Loading...
Loading...
Found 776 Skills
Adapter boundary rules for plugin integrations. Trigger: Changes in plugin scripts/hooks for Claude, OpenCode, Gemini, or Codex.
A skill for retrieving the latest library documentation using Context7. Use when the user asks about how to use a library, requests code examples, or instructs to "use context7". Prevents hallucinations based on outdated training data and provides up-to-date API information.
Fetch, organize, and analyze LangSmith traces for debugging and evaluation. Use when you need to: query traces/runs by project, metadata, status, or time window; download traces to JSON; organize outcomes into passed/failed/error buckets; analyze token/message/tool-call patterns; compare passed vs failed behavior; or investigate benchmark and production failures.
Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cycle to prompt engineering using subagents for isolated testing
Launch a sub-agent judge to evaluate results produced in the current conversation
Audit and maintain the joelclaw skill inventory. Use when checking skill health, fixing broken symlinks, finding stale skills, or running the skill garden. Triggers: 'skill audit', 'check skills', 'stale skills', 'skill health', 'skill garden', 'broken skill', 'skill review', 'fix skills', 'garden skills', or any task involving skill inventory maintenance.
Merges valuable content into permanent documentation, then deletes source files. Use when you have untracked *_REPORT.md or *_ANALYSIS.md files, git status shows markdown artifacts that shouldn't be committed, preparing PR and need to clean up working artifacts, preserving insights from code reviews. Do not use when files are already in docs/ or skills/ locations. DO NOT use when: files are intentionally temporary scratch notes. DO NOT use when: source files have no extractable value.
Adversarial code review using the opposite model. Spawns 1–3 reviewers on the opposing model (Claude spawns Codex, Codex spawns Claude) to challenge work from distinct critical lenses. Triggers: "adversarial review".
Build Model Context Protocol servers and implementations. Creates protocol-compliant tools and integrations for AI-powered applications.
Use when working with Anthropic Claude Agent SDK. Provides architecture guidance, implementation patterns, best practices, and common pitfalls.
Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.
Generate deep links to traces, spans, and sessions in the Arize UI. Use when the user wants a clickable URL to open a specific trace, span, or session.