
[Hyper] Optimize an existing codebase through baseline-first experiments, binary evaluation, and one-mutation-at-a-time iteration. Use for codebase autoresearch, measured bottleneck reduction, benchmarked code optimization, and evidence-backed refactors.
[Hyper] Analyze bugs, present repair options, then implement and verify the user-selected fix path. Routes simple bugs directly; tracks complex multi-phase investigations via .hypercore/bug-fix/ JSON flow.
[Hyper] Optimize an existing Codex skill through baseline-first experiments, binary evals, optional guards, and one-mutation-at-a-time iteration. Use for skill autoresearch, measured trigger/workflow improvement, self-optimizing a skill, benchmarking skill changes, or resuming skill experiment artifacts.
[Hyper] Use when the user explicitly wants Anthropic Claude Code CLI (`claude`) for an isolated session, non-interactive (`-p`) run, session resume by ID or name, or a CI-friendly `--bare` invocation. Trigger phrases: "use claude code", "ask claude", "run claude", "continue the last claude session", "resume the auth-refactor claude session", or "use Anthropic's CLI to inspect or fix this repo".
[Hyper] Convert colors between hex, rgb, and oklch using @kood/color-cli. Use when the user asks to convert colors, transform CSS file colors, or needs accurate oklch values. Trigger phrases — "color convert", "hex to oklch", "oklch to hex", "rgb to oklch", "CSS color conversion", "color conversion", "tell me the oklch value".
[Hyper] Diagnose and fix build failures, CI pipeline errors, and deployment errors across the entire repository or a specific folder. Routes simple build breaks directly; tracks complex multi-system failures via .hypercore/deploy-fix/ JSON flow.
[Hyper] Investigate websites with Playwriter plus CDP to choose a crawl strategy, capture API/auth evidence, document findings under `.hypercore/crawler/[site]/`, and generate crawler code only after discovery is grounded.
[Hyper] Immediately start working on a given task with adaptive thinking depth — light thinking for easy tasks, deep thinking for hard ones. Use when the user wants immediate execution, not diagnosis, planning, or review.
[Hyper] Create and refactor AI-readable docs, instruction bases, runbooks, specs, and harness-ready rule packs for context, prompt, tool, eval, sourcing, safety, and validation workflows.
[Hyper] Use when the user wants to invoke Google Gemini CLI (`gemini`) for reasoning, research, or AI assistance. Trigger phrases: "use gemini", "ask gemini", "run gemini", "call gemini", "gemini cli", "Google AI", "Gemini reasoning", or when users request Google's Gemini models, research with web search, plan-mode review, or want to resume a previous Gemini session. Do not use for generic writing, runbook cleanup, or local edits that do not require the Gemini CLI.
[Hyper] Create one or more Conventional Commits from the current repository state. Inspect staged and unstaged changes, group them into logical change sets, generate a compliant message per group, and commit each group separately in sequence.
[Hyper] Push unpushed commits to the remote. Discovers the current or descendant git repositories, checks for commits ahead of upstream, and pushes them. Use when the user wants to push, sync to remote, or send commits upstream.
[Hyper] Commit and push in one action, including from linked Git worktrees. Use when the user asks to commit and push together, save and push changes, or run `/git-maker`; it performs safe commit grouping first, then automatically pushes without a second confirmation.
[Hyper] Create, enter, list, remove, clean up, or repair Git worktrees for isolated branches and parallel agent sessions, including direct `git-worktree <ARGUMENT>` creation without follow-up questions. Use when the user asks for git worktree setup/removal, branch-per-folder workflows, parallel Codex/Claude/Cursor workspaces, or the repository-local `.hypercore/git-worktree/<folder_name>` convention; when creating and no argument/task is clear, ask what work will happen there in the user's language, derive the folder name, then move subsequent work into the new worktree.
[Hyper] Improve an existing code path, document, design, prompt, or skill by analyzing the target, running local multi-pass improvement reasoning, selecting a safe improvement path from user criteria or self-generated options, then editing and validating. Uses local reasoning only; no external reasoning MCP is required.
[Hyper] Use when working on Hono projects or adding Hono into a codebase. Enforces Hono architecture rules for app composition, route modules, middleware, validation, error handling, testing, and typed RPC boundaries before any code change.
[Hyper] Use when the user explicitly wants OpenAI Codex CLI (`codex`) for an isolated session, non-interactive run, code review, or session resume. Trigger phrases: 'use codex', 'ask codex', 'run codex', 'codex exec', 'codex review', 'continue the last codex session', or 'use OpenAI CLI to inspect or fix this repo'.
[Hyper] Use when working on Next.js projects, especially App Router or App Router migration work. Enforces current official Next.js architecture rules for project/folder structure, nested shared `lib` organization, route/file conventions, Server and Client Component boundaries, Cache Components and data freshness, Server Actions for internal UI writes, Route Handlers for HTTP-native endpoints, Proxy as a last resort, and platform/env safety.
[Hyper] Convert colors between hex, rgb, and oklch using @kood/color-cli. Use when the user asks to convert colors, transform CSS file colors, or needs accurate oklch values. Trigger phrases — "color convert", "hex to oklch", "oklch to hex", "rgb to oklch", "CSS color conversion", "color conversion", "tell me the oklch value".
[Hyper] Run deploy-readiness validation and fix reproduced lint/typecheck/build blockers for Node.js, Rust, and Python repos. Use for pre-deploy checks, deploy-ready requests, or final quality/build gates before deployment.
[Hyper] Create, enter, list, remove, clean up, or repair Git worktrees for isolated branches and parallel agent sessions, including direct `git-worktree <ARGUMENT>` creation without follow-up questions. Use when the user asks for git worktree setup/removal, branch-per-folder workflows, parallel Codex/Claude/Cursor workspaces, or the repository-local `.hypercore/git-worktree/<folder_name>` convention; when creating and no argument/task is clear, ask what work will happen there in the user's language, derive the folder name, then move subsequent work into the new worktree.
[Hyper] Use when the user explicitly wants OpenAI Codex CLI (`codex`) for an isolated session, non-interactive run, code review, or session resume. Trigger phrases: 'use codex', 'ask codex', 'run codex', 'codex exec', 'codex review', 'continue the last codex session', or 'use OpenAI CLI to inspect or fix this repo'.
[Hyper] Analyze bugs, present repair options, then implement and verify the user-selected fix path. Routes simple bugs directly; tracks complex multi-phase investigations via .hypercore/bug-fix/ JSON flow.
[Hyper] Commit and push in one action, including from linked Git worktrees. Use when the user asks to commit and push together, save and push changes, or run `/git-maker`; it performs safe commit grouping first, then automatically pushes without a second confirmation.
[Hyper] Create one or more Conventional Commits from the current repository state. Inspect staged and unstaged changes, group them into logical change sets, generate a compliant message per group, and commit each group separately in sequence.
[Hyper] Optimize an existing codebase through baseline-first experiments, binary evaluation, and one-mutation-at-a-time iteration. Use for codebase autoresearch, measured bottleneck reduction, benchmarked code optimization, and evidence-backed refactors.
[Hyper] Create integrated SEO, AEO, GEO, and LLMO audits and optimization reports. Use for on-page, technical, content, Core Web Vitals, answer-engine, generative-engine, AI search visibility, metadata, citation readiness, or score-improvement loops saved under `.hypercore/seo-maker/[slug]/`.
[Hyper] Use when the user explicitly wants Anthropic Claude Code CLI (`claude`) for an isolated session, non-interactive (`-p`) run, session resume by ID or name, or a CI-friendly `--bare` invocation. Trigger phrases: "use claude code", "ask claude", "run claude", "continue the last claude session", "resume the auth-refactor claude session", or "use Anthropic's CLI to inspect or fix this repo".
[Hyper] Use when the user wants to invoke Google Gemini CLI (`gemini`) for reasoning, research, or AI assistance. Trigger phrases: "use gemini", "ask gemini", "run gemini", "call gemini", "gemini cli", "Google AI", "Gemini reasoning", or when users request Google's Gemini models, research with web search, plan-mode review, or want to resume a previous Gemini session. Do not use for generic writing, runbook cleanup, or local edits that do not require the Gemini CLI.
[Hyper] Use when working on Hono projects or adding Hono into a codebase. Enforces Hono architecture rules for app composition, route modules, middleware, validation, error handling, testing, and typed RPC boundaries before any code change.
[Hyper] Push unpushed commits to the remote. Discovers the current or descendant git repositories, checks for commits ahead of upstream, and pushes them. Use when the user wants to push, sync to remote, or send commits upstream.
[Hyper] Create or update a ManyFast-style AI planning package from a rough product idea: PRD, visual planning diagram, feature spec, user flow, low-fidelity wireframe, HTML preview viewer, source log, and optional flow tracking under `.hypercore/prd/[slug]/`. Use when the user wants product planning output before implementation, especially PRD plus diagram/specs/flows/wireframes.
[Hyper] Test Codex/agent skills for intended triggering and behavior with realistic positive, negative, boundary, and edge-case scenarios. Use when validating a skill folder, SKILL.md, rules/references/scripts/assets, trigger precision, workflow correctness, or regression coverage before shipping skill changes.
[Hyper] Create or refactor a project README.md by carefully reading the codebase. Detects project shape (CLI, library, web app, monorepo, plugin, framework, docs site, service), entry points, scripts, configuration, license, and existing docs, then produces a structured Korean README by default, unless the user requests another language or an existing README must preserve its current language. Use when the user wants a new README, a refactor of a stale README, or a section update grounded in the actual code.
[Hyper] Diagnose and fix build failures, CI pipeline errors, and deployment errors across the entire repository or a specific folder. Routes simple build breaks directly; tracks complex multi-system failures via .hypercore/deploy-fix/ JSON flow.
[Hyper] Use when working on Vite + TanStack Router projects - enforces architecture rules (layers, routes, hooks, services, conventions) with mandatory validation before any code change. Triggers on file creation, route work, hook patterns, or any structural change in a Vite + TanStack Router codebase.
[Hyper] Run deploy-readiness validation and fix reproduced lint/typecheck/build blockers for Node.js, Rust, and Python repos. Use for pre-deploy checks, deploy-ready requests, or final quality/build gates before deployment.
[Hyper] Create or refactor a project README.md by carefully reading the codebase. Detects project shape (CLI, library, web app, monorepo, plugin, framework, docs site, service), entry points, scripts, configuration, license, and existing docs, then produces a structured Korean README by default, unless the user requests another language or an existing README must preserve its current language. Use when the user wants a new README, a refactor of a stale README, or a section update grounded in the actual code.
[Hyper] Analyze vague or relayed non-developer stakeholder requests (client, executive, PM, sales/support) by mapping them to codebase impact, presenting interpretation candidates with risks, then implementing only after confirmation. Use for stakeholder-message analysis, not browser QA testing, CI/build failures, or already-clear technical tasks.
[Hyper] Create or update a ManyFast-style AI planning package from a rough product idea: PRD, visual planning diagram, feature spec, user flow, low-fidelity wireframe, HTML preview viewer, source log, and optional flow tracking under `.hypercore/prd/[slug]/`. Use when the user wants product planning output before implementation, especially PRD plus diagram/specs/flows/wireframes.
[Hyper] Produce a multi-source, source-backed markdown research report for fact-finding, comparisons, market/trend analysis, or evidence-backed recommendations across live web, official docs, GitHub, and local repo sources. Use when synthesis and citations are needed, not for one-source lookups.
[Hyper] Create integrated SEO, AEO, GEO, and LLMO audits and optimization reports. Use for on-page, technical, content, Core Web Vitals, answer-engine, generative-engine, AI search visibility, metadata, citation readiness, or score-improvement loops saved under `.hypercore/seo-maker/[slug]/`.
[Hyper] Create new Codex skills or refactor existing skill folders when the user asks for a reusable skill, better trigger wording, cleaner resource placement, or stronger validation across `SKILL.md`, `rules/`, `references/`, `scripts/`, and `assets/`.
[Hyper] Test Codex/agent skills for intended triggering and behavior with realistic positive, negative, boundary, and edge-case scenarios. Use when validating a skill folder, SKILL.md, rules/references/scripts/assets, trigger precision, workflow correctness, or regression coverage before shipping skill changes.
[Hyper] Optimize an existing Codex skill through baseline-first experiments, binary evals, optional guards, and one-mutation-at-a-time iteration. Use for skill autoresearch, measured trigger/workflow improvement, self-optimizing a skill, benchmarking skill changes, or resuming skill experiment artifacts.
[Hyper] Enforce TanStack Start architecture in existing Start projects, especially project/folder structure, route structure, nested shared folder organization, server functions, loader/client-server boundaries, importProtection, hooks, SSR/hydration, and hypercore conventions. Use before structural code changes, folder-structure reviews, route work, server function work, or architecture audits in TanStack Start codebases.
[Hyper] Use when working on TanStack Start projects and the task involves auth, sessions, cookies, CSRF, secrets, env exposure, server functions/routes, headers/CSP, webhooks, or security review/fixes. Triggers on protecting routes, hardening auth flows, preventing secret leaks, securing server boundaries, or reviewing HTTP/security behavior in a TanStack Start app.
[Hyper] Update semantic versions across node/rust/python projects, keep discovered version files synchronized, and prefer the installed `git-commit` skill for the final git step with a direct fallback when it is unavailable.
[Hyper] Improve an existing code path, document, design, prompt, or skill by analyzing the target, running local multi-pass improvement reasoning, selecting a safe improvement path from user criteria or self-generated options, then editing and validating. Uses local reasoning only; no external reasoning MCP is required.
[Hyper] Investigate websites with Playwriter plus CDP to choose a crawl strategy, capture API/auth evidence, document findings under `.hypercore/crawler/[site]/`, and generate crawler code only after discovery is grounded.
[Hyper] Analyze vague or relayed non-developer stakeholder requests (client, executive, PM, sales/support) by mapping them to codebase impact, presenting interpretation candidates with risks, then implementing only after confirmation. Use for stakeholder-message analysis, not browser QA testing, CI/build failures, or already-clear technical tasks.
[Hyper] Create and refactor AI-readable docs, instruction bases, runbooks, specs, and harness-ready rule packs for context, prompt, tool, eval, sourcing, safety, and validation workflows.
[Hyper] Immediately start working on a given task with adaptive thinking depth — light thinking for easy tasks, deep thinking for hard ones. Use when the user wants immediate execution, not diagnosis, planning, or review.
[Hyper] Produce a multi-source, source-backed markdown research report for fact-finding, comparisons, market/trend analysis, or evidence-backed recommendations across live web, official docs, GitHub, and local repo sources. Use when synthesis and citations are needed, not for one-source lookups.
[Hyper] Create new Codex skills or refactor existing skill folders when the user asks for a reusable skill, better trigger wording, cleaner resource placement, or stronger validation across `SKILL.md`, `rules/`, `references/`, `scripts/`, and `assets/`.
[Hyper] Update semantic versions across node/rust/python projects, keep discovered version files synchronized, and prefer the installed `git-commit` skill for the final git step with a direct fallback when it is unavailable.
[Hyper] Use when working on TanStack Start projects and the task involves auth, sessions, cookies, CSRF, secrets, env exposure, server functions/routes, headers/CSP, webhooks, or security review/fixes. Triggers on protecting routes, hardening auth flows, preventing secret leaks, securing server boundaries, or reviewing HTTP/security behavior in a TanStack Start app.
[Hyper] Enforce TanStack Start architecture in existing Start projects, especially project/folder structure, route structure, nested shared folder organization, server functions, loader/client-server boundaries, importProtection, hooks, SSR/hydration, and hypercore conventions. Use before structural code changes, folder-structure reviews, route work, server function work, or architecture audits in TanStack Start codebases.
[Hyper] Use when working on Vite + TanStack Router projects - enforces architecture rules (layers, routes, hooks, services, conventions) with mandatory validation before any code change. Triggers on file creation, route work, hook patterns, or any structural change in a Vite + TanStack Router codebase.
[Hyper] Use when working on Next.js projects, especially App Router or App Router migration work. Enforces current official Next.js architecture rules for project/folder structure, nested shared `lib` organization, route/file conventions, Server and Client Component boundaries, Cache Components and data freshness, Server Actions for internal UI writes, Route Handlers for HTTP-native endpoints, Proxy as a last resort, and platform/env safety.