Runs a full "dream" pass over the vault: dedup, archive stale entries, resolve contradictions, and produce a summary report. Inspired by how REM sleep consolidates biological memory.

Develop the agent's own internals with the vault as the primary source of truth. The vault knows more about the agent than any code scan or model training data. Always search the vault first, extract maximum context, and only then touch code.

Help users understand what this agent can do, how to use it effectively, and what makes it different from a raw LLM. This skill handles the deep discovery flow — proactive tool suggestions during normal work are handled by the engine rules (Tool Advocacy section).

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.

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.

Surface what the brain has learned across sessions and projects. Turns raw vault data into actionable intelligence.

Review code against vault patterns, anti-patterns, and project conventions. Catches violations that no linter knows about.

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.

Multi-pass code review that goes beyond surface lint. Analyzes structural health, code smells, architectural fitness, and solution quality. Works on any codebase — vault context is optional enrichment, not a requirement.

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.

Structured exploration before committing to a plan. Define the question, research prior art, explore the codebase, identify constraints, draft options with tradeoffs, and recommend a path forward.

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.

Fix bugs through a structured recovery workflow, then capture the root cause as a reusable anti-pattern. The learning step makes fixes compound across sessions.

Comprehensive maintenance cycle on the knowledge base. Finds stale entries, duplicates, contradictions, and quality issues.

Point at code, docs, PRs, architecture decisions, or postmortems — the agent extracts every pattern, anti-pattern, decision, and principle, then captures them to the vault.

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.

Structured tour of everything the vault knows about this project. Decisions, patterns, anti-patterns, conventions — all in one walkthrough.

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.

Generate a data-driven retrospective from session data, vault captures, plan outcomes, and brain intelligence.

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.