Loading...
Loading...
Found 21 Skills
Recursive tech-audit & decision-tree mapping. Use when the user wants to break down a requirement, audit a tech stack, map dependencies, or plan an implementation.
Turn casual ideas, vague goals, plans, or designs into clearer decisions through scoped questioning, decision-tree review, and optional records.
Best practices for agents managing PostHog skills via the MCP `skill-*` tools — how to discover, read, create, update, and refactor skills efficiently, especially large skills with many bundled files. Use whenever you are about to call any `skill-*` tool, asked to author or edit a shared skill, or troubleshoot why a skill write was rejected. Pairs with `skills-store` (which covers the raw tool surface) by adding the decision-tree, efficiency, and pitfall guidance.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features
Interview-driven flow picker. Use when the user is unsure which skill/flow/pipeline fits — new project kickoff, cross-domain work, or a fuzzy situation. Reads the three routers live and recommends ONE flow. Not for tasks whose owner is already obvious.
Questionnement structuré pour cadrer une feature ou brainstormer une app : une question à la fois, descend l'arbre de décision, recommandation justifiée. Utilise sur /interroge, "aide-moi à planifier", "j'ai une idée de feature/app".
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use whenever the user wants to stress-test a plan, get grilled on their design, mentions "grill me", "challenge my thinking", "poke holes in this", "play devil's advocate", "review my approach", "what am I missing", "pressure test", "tell me why this won't work", or asks for feedback on a plan, proposal, architecture decision, or technical design. Even if they're just explaining an idea or asking "does this make sense?", treat it as a signal to invoke this skill and interview them thoroughly. Don't wait for an explicit "grill me" — any request for input on a plan or decision warrants this.
Interview the user relentlessly about whatever they want to work on — a plan, task, design, idea, feature, architecture decision, or anything else — until reaching shared understanding. Walk the decision tree one branch at a time, resolving dependencies between decisions. Use when the user says "grill me", wants to stress-test a plan or idea, wants to be interviewed about a design, or wants to flesh out an under-specified task.
Skill index and decision guide. Use to pick the right Effect Skill quickly and follow a minimal decision tree.
This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions. Use this skill when users ask to pitch a new research idea, work through a project problem, evaluate project risks, plan research strategy, navigate decision trees, or get help choosing what scientific problem to work on. Typical requests include "I have an idea for a project", "I'm stuck on my research", "help me evaluate this project", "what should I work on", or "I need strategic advice about my research".
Use this skill when > Conduct a comprehensive plan or design stress-test through systematic questioning. Interviews relentlessly about every decision point, resolves interdependencies progressively, and traverses the complete decision tree. Use when thoroughly vetting a proposal, design, or architecture before committing to it.