Skill Claude Code
Use when someone needs a plain-language explanation of how an existing feature or edge case behaves in the codebase. Triggers - non-technical stakeholder asks how something works, need code-informed functional explanation, need to understand rules or edge cases without implementation planning.
Skill Claude Code
Use when a developer wants to go from rough idea to working code autonomously. Triggers - imperfect prompt, solo dev wants full pipeline, "just build it", idea to implementation without manual steps.
Skill Claude Code
Use when creating a new agentic workflow skill. Triggers - need new multi-step orchestrated process, want to add workflow to agentic framework, building spec-driven pipeline.
Skill Claude Code
Use when debugging bug reports, CI failures, test failures, runtime errors, or flaky tests. Takes error logs, stack traces, or issue descriptions and systematically investigates to a verified fix. Evidence-based, no guessing.
Skill Claude Code
Use when building frontend features from idea to implementation. Triggers on new UI components, pages, or features needing design and code.
Skill Claude Code
Use when implementing from a technical plan (from agentic:technical-planning or planning mode). Triggers - "implement this plan", "implement technical plan", technical plan file provided.
Skill Claude Code
Use when reviewing a pull request for code quality, test coverage, and security. Triggers - "review PR", "review pull request", PR number or link provided, code review request.
Skill Claude CodeCodex
Use when transforming a raw idea into a precise product specification. Triggers - vague feature request, new product idea, need rigorous requirements before design.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: