adrozdenko
132 verified skills704 total stars
soleri-writing-plans
Triggers: "create a plan", "write up a plan", "break this down", "plan the implementation". Produces markdown plan file. Priority over orchestrate_plan for explicit requests. Use brainstorming for ideation.
testing6
soleri-code-patrol
Triggers: "check against patterns", "pattern compliance", "convention check", "review against vault", "institutional review". Reviews code against vault patterns/conventions. Use deep-review for general quality/architecture.
development6
soleri-knowledge-harvest
Triggers: "learn from this", "harvest knowledge", "ingest this", "extract patterns from". Bulk-extracts patterns from code/docs/PRs/articles into vault. Use vault-capture for single patterns.
development6
soleri-agent-mode
Triggers: "AgentName, ...", "Hey AgentName", "what commands do I have", "what can you do with MCP", "command reference". Routes ambiguous intent to correct facade + op. Also handles vague phrases like "save this", "remember this", "search for patterns".
tools6
soleri-agent-persona
Triggers: "activate persona", "be yourself", "stay in character", "hello [agent name]". Reinforces character persistence across session and context compaction.
data-ai6
soleri-compress
Triggers: "compress this file", "compress CLAUDE.md", "compress memory", "shrink this", "reduce tokens in file", or invokes /compress. Compresses natural language files to save input tokens.
tools6
soleri-curator
Triggers: "curator status", "vault health", "how is the vault", "curator health", "check vault quality", "what needs grooming". Quick vault health + grooming recs. Use vault-curate for full maintenance.
testing6
soleri-deep-review
Triggers: "deep review", "code smells", "architecture review", "is this well architected", "optimization review". Multi-pass structural health/smells/quality review. Use code-patrol for vault pattern compliance.
development6
soleri-dream
Triggers: "dream", "consolidate memory", "clean up memory", "memory cleanup", "dream status". Automatic memory consolidation: dedup, archive stale, resolve contradictions.
tools6
soleri-env-setup
Triggers: "setup environment", "post-clone setup", "broken build", "missing dependencies", "MODULE_NOT_FOUND". Detects project needs, diagnoses gaps, produces setup checklist.
development6
soleri-executing-plans
Triggers: "execute my plan", "run the plan", "start executing", "implement the plan". Sequential task execution with review checkpoints. Use parallel-execute for concurrent.
testing6
soleri-agent-guide
Triggers: "what can you do", "how do I use this", "what features", "what tools available", "who are you", "show capabilities". Agent capability discovery and tool reference.
tools6
soleri-agent-issues
Triggers: "create issue", "file bug", "gh issue", "create task", "report bug", "create tickets". Creates structured GitHub issues optimized for agent execution.
data-ai6
soleri-brain-debrief
Triggers: "brain stats", "pattern strengths", "intelligence report", "show brain data", "what patterns are strongest". Surfaces brain pattern intelligence. Use retrospective for time-bound work reflection.
data-ai6
soleri-build-skill
Triggers: "create a skill", "new skill", "build skill", "add a skill", "write a skill", "skill template", "scaffold skill". Creates/updates/scaffolds Soleri agent skills.
development6
soleri-discovery-phase
Triggers: "I don't know where to start", "investigate", "research this", "explore the problem", "discovery". Structured exploration before committing to a plan, produces options with tradeoffs.
research6
soleri-intake
Triggers: "ingest this", "add this URL", "import this book", "read and capture", "ingest batch". Imports external content (URLs, text, books, batches) into vault with knowledge extraction.
content-media6
soleri-health-check
Triggers: "system health", "agent health", "run diagnostics", "system status", "check health". Read-only knowledge base health assessment. Use vault-smells for deep quality analysis.
testing6
soleri-research-scout
Triggers: "scout", "research scout", "find new info", "what's new", "scan the web". Discovers new info that challenges or updates vault knowledge via web search.
development6
soleri-retrospective
Triggers: "sprint retro", "weekly summary", "what went well", "end of sprint", "monthly report". Time-bound work reflection with actionable improvements. Use brain-debrief for pattern intelligence.
data-ai6
soleri-second-opinion
Triggers: "second opinion", "technical decision", "comparing approaches", "which approach". Informed recommendations backed by vault, brain, and web research.
development6
soleri-terse
Triggers: "terse mode", "be brief", "less tokens", "fewer tokens", "compress output", "caveman", or invokes /terse. Token-efficient responses with full technical accuracy.
testing6
soleri-systematic-debugging
FIRST response for "bug", "failing test", "not working", "debug this", "error", "crash", "weird issue". Diagnoses root cause before fixes. Hand off to fix-and-learn for repair.
development6
soleri-vault-smells
Triggers: "vault quality", "vault analysis", "knowledge quality", "knowledge debt", "stale patterns", "find contradictions". Deep knowledge quality analysis. Use health-check for basic operational diagnostics.
testing6
soleri-yolo-mode
Triggers: "yolo", "autonomous", "skip approvals", "full auto", "hands off". Autonomous execution skipping approval gates, safety invariants preserved.
tools6
soleri-verification-before-completion
Triggers: "verify this works", "check output", "quality gate", "run tests before done". Internal quality gate before task completion. Use deliver-and-ship for shipping.
testing6
soleri-deliver-and-ship
Triggers: "ship it", "pre-PR check", "delivery checklist", "is this ready", "final review", "ready to deploy". Pre-delivery quality gates. Use verification-before-completion for mid-workflow checks.
testing6
soleri-orchestrate
Triggers: "implement X", "build Y", "fix Z", "add feature", or any work task needing planning + execution. Full orchestration loop: plan, execute, complete with vault context and brain recs.
development6
soleri-finishing-a-development-branch
Triggers: "finish branch", "ready to merge", "PR ready", "submit PR", "close branch". Pre-merge checks, PR creation, merge strategy, branch cleanup.
development6
soleri-agent-dev
Triggers: "add a facade", "new tool", "extend vault", "add brain feature", "new skill", "extend agent". Extends agent internals with vault-first knowledge gathering.
tools6
soleri-subagent-driven-development
Triggers: "use subagents", "parallel agents", "subagent driven", "isolated execution". Decomposes work into isolated units, dispatches subagents.
development6
soleri-parallel-execute
Triggers: "run in parallel", "fan out", "concurrent execution", "batch execute", "dispatch subagents". Concurrent task execution via subagents. Use executing-plans for sequential.
data-ai6
soleri-fix-and-learn
Triggers: "fix it", "apply the fix", "patch this and remember", "fix and capture". Executes fix after root cause identified, captures learning to vault. Use systematic-debugging first.
development6
soleri-loop
Triggers: "start a loop", "run until done", "iterate until X", "loop status", "cancel loop". Iterative execution until condition met or grade threshold reached.
tools6
soleri-context-resume
Triggers: "where did I leave off", "what was I working on", "catch me up", "resume session", "continue where we stopped". Reconstructs working context from memory, plans, sessions.
tools6
soleri-brainstorming
Triggers: "I want to build something", "let's think about", "what if we", "creative exploration", "ideate". Open-ended creative exploration when requirements are not yet clear.
development6
soleri-mcp-doctor
Triggers: "MCP not working", "tools missing", "fix MCP", "mcp doctor", "server not connecting". Diagnoses and repairs MCP server connectivity.
tools6
soleri-vault-capture
Triggers: "save this to vault", "capture this", "remember this pattern", "add to vault", "vault capture". Durable patterns/decisions/anti-patterns. Use memory_capture for session notes, knowledge-harvest for bulk extraction.
testing6
soleri-test-driven-development
Triggers: "TDD", "write tests first", "red green refactor", "test driven". Write failing tests before implementation code.
development6
soleri-onboard-me
Triggers: "onboard me", "I'm new here", "project overview", "what should I know about this codebase". Structured tour of vault knowledge about this project.
development6
soleri-release
Triggers: "release", "bump version", "publish packages", "cut a release", "version bump", "npm publish". Bumps monorepo versions, commits, tags, pushes to trigger CI release. Use deliver-and-ship for quality gates.
testing6
soleri-using-git-worktrees
Triggers: "worktree", "parallel branch", "safe branch", "isolated branch". Protocol for creating, working in, and cleaning up git worktrees.
tools6
soleri-vault-curate
Triggers: "clean vault", "deduplicate vault", "groom knowledge", "merge patterns", "vault maintenance". Vault quality via dedup, grooming, contradiction detection.
testing6
soleri-vault-navigator
Triggers: "search the vault", "find patterns for", "have we seen this before", "vault search", "best practice for". Queries knowledge base for existing solutions and prior art.
tools6
agent-persona
Use when the user activates the agent's persona via its greeting phrase, or says "activate persona", "be yourself", "stay in character", or any activation phrase defined in the agent's persona configuration. Reinforces character persistence through the session and survives context compaction.
data-ai5
brain-debrief
Use when the user wants to explore the brain's learned PATTERNS — "brain stats", "pattern strengths", "what patterns are strongest", "intelligence report", "show brain data". Focused on the brain module's accumulated pattern intelligence. For time-bound sprint or weekly reflection, use retrospective instead.
data-ai5
context-resume
Use when the user says "where did I leave off", "what was I working on", "catch me up", "resume", "continue where we stopped", or is starting a new session and needs to reconstruct working context from memory, plans, and sessions.
tools5
code-patrol
Use when reviewing code against the project's own captured patterns, anti-patterns, and conventions — not generic lint rules but institutional knowledge.
development5
onboard-me
Use when someone is new to the PROJECT and needs orientation — "onboard me", "I'm new here", "project overview", "what should I know about this codebase". Questions about the project's patterns and conventions, not about the agent's capabilities (use agent-guide for that).
development5
knowledge-harvest
Use to EXTRACT multiple patterns from a source — code, docs, PRs, articles. Triggers on "learn from this", "harvest knowledge", "ingest this document", "extract patterns from". The agent reads the source and identifies what to capture. For saving a single known item, use vault-capture instead.
development5
mcp-doctor
Use when MCP servers fail to connect, tools are missing, or the user says "check MCP", "MCP not working", "server not connecting", "tools missing", "heal MCP", "fix MCP", "mcp doctor", "mcp status". Diagnoses and repairs MCP server connectivity issues.
tools5
retrospective
Use for time-bound reflection on recent WORK — "sprint retro", "weekly summary", "what went well this week", "end of sprint", "monthly report". Reviews sessions and extracts actionable improvements. For brain pattern intelligence and strength scores, use brain-debrief instead.
data-ai5
second-opinion
Use when facing a technical decision, comparing approaches, or needing an informed recommendation backed by vault knowledge, brain patterns, and web research.
development5
test-driven-development
Use when implementing any feature or bugfix — write failing tests before implementation code.
development5
vault-curate
Use when the user says "clean vault", "deduplicate", "groom knowledge", "consolidate vault", "vault maintenance", "find duplicates", "merge patterns", "check contradictions", "vault health", or wants to maintain, clean, reorganize, or improve the quality of the agent's knowledge base.
testing5
vault-capture
Use to capture a SINGLE known pattern, anti-pattern, workflow, decision, or principle to the vault. Triggers on "save this", "capture this", "remember this pattern", "add to vault". The user already knows what to capture. For bulk extraction from documents, code, or PRs, use knowledge-harvest instead.
development5
writing-plans
Use when the user has clear requirements or a spec and needs a structured implementation plan — "create a plan", "break this down", "plan the implementation". Requirements are already known. For open-ended exploration when requirements are unclear, use brainstorming instead.
data-ai5
discovery-phase
Use for structured exploration before committing to a plan — "I don't know where to start", "what are our options", "investigate", "research this", "explore options", "discovery". Ideal when requirements are unclear, entering a new domain, or facing architectural decisions. Produces a discovery document with options, tradeoffs, and a recommendation.
testing5
health-check
Use when the user asks "check health", "system status", "how healthy is the vault", "knowledge quality", "run diagnostics", "vault health report", or wants a read-only health assessment of the knowledge base — scoring, reporting, finding issues. Does NOT modify vault entries. To actively clean, merge, or deduplicate, use vault-curate instead.
testing5
soleri-agent-persona
Use when the user says "activate persona", "be yourself", "stay in character", or "hello [agent name]". Reinforces character persistence through the session and survives context compaction.
data-ai5
soleri-brain-debrief
Use when the user says "brain stats", "pattern strengths", "intelligence report", "show brain data", or "what patterns are strongest". Surfaces accumulated pattern intelligence from the brain module.
data-ai5
soleri-brainstorming
Use when the user says "I want to build something", "let's think about", "what if we", "creative exploration", or "ideate". For open-ended creative exploration when requirements are NOT yet clear.
development5
vault-navigator
Use when the user asks "search the vault", "find patterns for", "have we seen this before", "what does the vault say about", "best practice for", "check vault", "vault search", or wants to query the knowledge base for existing solutions and prior art. For saving a new entry, use vault-capture instead.
testing5
soleri-context-resume
Use when the user says "where did I leave off", "what was I working on", "catch me up", "resume session", or "continue where we stopped". Reconstructs working context from memory, plans, and sessions.
tools5
soleri-deep-review
Use when the user says "deep review", "code smells", "architecture review", "is this well architected", or "optimization review". Multi-pass code review analyzing structural health, smells, and solution quality.
development5
soleri-deliver-and-ship
Use when the user says "pre-PR check", "delivery checklist", "is this ready", "final review", or "ready to deploy". Runs pre-delivery quality gates to ensure nothing ships without passing stability and code quality checks.
development5
soleri-env-setup
Use when the user says "setup environment", "post-clone setup", "broken build", "missing dependencies", or "MODULE_NOT_FOUND". Detects what a project needs, diagnoses what's missing, and produces an actionable setup checklist.
development5
soleri-health-check
Use when the user says "system health", "agent health", "run diagnostics", "system status", or "check health". Read-only health assessment of the knowledge base — scoring, reporting, finding issues.
testing5
soleri-mcp-doctor
Use when the user says "MCP not working", "tools missing", "fix MCP", "mcp doctor", or "server not connecting". Diagnoses and repairs MCP server connectivity issues.
tools5
soleri-parallel-execute
Use when the user says "run in parallel", "fan out", "concurrent execution", "batch execute", or "dispatch subagents". Executes independent plan tasks concurrently via subagents. For sequential execution, use executing-plans.
data-ai5
soleri-retrospective
Use when the user says "sprint retro", "weekly summary", "what went well", "end of sprint", or "monthly report". Time-bound reflection on recent work that reviews sessions and extracts actionable improvements.
business5
soleri-second-opinion
Use when the user says "second opinion", "technical decision", "comparing approaches", or "which approach". Provides informed recommendations backed by vault knowledge, brain patterns, and web research.
development5
soleri-systematic-debugging
Use as the FIRST response when something is broken — "bug", "failing test", "not working", "debug this", "error", "crash", or "weird issue". Diagnoses root cause before proposing fixes.
development5
soleri-vault-capture
Use when the user says "save this", "capture this", "remember this pattern", "add to vault", "vault capture", or when persisting learnings from a work session. Validated capture with tier scoping, duplicate detection, and abstraction review.
testing5
soleri-vault-navigator
Use when the user says "search the vault", "find patterns for", "have we seen this before", "vault search", or "best practice for". Queries the knowledge base for existing solutions and prior art.
tools5
soleri-vault-smells
Use when the user says "vault quality", "vault analysis", "knowledge quality", "knowledge debt", "stale patterns", or "find contradictions". Deep knowledge quality analysis beyond operational health checks.
testing5
soleri-writing-plans
Use when the user says "create a plan", "break this down", or "plan the implementation". Creates structured implementation plans when requirements are already known. For exploration, use brainstorming.
data-ai5
deliver-and-ship
Use when the user says "ship it", "ready to deploy", "package", "release", "pre-PR check", "delivery checklist", "is this ready", "final review", or mentions shipping, deploying, packaging, or releasing work. Runs pre-delivery quality gates to ensure nothing ships without passing stability, knowledge capture, and code quality checks.
development5
deep-review
Use for in-depth code review beyond linting — architecture fitness, code smells, solution quality, optimization opportunities. Triggers on "deep review", "review this code", "is this well architected", "code smells", "review this module", "architecture review", "is this the right approach", "optimization review". Works on any codebase. For vault-specific knowledge quality, use vault-smells instead.
development5
finishing-a-development-branch
Use when the user says "finish branch", "merge branch", "ready to merge", "PR ready", "close branch", "submit PR", or wants to finalize a development branch for merge into the base branch.
development5
knowledge-harvest
Use to EXTRACT multiple patterns from a source — code, docs, PRs, articles. Triggers on "learn from this", "harvest knowledge", "ingest this document", "extract patterns from". The agent reads the source and identifies what to capture. For saving a single known item, use vault-capture instead.
development5
parallel-execute
Use when executing a plan where independent tasks can run concurrently. Triggers on "run in parallel", "parallelize", "fan out", "concurrent execution", "run simultaneously", "at the same time", "dispatch subagents", "batch execute", or when a plan has 3+ tasks with no dependency overlap. For sequential task-by-task execution, use executing-plans instead.
data-ai5
vault-navigator
Use when the user asks "search the vault", "find patterns for", "have we seen this before", "what does the vault say about", "best practice for", "check vault", "vault search", or wants to query the knowledge base for existing solutions and prior art. For saving a new entry, use vault-capture instead.
testing5
brain-debrief
Use when the user wants to explore the brain's learned PATTERNS — "brain stats", "pattern strengths", "what patterns are strongest", "intelligence report", "show brain data". Focused on the brain module's accumulated pattern intelligence. For time-bound sprint or weekly reflection, use retrospective instead.
data-ai5
parallel-execute
Use when executing a plan where independent tasks can run concurrently. Triggers on "run in parallel", "parallelize", "fan out", "concurrent execution", "run simultaneously", "at the same time", "dispatch subagents", "batch execute", or when a plan has 3+ tasks with no dependency overlap. For sequential task-by-task execution, use executing-plans instead.
data-ai5
agent-issues
Use when creating GitHub issues, bugs, tasks, or milestones that will be worked on by AI coding agents. Triggers on: "create issue", "file bug", "gh issue", "add milestone", "create task", "report bug", "gh tasks", "create tasks", "create tickets", "file tickets", or when generating structured work items from conversation context.
data-ai5
mcp-doctor
Use when MCP servers fail to connect, tools are missing, or the user says "check MCP", "MCP not working", "server not connecting", "tools missing", "heal MCP", "fix MCP", "mcp doctor", "mcp status". Diagnoses and repairs MCP server connectivity issues.
tools5
agent-dev
Use when extending the agent itself — adding facades, tools, vault operations, brain features, new skills, or modifying agent internals. Triggers on "add a facade", "new tool", "extend vault", "add brain feature", "new skill", "add operation", "extend agent", or when the work target is the agent's own codebase rather than a project the agent assists with. Enforces vault-first knowledge gathering before any code reading or planning.
tools5
soleri-build-skill
Use when creating a new skill, updating an existing skill, or scaffolding a skill template for a Soleri agent. Triggers on "create a skill", "new skill", "build skill", "add a skill", "write a skill", "skill template", "scaffold skill".
development5
soleri-agent-dev
Use when the user says "add a facade", "new tool", "extend vault", "add brain feature", "new skill", or "extend agent". For extending the agent's own internals with vault-first knowledge gathering.
tools5
agent-dev
Use when extending the agent itself — adding facades, tools, vault operations, brain features, new skills, or modifying agent internals. Triggers on "add a facade", "new tool", "extend vault", "add brain feature", "new skill", "add operation", "extend agent", or when the work target is the agent's own codebase rather than a project the agent assists with. Enforces vault-first knowledge gathering before any code reading or planning.
tools5
context-resume
Use when the user says "where did I leave off", "what was I working on", "catch me up", "resume", "continue where we stopped", or is starting a new session and needs to reconstruct working context from memory, plans, and sessions.
tools5
deep-review
Use for in-depth code review beyond linting — architecture fitness, code smells, solution quality, optimization opportunities. Triggers on "deep review", "review this code", "is this well architected", "code smells", "review this module", "architecture review", "is this the right approach", "optimization review". Works on any codebase. For vault-specific knowledge quality, use vault-smells instead.
development5
env-setup
Use when a developer needs to set up, fix, or restore a local development environment. Triggers on post-clone setup, project onboarding, first-time running a repo, pulled changes that broke the build, missing or misconfigured dependencies, MODULE_NOT_FOUND or Cannot find module errors, gyp ERR or native module build failures, missing .env files or unknown required environment variables, database setup, Docker compose issues, or connection refused during local dev. Covers Node.js, Python, Rust, Go, Ruby, PHP, and Docker-based projects.
development5
second-opinion
Use when facing a technical decision, comparing approaches, or needing an informed recommendation backed by vault knowledge, brain patterns, and web research.
development5
test-driven-development
Use when implementing any feature or bugfix — write failing tests before implementation code.
development5
vault-curate
Use when the user says "clean vault", "deduplicate", "groom knowledge", "consolidate vault", "vault maintenance", "find duplicates", "merge patterns", "check contradictions", "vault health", or wants to maintain, clean, reorganize, or improve the quality of the agent's knowledge base.
testing5
vault-smells
Use for deep knowledge quality analysis — finding contradictions, stale patterns, orphaned entries, weak links, knowledge decay, and structural issues in the vault. Triggers on "vault smells", "knowledge quality", "vault analysis", "find contradictions", "stale patterns", "knowledge debt", "vault deep check", "is my vault healthy". Goes deeper than health-check (which is operational). For code review, use deep-review instead.
development5
brainstorming
Use for open-ended creative exploration when requirements are NOT yet clear — "I want to build something", "let's think about", "explore options for", "what if we". Explores intent and design before implementation. If the user already has a spec or clear requirements, use writing-plans instead.
development5
deliver-and-ship
Use when the user says "ship it", "ready to deploy", "package", "release", "pre-PR check", "delivery checklist", "is this ready", "final review", or mentions shipping, deploying, packaging, or releasing work. Runs pre-delivery quality gates to ensure nothing ships without passing stability, knowledge capture, and code quality checks.
development5
env-setup
Use when a developer needs to set up, fix, or restore a local development environment. Triggers on post-clone setup, project onboarding, first-time running a repo, pulled changes that broke the build, missing or misconfigured dependencies, MODULE_NOT_FOUND or Cannot find module errors, gyp ERR or native module build failures, missing .env files or unknown required environment variables, database setup, Docker compose issues, or connection refused during local dev. Covers Node.js, Python, Rust, Go, Ruby, PHP, and Docker-based projects.
development5
subagent-driven-development
Use when the user says "use subagents", "parallel agents", "fan out", "dispatch agents", "subagent driven", or when a task decomposes into 2+ independent units that benefit from isolated execution. Covers when to dispatch, worktree isolation, and merge strategy.
development5
systematic-debugging
Use as the FIRST response when something is broken — "bug", "failing test", "not working", "debug this", "error", "crash", "unexpected behavior", "weird issue". Diagnoses root cause before proposing fixes. After root cause is found, hand off to fix-and-learn for repair and knowledge capture.
development5
executing-plans
Use when the user says "execute my plan", "run the plan", "start executing", "implement the plan step by step", or has a written plan to execute sequentially with review checkpoints. Tasks run one at a time in order. If tasks are independent and can run in parallel, use parallel-execute instead.
testing5
vault-smells
Use for deep knowledge quality analysis — finding contradictions, stale patterns, orphaned entries, weak links, knowledge decay, and structural issues in the vault. Triggers on "vault smells", "knowledge quality", "vault analysis", "find contradictions", "stale patterns", "knowledge debt", "vault deep check", "is my vault healthy". Goes deeper than health-check (which is operational). For code review, use deep-review instead.
development5
verification-before-completion
Use as an internal quality gate before claiming any task is done — run tests, check output, verify behavior. This is a mid-workflow checkpoint, not a shipping gate. For actual deployment and release workflows, use deliver-and-ship instead.
testing5
yolo-mode
Use when the user says "yolo", "autonomous", "skip approvals", "full auto", "hands off", or asks to execute without approval gates. Activates autonomous execution mode where the agent skips plan approval gates but preserves all safety invariants.
data-ai5
using-git-worktrees
Use when the user says "worktree", "isolate", "parallel branch", "safe branch", or when a plan has independent tasks that benefit from parallel execution in isolated branches. Provides the protocol for creating, working in, and cleaning up git worktrees safely.
tools5
soleri-agent-guide
Use when the user says "what can you do", "how do I use this", "what features", "what tools available", "who are you", or "show capabilities". Helps users discover agent capabilities and available tools.
tools5
soleri-code-patrol
Use when the user says "check against patterns", "pattern compliance", "convention check", "review against vault", or "institutional review". Reviews code against the project's own captured patterns and conventions.
development5
soleri-executing-plans
Use when the user says "execute my plan", "run the plan", "start executing", or "implement the plan". Executes tasks sequentially with review checkpoints. For parallel execution, use parallel-execute instead.
testing5
soleri-fix-and-learn
Use when the user says "fix it", "apply the fix", "patch this and remember", or "fix and capture". Executes a fix AFTER root cause is identified and captures the learning in the vault. Use systematic-debugging first.
development5
soleri-knowledge-harvest
Use when the user says "learn from this", "harvest knowledge", "ingest this", or "extract patterns from". Extracts multiple patterns from a source like code, docs, PRs, or articles into the vault.
development5
soleri-onboard-me
Use when the user says "onboard me", "I'm new here", "project overview", or "what should I know about this codebase". Provides a structured tour of everything the vault knows about this project.
development5
soleri-test-driven-development
Use when the user says "TDD", "write tests first", "red green refactor", or "test driven". Write failing tests before implementation code for any feature or bugfix.
development5
soleri-vault-curate
Use when the user says "clean vault", "deduplicate vault", "groom knowledge", "merge patterns", or "vault maintenance". Maintains vault quality through deduplication, grooming, and contradiction detection.
testing5
soleri-verification-before-completion
Use when the user says "verify this works", "check output", "quality gate", or "run tests before done". Internal quality gate before claiming any task is done. For shipping, use deliver-and-ship instead.
testing5
fix-and-learn
Use AFTER a root cause has been identified (typically via systematic-debugging) to execute the fix and capture the learning in the vault. Triggers on "fix it", "apply the fix", "patch this and remember". Do NOT use as the first response to a bug — use systematic-debugging first to find root cause.
development5
agent-persona
Use when the user activates the agent's persona via its greeting phrase, or says "activate persona", "be yourself", "stay in character", or any activation phrase defined in the agent's persona configuration. Reinforces character persistence through the session and survives context compaction.
data-ai5
agent-guide
Use when the user asks "what can you do", "help me", "how do I use this", "what features do you have", "what tools are available", "how does this work", "show me your capabilities", "what are you", "who are you", or any question about the agent's identity, capabilities, available tools, or how to use them. Not needed for proactive tool suggestions — those are handled by engine rules.
tools5
brainstorming
Use for open-ended creative exploration when requirements are NOT yet clear — "I want to build something", "let's think about", "explore options for", "what if we". Explores intent and design before implementation. If the user already has a spec or clear requirements, use writing-plans instead.
development5
code-patrol
Use when reviewing code against the project's own captured patterns, anti-patterns, and conventions — not generic lint rules but institutional knowledge.
development5
executing-plans
Use when the user says "execute my plan", "run the plan", "start executing", "implement the plan step by step", or has a written plan to execute sequentially with review checkpoints. Tasks run one at a time in order. If tasks are independent and can run in parallel, use parallel-execute instead.
testing5
fix-and-learn
Use AFTER a root cause has been identified (typically via systematic-debugging) to execute the fix and capture the learning in the vault. Triggers on "fix it", "apply the fix", "patch this and remember". Do NOT use as the first response to a bug — use systematic-debugging first to find root cause.
development5
health-check
Use when the user asks "check health", "system status", "how healthy is the vault", "knowledge quality", "run diagnostics", "vault health report", or wants a read-only health assessment of the knowledge base — scoring, reporting, finding issues. Does NOT modify vault entries. To actively clean, merge, or deduplicate, use vault-curate instead.
testing5
onboard-me
Use when someone is new to the PROJECT and needs orientation — "onboard me", "I'm new here", "project overview", "what should I know about this codebase". Questions about the project's patterns and conventions, not about the agent's capabilities (use agent-guide for that).
development5
retrospective
Use for time-bound reflection on recent WORK — "sprint retro", "weekly summary", "what went well this week", "end of sprint", "monthly report". Reviews sessions and extracts actionable improvements. For brain pattern intelligence and strength scores, use brain-debrief instead.
data-ai5
systematic-debugging
Use as the FIRST response when something is broken — "bug", "failing test", "not working", "debug this", "error", "crash", "unexpected behavior", "weird issue". Diagnoses root cause before proposing fixes. After root cause is found, hand off to fix-and-learn for repair and knowledge capture.
development5
vault-capture
Use to capture a SINGLE known pattern, anti-pattern, workflow, decision, or principle to the vault. Triggers on "save this", "capture this", "remember this pattern", "add to vault". The user already knows what to capture. For bulk extraction from documents, code, or PRs, use knowledge-harvest instead.
development5
verification-before-completion
Use as an internal quality gate before claiming any task is done — run tests, check output, verify behavior. This is a mid-workflow checkpoint, not a shipping gate. For actual deployment and release workflows, use deliver-and-ship instead.
testing5
writing-plans
Use when the user has clear requirements or a spec and needs a structured implementation plan — "create a plan", "break this down", "plan the implementation". Requirements are already known. For open-ended exploration when requirements are unclear, use brainstorming instead.
data-ai5
agent-guide
Use when the user asks "what can you do", "help me", "how do I use this", "what features do you have", "what tools are available", "how does this work", "show me your capabilities", "what are you", "who are you", or any question about the agent's identity, capabilities, available tools, or how to use them. Not needed for proactive tool suggestions — those are handled by engine rules.
tools5