Loading...
Loading...
Found 3,203 Skills
A/B test agent variants measuring quality and total session token cost across simple and complex benchmarks. Use when creating compact agent versions, validating agent changes, comparing internal vs external agents, or deciding between variants for production. Use for "compare agents", "A/B test", "benchmark agents", or "test agent efficiency". Do NOT use for evaluating single agents, testing skills, or optimizing prompts without variant comparison.
Validate Perses resources: run percli lint locally or with --online against a server. Check dashboard definitions, datasource configs, variable schemas. Report errors with actionable fixes. Use for "perses lint", "validate perses", "check dashboard", "perses validate". Do NOT use for plugin schema testing (use perses-plugin-test).
Manage editorial content pipeline through 6 stages: Ideas, Outlined, Drafted, Editing, Ready, Published. Use when user wants to view pipeline status, add ideas, move content between stages, schedule posts, or archive published content. Use for "content calendar", "pipeline status", "add idea", "schedule post", or "move to drafted". Do NOT use for creating Hugo content files, deploying posts, or modifying site configuration.
Gold-standard code review for SAP CC Go repositories against the project's lead review standards. Dispatches 10 domain-specialist agents in parallel — each loads domain-specific references and scans ALL packages for violations in their assigned domain. Produces a prioritized report with REJECTED/CORRECT code examples. Optional --fix mode applies corrections on a worktree branch. This is the definitive "would this code pass lead review?" assessment.
Constructive critique through 5 HackerNews commenter personas with evidence-based claim validation. Use when user wants devil's advocacy, stress testing, or critical review of ideas, docs, architecture, or code. Use for "roast", "critique this", "poke holes", "devil's advocate", "stress test", or "what's wrong with". Do NOT use for code review (use systematic-code-review), implementation changes, or performance profiling without a specific critique request.
Voice-integrated blog post creation with 4-phase workflow: Assess, Decide, Draft, Preview. Use when user wants to write a blog post, create content for a Hugo site, or draft an article using a specific voice profile. Use for "write post", "blog about", "draft article", "create content", or "write about [topic]". Do NOT use for editing existing posts, voice profile creation, SEO optimization, or social media content.
Clinical Decision Support System (CDSS) development patterns. Drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), alert severity classification, and integration into EMR workflows.
Java logging best practices with SLF4J, structured logging (JSON), and MDC for request tracing. Includes AI-friendly log formats for Claude Code debugging. Use when user asks about logging, debugging application flow, or analyzing logs.
Installs agents, configures MCP servers, syncs configs, creates and audits instructions. Use after setup or when agents/MCP need alignment.
Prevent Ethereum hashing bugs in JavaScript and TypeScript. Node's sha3-256 is NIST SHA3, not Ethereum Keccak-256, and silently breaks selectors, signatures, storage slots, and address derivation.
Security checklist for Solidity AMM contracts, liquidity pools, and swap flows. Covers reentrancy, CEI ordering, donation or inflation attacks, oracle manipulation, slippage, admin controls, and integer math.
This skill should be used when the user asks to create a hookify rule, write a hook rule, configure hookify, add a hookify rule, or needs guidance on hookify rule syntax and patterns.