Loading...
Loading...
Found 117 Skills
Richard Feynman's Integrity Audit applied to any analysis, business plan, or decision. Spawns a team of specialist agents — Source Auditor, Self-Deception Hunter, Translation Tester, Cargo Cult Inspector, Confidence Inverter — who each apply a distinct lens from Feynman's framework to detect dishonesty, self-deception, and cargo cult reasoning. The lead synthesizes into a verdict: is this analysis honest, or is it fooling itself? Use when the user says "feynman this", "integrity audit", "is this honest", "am I fooling myself", "cargo cult check", or wants to stress-test any analysis, plan, or claim before trusting it. Works standalone or as a meta-audit after /munger or /thiel.
Spawning Plan. Use when user wants to spawn agents, create a team, or coordinate multiple agents. Automatically gathers context, asks team topology questions, outputs clean TEAM PLAN markdown, and gets user approval. 3 steps: context gathering → questions → present plan. **CRITICAL**: MUST NOT SPAWN AGENTS SKIPPING THIS SKILL, USE ALWAYS.
This skill should be used when the user asks to "팀 구성해줘", "team assemble", "전문가 팀으로 해줘", "팀으로 해줘", "swarm", "병렬로 전문가 팀", or wants to decompose a complex task into specialist roles executed via TeamCreate. Also triggers when user describes a task clearly benefiting from parallel expert execution.
Generative ideation engine. Takes a domain, trend, question, or constraint and produces 15-30 novel possibilities — things that might be true, businesses that could exist, futures that could unfold. Spawns a team of 6 specialist agents — Signal Scout, Analogist, Inverter, Combinator, Contrarian, Futurist — who each generate ideas from a distinct creative angle. The lead cross-pollinates across agents, finds unexpected combinations, and ranks the output by novelty × plausibility. Use when the user says "brainstorm", "what could exist", "what's possible", "generate ideas", "what might be true", "possibilities", or presents a domain and wants divergent exploration rather than evaluation of a specific idea.
Scans the codebase against another skill's criteria using a parallel agent team. Use when the user says /scan <skill-name> to audit code quality, find violations, or assess conformance to best practices.
Multi-agent coordination discipline: one-message-then-wait (send complete context, wait for reply before sending again), idle notifications are heartbeats (no action unless extended + blocking + user asked), no polling loops (event-driven only), never fabricate agent responses (wait for real system events), sequential agent spawning (acknowledge between each), and proper shutdown protocol (request, wait, respect rejection). Activate when orchestrating multiple agents, managing agent teams, coordinating handoffs between agents, spawning subagents, or building multi-agent workflows. Triggers on: "coordinate agents", "spawn multiple agents", "manage agent team", "agent keeps sending messages", "polling loop", "agent idle", "shut down agent", "multi-agent workflow", "agent handoff", "coordinate parallel work", "stop bothering the other agent". Also relevant when an agent is fabricating responses, sending follow-up messages before replies arrive, or reacting to idle notifications unnecessarily.
Annie Duke's Decision Quality framework applied to a business decision. Spawns a team of specialist agents — Resulting Auditor, Calibrator, Pre-Mortem Analyst, Quit Strategist, Process Architect — who each apply a distinct lens from Duke's framework to evaluate whether a decision is sound regardless of outcome. The lead synthesizes into a stacking analysis: which biases are operating, which process flaws exist, and the honest Duke verdict. Use when the user says "duke this", "is this a good bet", "should I quit", "evaluate this decision", or faces any high-stakes choice under uncertainty and wants rigorous decision-process analysis. Works as a standalone analysis or after /office-hours.
Manus-style context engineering for Agent Teams. Coordinate multiple Claude Code instances with shared planning files. Use when complex tasks need parallel work (code review, debugging, feature development). Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1.
[BETA] Execute work plans with external delegate support. Same as ce:work but includes experimental Codex delegation mode for token-conserving code implementation.