asafelobotomy

Guide for implementing new agent tools for ClosedClaw's AI assistant. Use when adding capabilities like web search, file operations, API integrations, or custom actions. Covers tool factory pattern, parameter validation, registration, and testing.

Guide for creating new messaging channel plugins/extensions for ClosedClaw. Use when adding support for new messaging platforms (e.g., Matrix, Teams, BlueBubbles). Covers plugin structure, CliDeps extension, routing setup, and testing.

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

Help with config schema changes and migrations in ClosedClaw. Use when updating config types, syncing Zod schemas, creating migrations, or handling breaking config changes. Covers type definitions, validation, and legacy migration patterns.

Guide for writing and maintaining ClosedClaw documentation. Use when creating docs for new features, channels, tools, or updating existing documentation. Covers markdown conventions, link styles, formatting rules, and documentation structure.

Guide for writing e2e tests for ClosedClaw gateway and channels. Use when testing multi-instance gateway behavior, WebSocket/HTTP surfaces, node pairing, agent workflows with real networking. Covers test helpers, assertion patterns, and common scenarios.

Troubleshooting gateway issues in ClosedClaw. Use when debugging gateway startup failures, port conflicts, lock file issues, WebSocket disconnections, or RPC errors. Covers log analysis, diagnostics, and recovery procedures.

Version bumping, changelog updates, and npm publishing workflow for ClosedClaw. Use when preparing releases, updating versions, managing semantic versioning, creating release tags, or publishing to npm. Covers stable, beta, and dev release channels.

Health check procedures D1–D14 for the Audit agent — structural validation, attention budget, version checks, workspace integrity, and static audit

Configure and manage Model Context Protocol servers for external tool access

Review a UI for accessibility — WCAG 2.1 AA compliance, semantic HTML, ARIA usage, keyboard navigation, focus management, colour contrast, and screen reader compatibility

Design or review a REST or GraphQL API — resource modeling, versioning strategy, error contract, OpenAPI/schema-first workflow, and security baseline

Generate a CHANGELOG.md entry from staged changes, a commit range, or a PR diff — following Keep a Changelog format with conventional commit classification

Set up and audit environment variable management — create .env.example, add startup validation, separate secrets from config, and document every variable

Generate or update onboarding documentation — README, CONTRIBUTING guide, dev environment setup script, and new-developer validation checklist

Profile a slow function, endpoint, or query — identify hot paths, N+1 queries, and memory pressure, then apply targeted optimizations with before/after measurements

Use when: reviewing .prompt.md, .agent.md, SKILL.md, or .instructions.md files for contradictions, ambiguity, persona consistency, cognitive load, coverage gaps, and composition conflicts.

Use when: checking xanadAssistant workspace health, install status, repair reasons, or lockfile validity before proposing install, update, repair, or restore operations.

Use when: designing or reviewing CI/CD pipelines, GitHub Actions, stage design, environment gates, or artifact discipline.

Use when: writing or reviewing Dockerfiles, container images, multi-stage builds, layer caching, or image security.

Use when: writing or reviewing Infrastructure as Code for naming, state management, modularity, and drift detection.

Use when: reviewing DevOps changes for pipeline safety, secret hygiene, permissions, rollback, and deployment risk.

Use when: writing or reviewing API and code documentation, including docstrings, OpenAPI patterns, and parameter tables.

Use when: reviewing documentation for accuracy, completeness, clarity, link health, and merge readiness.

Use when running workspace tests, choosing a test command, or summarizing results before handoff to debugger.

Use when running workspace tests, choosing a test command, or summarizing results before handoff to debugger.

Use when: running pre-commit or pre-push CI-equivalent checks in any workspace — discovers workflow commands with Cursor tools, filters for local executability, scopes to staged changes, and runs checks cheapest-first.

Use when the user wants to install or customize cursorAssistant in the current project (GitHub install or configure).

Use when: running pre-commit or pre-push CI-equivalent checks in any workspace — discovers workflow commands with Cursor tools, filters for local executability, scopes to staged changes, and runs checks cheapest-first.

Use when: discovering package manifests, assessing dependency health, finding replacements, or confirming import usage before removal — discovery only; mutating installs are handled by the deps agent.

Use before proposing cursorAssistant setup, update, or repair — inspect lockfile and managed file drift.

Use when task complexity is unclear — classify as Trivial, Simple, Compound, Complex, or Blocked and recommend the minimal path before spawning subagents.

Set up and manage GitHub Actions workflows that use Copilot coding agents for automated PR handling and issue resolution

Inspect active GitHub Actions workflows before commit or push, run matching local checks for staged or unpushed files, ask which missing tools to install via askQuestions, and fix in-scope issues so the Commit agent can proceed.

Write a commit message following the Conventional Commits specification with scope and body

Create an Architectural Decision Record (ADR) to document a significant design or technology choice

Audit VS Code extensions against the current project stack and recommend keep/add/remove actions

Diagnose and fix a failing CI pipeline or GitHub Actions workflow

Triage a GitHub issue by classifying severity, labelling waste category, proposing next action, and drafting a structured response

Review a pull request using Lean waste categories and structured severity ratings

Create an Architectural Decision Record (ADR) to document a significant design or technology choice

Audit VS Code extensions against the current project stack and recommend keep/add/remove actions

Diagnose and fix a failing CI pipeline or GitHub Actions workflow

Triage a GitHub issue by classifying severity, labelling waste category, proposing next action, and drafting a structured response

Create a new MCP server — clarify purpose, choose transport, scaffold, implement, test, and register

Configure and manage Model Context Protocol servers for external tool access

Discover, evaluate, install, test, and manage agent plugins for VS Code Copilot

Create a new agent skill following the Agent Skills open standard

Audit VS Code extensions against the current project stack and recommend keep/add/remove actions

Review a pull request using Lean waste categories and structured severity ratings

Configure and manage Model Context Protocol servers for external tool access

Set up browser testing — dual path with built-in browser tools (interactive) or Playwright (CI); detect framework, scaffold, verify

Encode, decode, validate, and render Ceeline compact envelopes for internal AI-to-AI communication. Use when compressing handoff payloads, session summaries, memory notes, tool summaries, routing metadata, or prompt context into token-efficient compact format. Also use when validating incoming compact text, checking for leaked Ceeline artifacts in user-facing output, or round-tripping between JSON envelope and compact wire format.