Loading...
Loading...
Found 141 Skills
4-phase code review methodology: UNDERSTAND changes, VERIFY claims against code, ASSESS security/performance/architecture risks, DOCUMENT findings with severity classification. Use when reviewing pull requests, auditing code before release, evaluating external contributions, or pre-merge verification. Use for "review PR", "code review", "audit code", "check this PR", or "review my changes". Do NOT use for writing new code or implementing features.
Non-destructive 4-phase image validation: Discover, Validate, Analyze, Report. Use when auditing web images for accessibility, broken references, oversized files, or format mismatches. Use for "image audit", "check alt text", "find broken images", "optimize images", or "page weight". Do NOT use for image creation, editing pixels, CDN configuration, or automated image conversion without explicit user consent.
Run Vitest tests and parse results into actionable output. Use WHEN user needs to run JavaScript/TypeScript tests in a Vitest-configured project, verify test suites pass, or get structured failure reports. Use for "run tests", "vitest", "check if tests pass", or "test results". Do NOT use for Jest/Mocha projects, installing dependencies, writing new tests, or auto-fixing failing assertions.
Deterministic API endpoint validation with structured pass/fail reporting. Use when endpoints need smoke testing, health checks are required before deployment, or CI/CD pipelines need HTTP validation gates. Use for "validate endpoints", "check api health", "api smoke test", or "are endpoints working". Do NOT use for load testing, browser testing, full integration suites, or OAuth/complex authentication flows.
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.
Deterministic audit of cron/scheduled job scripts for reliability, error handling, logging, cleanup, and concurrency safety. Use when user says "audit cron", "check cron script", "cron best practices", "scheduled job review", or "bash script audit". Do NOT use for crontab scheduling syntax, systemd timers, or general shell linting without a cron/scheduled-job context.
Spawn 10 independent parallel agents to analyze source material from distinct perspectives, synthesize findings, and apply improvements to a target agent or skill. Use when source material is complex and multi-angle extraction justifies 3-5x token cost over inline analysis. Use for "parallel analysis", "multi-perspective", or "deep extraction". Do NOT use for routine improvements, simple source material, or when token budget is limited.
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.
Create session handoff artifacts (HANDOFF.json + .continue-here.md) that capture completed work, remaining tasks, decisions, uncommitted files, and reasoning context so the next session can resume without reconstruction overhead. Use for "pause", "save progress", "handoff", "stopping for now", "end session", "pick this up later". Do NOT use for task planning (use task_plan.md), session summaries (use /retro), or committing work (use /commit or git directly).
Plan multi-part content series with structure, cross-linking, and publishing cadence. Use when user needs to plan a blog post series, structure a multi-part tutorial, or design content with cross-linked navigation. Use for "plan series", "series on [topic]", "multi-part blog", or "content series". Do NOT use for writing individual posts, single-article outlines, or content calendar planning without series structure.
Multi-step voice content generation with deterministic validation. Orchestrates a 7-phase pipeline: LOAD, GROUND, GENERATE, VALIDATE, REFINE, OUTPUT, CLEANUP. Use when generating content in a specific voice, writing as a persona, or validating existing content against a voice profile. Use for "voice write", "write as", "generate in voice", or "voice content". Do NOT use for creating new voice profiles (use voice-calibrator), analyzing writing samples (use voice_analyzer.py), or general content without a voice target.
Local branch cleanup after PR merge: identify, switch, delete, prune in 4 steps. Use when a PR has been merged and local branches need cleanup, when stale branches accumulate, or when user says "clean up branches", "delete merged branch", or "prune". Do NOT use for branch creation, PR review, or CI checks.