Total 58,116 skills
Showing 12 of 58116 skills
複数の専門成果物を統合する中規模以上のdesign・implementation・review、end-to-endの要件再現性検証、または複数runのreproduction-testで使うrouter。単一成果物や、公開契約・data meaningに触れない小規模機械変更には使わない。
Coordinate Codex sub-agents for substantial multi-step work. Requires Codex collaboration tools and the listed Luna, Terra, and Sol model families. Use proactively when a request involves two or more separable workstreams; repository exploration plus implementation or verification; production diagnosis across logs, code, and live systems; PR or release review; multi-source analytics or research; or long-running tests, transfers, workflows, and monitors that should not block user communication. Assign bounded leaf work to Luna and collaborative or high-stakes work to Terra or Sol. Skip only trivial single-step or tightly sequential tasks.
Applies source-code fixes from an accessibility-audit report—mechanical (lang, aria-hidden, viewport, tables, reduced-motion) and contextual (alt text, aria-label, link copy)—then re-runs the audit to verify. Use after running accessibility-audit.
Append a structured entry to the project's session log (`docs/LOGS.md`): what was done this session, files touched, decisions taken, and the next step — so the next session (or another person) can pick up the thread without re-reading git history. Run it before `/clear`, before closing Claude Code, or at any natural stopping point. On Claude Code and want hand-tuned per-skill model/effort tiers? Install the `#claude` branch instead (`npx skills add gtrabanco/agentic-workflow#claude`) — see the README. This branch is model-agnostic: the skill inherits whatever model and effort your agent session is already using. Triggers: "log this session", "log-session", "write a session log", "journal what we did", "record this session before I clear", "save the session summary".
Audit cross-document coherence: docs ↔ roadmap ↔ code ↔ fix index ↔ issues. Finds drift — features in docs/ not in the roadmap (or vice versa), fix-index entries already merged/closed, broken documentation-map links, dependency cycles, artifacts in the wrong language, naming-convention violations — and reports them ranked by severity, fixing only low-risk items on request. On Claude Code and want hand-tuned per-skill model/effort tiers? Install the `#claude` branch instead (`npx skills add gtrabanco/agentic-workflow#claude`) — see the README. This branch is model-agnostic: the skill inherits whatever model and effort your agent session is already using. Triggers: "check doc consistency", "are the docs in sync", "audit the docs", "doc coherence review", "did the docs drift", "validate the roadmap".
Internal planning gate: consumes the normalized repository state and makes the ONE final architectural classification, using a two-stage contract that allows a lightweight NRS read during planning and a full architectural classification after the plan is cut. Used by plan-feature, plan-feature-from-issue, plan-feature-scaffold, and plan-fix. Not a menu entry.
Generate 3D assets with Tencent's Hunyuan3D family — open-weight self-hosted models (Hunyuan3D-2.0/2.1 and HunyuanWorld / HY-World for scenes) and the hosted, closed API tiers (2.5, PolyGen, 3.0/3.1 via Tencent Cloud and third-party hosts). Use when a task involves image-to-3D or text-to-3D mesh generation, the shape-then-texture (DiT + Paint / PBR) workflow, choosing between self-hosting and a hosted API, checking the Community License's Territory (EU/UK/South Korea) and 1M-MAU commercial gate, sizing GPU/VRAM for local inference, ComfyUI integration, or reviewing and post-processing (retopology, UVs, decimation) the meshes these models produce. Not for image, video, or general LLM tasks.
Internal security review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not a menu entry. Checks secrets, input validation, injection, authn/authz, PII exposure, and dependency risk on the changed surface. Findings only; never edits code.
Monitor competitor pricing, features, changelogs, dashboards, and product changes with Firecrawl. Use for recurring competitive intelligence, pricing tier extraction, feature change tracking, or structured competitor alerts.
Pull metrics from analytics dashboards and internal web tools with Firecrawl browser. Use when the user needs dashboard reporting, cross-platform metric summaries, authenticated analytics extraction, date-range reports, or structured metrics from web dashboards.
Extract structured company lists from directories with Firecrawl. Use for scraping YC, Crunchbase, Product Hunt, G2, startup directories, category directories, or custom company databases into JSON, CSV, CRM-ready lists, or research tables.
Accept a vague instruction, automatically conduct investigation, classification, break it down into XML phase plans, select skills, define completion criteria, then execute it fully in unattended mode via loop/goal + agent-mode — including automatic deployment, automatic E2E testing, automatic code review, without skipping any phases. Activate proactively when the user provides a broad task — such as "fix the bug", "add tests", "optimize performance", "finish this feature", "scan the code", "investigate why XX happens". It also triggers when the user says "autopilot", "auto", "help me plan", "handle it yourself", "run directly", "break it down for me", "don't ask me how to do it". Even if the user doesn't use these keywords, it should activate proactively if the input is clearly an unbroken broad intent. Calling autopilot = authorizing fully automatic unattended execution, no mid-process confirmation required.