Loading...
Loading...
Found 837 Skills
Run the trigger evaluation pipeline — classify, analyze, and optionally compare against a baseline. Only run when explicitly asked — evals are expensive.
Analyze a task, pick the right fleet type, and generate a ready-to-launch fleet (fleet.json + prompt.md files). Discovers available fleet skills dynamically. Use when the user wants to run work in parallel, asks to "plan a fleet", or says "fleet-plan".
Interactive hypothesis-driven debugging with documented exploration, understanding evolution, and analysis-assisted correction.
Plans.mdのタスクを実装。スコープを聞いて自動判断、1タスクから全タスクまで。Use when user mentions '/work', execute plan, implement tasks, build features, work on tasks, 'do everything', 'implement', '実装して', '全部やって', 'ここだけ'. Do NOT load for: planning, reviews, setup, deployment, or breezing (team execution).
Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
어떤 주제/과제든 받아서 스스로 팀을 구성하고 조사·분석·검토·결과도출까지 처리하는 범용 에이전트 팀 오케스트레이터. "팀으로 분석해줘", "에이전트 팀으로 조사해줘", "다각도로 검토해줘", "심층 분석 부탁해", "여러 관점으로 봐줘", "think-team", "think team" 키워드로 트리거. 단순 질문이 아닌 복합적 판단, 조사, 전략 결정이 필요한 모든 상황에서 사용.
Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.
Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available; otherwise guide the user to enable `openaiDeveloperDocs`.
Set up deterministic commands, worktrees, and quality gates so agents can run safely in this repository.
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.
Fix issues found by stripe-audit. Reconciles configuration drift, fixes code patterns, and resolves discrepancies.