Loading...
Loading...
Found 145 Skills
Run Python (ruff) and JavaScript (Biome) linting, formatting, and code quality checks with auto-fix support. Use when code needs linting, formatting, or style checking before commits. Use for "lint", "format", "ruff", "biome", "code style", or "check quality". Do NOT use for comprehensive code review (use systematic-code-review).
Generate a project-specific CLAUDE.md by analyzing the current repository's code, build system, and architecture. 4-phase pipeline: SCAN, DETECT, GENERATE, VALIDATE. Auto-detects language/framework and enriches output with domain-specific conventions (e.g., go-sapcc-conventions for sapcc Go repos). Use for "generate claude.md", "create claude.md", "init claude.md", "bootstrap claude.md", "make claude.md". Do NOT use for improving an existing CLAUDE.md (use claude-md-improver instead).
RED-GREEN-REFACTOR cycle with strict phase gates. Write failing test first, implement minimum code to pass, then refactor while keeping tests green. Use when implementing new features, fixing bugs with test-first approach, improving test coverage, or when user mentions TDD. Use for "TDD", "test first", "red green refactor", "write tests", or "implement with tests". Do NOT use for debugging existing failures (use systematic-debugging) or for refactoring without new tests (use systematic-refactoring).
Multi-language code quality gate with auto-detection and language-specific linters. Use when user asks to "run quality checks", "quality gate", "lint all", "check everything", "pre-commit checks", or "is this code ready to commit". Use for verifying code quality across polyglot repos. Do NOT use for single-language linting (use code-linting) or comprehensive code review (use systematic-code-review).
Auto-extract patterns from coding sessions, track corrections, and build reusable knowledge with confidence scoring
Docker best practices including multi-stage builds, compose patterns, image optimization, and security
Evaluate agents and skills for quality, completeness, and standards compliance using a 6-step rubric: Identify, Structural, Content, Code, Integration, Report. Use when auditing agents/skills, checking quality after creation or update, or reviewing collection health. Triggers: "evaluate", "audit", "check quality", "review agent", "score skill". Do NOT use for creating or modifying agents/skills — only for read-only assessment and scoring.
Classify user requests and route to the correct agent + skill combination. Use for any user request that needs delegation: code changes, debugging, reviews, content creation, research, or multi-step workflows. Invoked as the primary entry point via "/do [request]". Do NOT handle code changes directly - always route to a domain agent. Do NOT skip routing for anything beyond pure fact lookups or single read commands.
DAG-based multi-skill orchestration: Discover, Plan, Validate, Execute. Builds execution graphs for tasks requiring multiple skills in sequence or parallel with dependency resolution and context passing. Use when a task requires 2+ skills chained together, parallel skill execution, or conditional branching between skills. Use for "compose skills", "chain workflow", "multi-skill", or "orchestrate skills". Do NOT use when a single skill can handle the request, or for simple sequential invocation that needs no dependency management.
Defense-in-depth verification before declaring any task complete. Run tests, check build, validate changed files, verify no regressions. Applies 4-level adversarial artifact verification (EXISTS > SUBSTANTIVE > WIRED > DATA FLOWS) with goal-backward framing. Use before saying "done", "fixed", or "complete" on any code change. Use for "verify", "make sure it works", "check before committing", or "validate changes". Do NOT use for debugging (use systematic-debugging) or code review (use systematic-code-review).
Interact with the learning system: show stats, list/search accumulated knowledge, and graduate mature entries into agents/skills. Backed by learning.db (SQLite + FTS5). Use when user says "retro", "retro list", "retro search", "retro graduate", "check knowledge", "what have we learned", "knowledge health", "graduate knowledge".
Decision-first data analysis with statistical rigor gates. Use when analyzing CSV, JSON, database exports, API responses, logs, or any structured data to support a business decision. Handles: trend analysis, cohort comparison, A/B test evaluation, distribution profiling, anomaly detection. Do NOT use for codebase analysis (use codebase-analyzer), codebase exploration (use explore-pipeline), or ML model training.