copilot-brain-bootstrap

Build the project and verify it compiles cleanly. Use after making changes to confirm nothing is broken before running tests. Reads the build command from context/build.md.

Auto-configure .github/copilot-instructions.md and context/ knowledge docs for a new project. Use when setting up Brain Bootstrap in a new repository. Discovers the codebase, fills in templates, and writes project-specific configuration.

Save session state before context gets full or before ending. Writes current task state, branch, and loaded docs to context/tasks/todo.md so the next session can resume cleanly.

Clean workspace — build artifacts, dependencies, caches, Docker volumes, or temp files. Accepts arguments like build, deps, all, cache, docker, tasks, reinstall.

Load all relevant context/ knowledge files for a domain area. Use at session start or when switching to a new topic. Accepts a domain keyword like api, database, auth, build, security.

Query the database — list schemas, tables, describe a table, or run SQL. Accepts arguments like schemas, tables, describe <table>, or raw SQL.

Root cause analysis for bugs and errors. Use when something is broken and the cause is not obvious. Applies the 5-step investigation method — observe, hypothesize, trace backwards, binary search, prove.

Manage dependencies and fix CVEs — check outdated packages, update a specific package, run security audit, explain why a package is installed, or deduplicate. Read context/cve-policy.md for the decision tree.

Docker workflow helpers — list containers, build, run, logs, compose up/down, prune. Non-interactive only.

Verify Copilot configuration health — copilot-instructions.md, hooks, skills, errors log, secrets scan, and MCP reachability. Reports ✅/⚠️/❌ for each check.

Run the linter and formatter check. Use before opening a PR to ensure code style compliance. Reads lint command from context/build.md.

Detect and fix stale context/*.md knowledge docs. Use when context/architecture.md or build.md references missing files, wrong commands, or outdated patterns. Keeps the knowledge base accurate.

Manage MCP (Model Context Protocol) servers — list configured tools, check status, show invocation format, or add a new server to .vscode/mcp.json.

Run database or schema migrations — up, down, rollback, status, or create a new migration. Reads context/build.md for migration commands.

Generate a PR/MR description after the review passes. Use after /review confirms the code is ready to merge. Reads context/templates.md for the required format.

Plan a non-trivial task before implementing. Use when the task requires 3+ steps, multiple files, or an architectural decision. Writes a checkable plan to context/tasks/todo.md.

Isolated codebase exploration that preserves your main context. Use when you need to understand code structure, trace call paths, or gather evidence before making changes. Spawns an explorer subagent.

Resume a previous session from context/tasks/todo.md. Use at the start of a new session to restore context and continue where you left off.

Full 10-point expert code review. Use before any PR or MR. Checks correctness, cross-layer consistency, transaction safety, test coverage, and security. Spawns reviewer subagent for isolation.

Start service(s) locally for development. Accepts a service name, all, frontend, or backend. Reads context/build.md for the actual start commands.

Generate a parallel workstream plan for multi-agent Copilot work. Decomposes a feature into independent workstreams, each ownable by a separate Copilot instance. Saves to context/tasks/ACTION_PLAN.md.

Project status dashboard — Copilot instructions budget, unfilled placeholders, lessons file size, hooks executability, jq availability, plugin states. One-glance health report.

Run the test suite and report results. Use after making changes to verify nothing is broken. Reads the test command from context/build.md.

Create a ticket/issue description with evidence-backed proof sections. Reads context/templates.md for the template format. Saves to context/tasks/ticket-<slug>.md.

Test-Driven Development skill. Automatically activates on test files. 3-phase protocol: Explore (understand existing tests), Plan (list scenarios), Act (write tests then implementation).

Brainstorming skill. HARD GATE before implementation. Forces structured option analysis before any code is written.

Structural code queries via CocoIndex. Find all callers of a function, trace data flows, understand module boundaries. Better than grep for semantic queries.

Generate architectural dependency graphs. Visualize module relationships, detect circular dependencies, spot architectural drift.

Maintain a persistent code index and summary. Track important functions, patterns, and architectural decisions for fast future retrieval.

E2E testing with Playwright. Write, run, and debug browser automation tests. Supports visual regression, accessibility checks, and multi-browser testing.

Generate a project recap: what is this repo, what are the main components, what is the current state of work.

Semantic code navigation via Serena language server. Provides go-to-definition, find-all-references, rename-symbol — semantic operations beyond grep.

Careful mode skill. Activates extra safety checks for destructive operations: rm -rf, DROP TABLE, git push --force, production deploys. Forces explicit confirmation.

Generate or update CHANGELOG.md following Keep a Changelog format. Groups changes by type: Added, Changed, Fixed, Removed, Security.

Use when you want to see token consumption by task type, model, one-shot rate, or cost — observability dashboard for GitHub Copilot sessions. Trigger with /codeburn to analyze session spending.

Cross-layer consistency check. Ensures new fields, enums, and types are consistent across all layers: DB → repository → service → DTO → validator → API response → tests.

Triage GitHub/GitLab issues. Classify by type, severity, and reproducibility. Add labels, ask for missing information, link related issues.

Triage pull requests. Check completeness, tests, changelog, documentation. Flag issues before review. Label and assign.

Skill for processing code review feedback. Triages review comments by severity, creates fix tasks, applies changes systematically, and responds to reviewers.

Root cause analysis skill. Iron Law: never fix a bug without stating the root cause. 5-step: Observe, Hypothesize, Trace Backwards, Isolate, Verify.