Loading...
Loading...
Found 367 Skills
Execute all plans in a phase with wave-based parallelization
Use for tasks that may need brief clarification before implementation but don't warrant a full plan. If clear, dispatches an implementer immediately; if unclear, asks 1-3 questions, proposes an approach, gets approval, then dispatches. No plan file — lighter and faster than nash + stoudemire.
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Inspect active background research work including running processes, scheduled follow-ups, and pending tasks. Use when the user asks what's running, checks on background work, or wants to see scheduled jobs.
Extract and analyze YouTube video content (transcripts + metadata). Use when the user explicitly requests to analyze, summarize, extract wisdom from, or get context from a YouTube video. Supports wisdom extraction, summary, Q&A prep, key quotes, and custom analysis. Does NOT auto-trigger on YouTube URLs - only when analysis is explicitly requested.
Use when coordinating non-trivial implementation work, executing implementation plans, or modifying AGENTS.md/CLAUDE.md.
Load this skill when the user mentions `ulw` or `ultrawork`.
Use when multiple subtasks have no shared files or dependencies and can be executed simultaneously.
Execute a single DAG step as an autonomous background sub-agent. Sibling of phase-running for DAG plans produced by v-planning. Reads a step-<n>.md file directly, atomically claims it via frontmatter status, runs the three-bucket Success Criteria, and reports back. Spawned by v-implementing or by /run-step.
Optimize CLAUDE.md and docs/ ecosystem following Boris Cherny's best practices
Build a personalized reading profile from your Readwise Reader data, used by triage, quiz, and other skills
Execute from requirement analysis to frontend design document creation