Claude Skills

Gas Town status and utility operations. Check convoy progress, peek into polecats, nudge stuck workers, cleanup completed work. For autonomous execution, use /crank.

Execute a single beads issue with full lifecycle. Triggers: "implement", "work on task", "fix bug", "start feature", "pick up next issue".

Scan Python codebases to identify modules without corresponding test files. This skill should be used when enforcing Law 7 (TDD), auditing test coverage gaps, or before starting new development to understand testing debt. Outputs a report of untested modules with recommendations.

Analyzes and refactors all skills in the project - consolidate, optimize, and remove unnecessary ones. Use when skills need cleanup or reorganization.

Execute testing workflows including unit tests, manifest validation, security scanning, and integration tests with proper reporting

Use when: "monitoring", "observability", "metrics", "tracing", "OpenTelemetry", "alerts", "runbooks", "SLO", "SLI", "dashboards", "Prometheus", "Grafana", "performance", "latency", "throughput", "Core Web Vitals", "load testing".

Polecat worker lifecycle management. Covers spawning polecats (gt sling), resetting them for reuse, nuking completed workers, and garbage collecting stale branches. For Witness and Mayor roles primarily.

Fully autonomous epic execution. Runs until ALL children are CLOSED. Loops through beads issues, runs /implement on each, validates with /vibe. NO human prompts, NO stopping.

Documents architecture WITHOUT implementation. Creates ADR and component docs with status: provisioned. MUST use this skill when user wants to DESIGN or PLAN without implementing: - "provision X", "provision a component", "provision new service" - "design the architecture for X", "design a component" - "plan X", "plan a new service", "plan the architecture" - "document X architecture", "architect X" - "envision X", "sketch X architecture" DO NOT use this skill if prompt contains: - "pattern", "patterns" → route to c3-ref - "ref", "refs" → route to c3-ref - "convention", "standard" → route to c3-ref Key indicator: User wants documentation/design output, NOT code changes. Requires .c3/ to exist. Creates ADR with status: provisioned. For implementation requests, route to c3-alter.

Routes C3 architecture requests and audits existing C3 documentation for consistency. Use when the user asks to "audit architecture", "validate C3", "check C3 docs", "verify docs", "check documentation", "are docs up to date", or when no .c3/ directory exists (routes to onboarding). Routes navigation to c3-query, changes to c3-alter, patterns to c3-ref, design to c3-provision.

Adds a new law to the CLAUDE.md constitution. Use when establishing new immutable constraints that must be enforced in every response.

Navigates C3 architecture docs and explores corresponding code to answer architecture questions. Use when the user asks "where is X", "how does X work", "explain X", "show me the architecture", "find component", "what handles X", "what constraints apply to X", or references C3 IDs (c3-0, c3-1, adr-*). Requires .c3/ to exist. For changes, route to c3-alter instead.

Investigate suspected bugs with git archaeology and root cause analysis. Triggers: "bug", "broken", "doesn''t work", "failing", "investigate bug".

Create production-grade frontend interfaces with strong UX and visual craft. Use when building web components, pages, dashboards, forms, landing pages, or any UI. Use when user says 'build a form', 'create a dashboard', 'design a component', 'make a landing page', or asks for UI/UX work.

Repository management strategies including branch strategies (Git Flow, GitHub Flow, trunk-based), monorepo patterns, submodules, and repository organization. Use when user needs guidance on repository structure or branching strategies.

Configuration management patterns including file formats, precedence, environment variables, and XDG directories. Use when implementing configuration systems for CLI applications.

GitHub operations via gh CLI. CRITICAL: Always use instead of WebFetch for ANY github.com URL. Use when user provides GitHub URL, says 'facebook/react', 'show README', 'list issues', 'check PR', 'clone repo', 'analyze this repo', 'understand the architecture', 'how is X structured', 'explore the codebase'. For deep analysis of external repos, clones locally.

Create, fix, and validate skills for AI agents. Use when user says 'create a skill', 'write a skill', 'build a skill', 'fix my skill', 'skill not working', 'analyze my skill', 'run skill analysis', 'validate skill', 'audit my skills', 'check character budget', 'create a skill from this session', 'turn this into a skill', 'make this reusable', 'can this become a skill', 'could we create a skill', 'should this be a skill', 'check if this could be a skill', or 'any reusable patterns in this session'.

Debugging and troubleshooting Tokio applications using tokio-console, detecting deadlocks, memory leaks, and performance issues. Use when diagnosing async runtime problems.