with the user
testing
flow-plan
Create critiqued plan in whiteboard.md using GODS framework with proactive uncertainty resolution
development
flow-init
Initialize project with AGENTS.md and rules, handling both Greenfield (new) and Brownfield (existing) projects.
data-ai
flow-reflect
Analyze agent's process, logic, technical decisions, context usage, and undocumented discoveries to find behavioral errors, poor engineering choices, inefficiencies, and missing knowledge in project instructions.
testing
create-requirement-ticket
Create GitHub issue as a requirement ticket: problem + requirements only, no implementation details. Use when user asks to create a ticket, issue, or task for a feature/fix/change.
data-ai
flow-skill-deno-cli
Manage all Deno capabilities via CLI (run, test, fmt, lint, task, add, etc.). Use this skill when you need to execute Deno commands, manage dependencies, run tests, or handle local development workflows.
tools
flow-skill-write-prd
Guidelines for writing comprehensive Product Requirements Documents (PRD)
documentation
flow-skill-write-dep
Writing a Development Enhancement Proposal (DEP) - a document for proposing technical improvements
development
flow-skill-playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction using playwright-cli. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
tools
flow-skill-draw-mermaid-diagrams
Draw and edit Mermaid diagrams in Markdown. Use when the user wants to visualize processes, flows, sequences, or asks for diagrams.
data-ai
flow-maintenance
Perform a comprehensive "Lead Engineer" audit: structure, consistency, code quality, technical debt, documentation coverage, and terminology checks.
development
flowai-workflow-adapt-agents
Adapt flowai-workflow agents to the current project after a framework update. Merges upstream agent changes with project-specific customizations.
development
flow-skill-cursor-agent-integration
Understand and interact with the cursor-agent CLI, including its output formats (JSON, text, stream-json), session management (resume), and integration with benchmarks. Use when working on cursor-agent CLI, benchmark runners, or automated agent interactions.
tools
flow-review
Review current changes as QA engineer and lead engineer simultaneously: verify task completion, code quality, architecture, and cleanup.
development
orchestrator
Long-cycle flowai-workflow orchestrator (Codex). Reads project orchestration policy, selects the next workflow, and returns a structured supervisor delegation request. Run inside an isolated Codex worker subagent spawned by the `orchestrate` skill.
development
supervise
Live flowai-workflow run supervisor. Use only for requests to run, monitor, continue, or resume a current workflow now. Exclude last-night, finished, post-mortem, root-cause-report, and conceptual questions.
data-ai
flow-investigate
Iterative issue investigation with user-controlled hypothesis selection
tools
supervise
Live flowai-workflow run supervisor. Use only for requests to run, monitor, continue, or resume a current workflow now. Exclude last-night, finished, post-mortem, root-cause-report, and conceptual questions.
data-ai
scaffold
Scaffold or adapt flowai-workflow DAGs in a project. Use for adding flowai-workflow, adapting an existing .flowai-workflow/<name>, validating workflow.yaml, or wiring agent prompts/scripts.
data-ai
run
Execute a bundled or project-local flowai-workflow DAG. Use to launch a workflow run from inside Claude Code without installing the CLI separately.
tools
flow-commit
Automated commit workflow with atomic grouping
tools
init
Copy a bundled flowai-workflow into the user's project so they can adapt and run it locally. Use when the user wants to start using flowai-workflow in a new repo.
data-ai
scaffold
Scaffold or adapt flowai-workflow DAGs in a project. Use for adding flowai-workflow, adapting an existing .flowai-workflow/<name>, validating workflow.yaml, or wiring agent prompts/scripts.
data-ai
flow-skill-engineer-command
Guide for creating effective AssistFlow commands. This skill should be used when users want to create a new command (or update an existing command) that extends AssistFlow's capabilities with specialized knowledge, workflows, or tool integrations. Works across IDEs (Cursor, Claude Code, OpenCode).
tools
flow-skill-engineer-skill
Guide for creating effective Agent Skills (SKILL.md packages). Use when users want to create a new skill, write a skill, author a SKILL.md, or ask about skill structure, best practices, or skill file format. Works across IDEs (Cursor, Claude Code, OpenCode).
development
flow-skill-configure-deno-commands
Configure and maintain Deno development commands (check, test, dev, prod). Use when the user wants to set up or update the standard command interface in deno.json and scripts/ directory.
development
flow-skill-ai-skel-ts
Scaffold a complete AI agent application skeleton with LLM integration, tool calling, observability, cost tracking, session management, and content fetching. Use when the user asks to create an AI agent, add LLM integration, scaffold an AI application, or mentions "ai-skel", "agent skeleton", or "AI scaffold". Works with any programming language.
tools
flowai-workflow-adapt-agents
Adapt flowai-workflow agents to the current project after a framework update. Merges upstream agent changes with project-specific customizations.
development
flow-skill-write-agent-benchmarks
Create, maintain, and run evidence-based benchmarks for AI agents. Use when setting up testing infrastructure, writing new test scenarios, or evaluating agent performance.
testing
orchestrate
Run the flowai-workflow orchestration policy loop. Delegates policy execution to the workflow orchestrator agent, which selects workflows from ORCHESTRATION.md and supervisor summaries.
data-ai
flow-skill-engineer-rule
Guide for creating persistent AI rules (coding standards, project conventions, file-specific patterns). Use when users want to create a rule, add coding standards, set up project conventions, configure file-specific patterns, or ask about rules placement. Works across IDEs (Cursor, Claude Code, OpenCode).
development
flow-skill-engineer-hook
Creation and configuration of event hooks/plugins to manage agent behavior, command filtering, auditing, and automation. Works across IDEs (Cursor, Claude Code, OpenCode). Use when you need to: (1) Create a new hook (e.g., for formatting or security checks), (2) Configure hooks/plugins, (3) Implement logic for blocking or modifying agent actions via scripts.
tools
supervisor
Supervisor for one flowai-workflow run (Codex). Starts or resumes a single workflow, diagnoses failures from run artifacts, patches root causes, resumes the same run. Run inside an isolated Codex worker subagent spawned by the `supervise`/`orchestrate` skill.
development
flow-skill-manage-github-tickets-by-mcp
How to manage GitHub tickets via MCP tools using the GODS framework. Use when creating, updating, or triaging GitHub issues.
tools
flow-setup-agent-code-style-ts-strict
Adds TypeScript strict mode code style rules to project AGENTS.md. Use when setting up TypeScript projects with strict mode or establishing coding standards.
development
flow-skill-write-gods-tasks
How to write tasks using GODS framework
development