metacognition skills

jongwony/epistemic-protocols

Skill Claude CodeCodex

Vet working context by dialectical antithesis before action. Type: (ContextSuspect, User, VET, WorkingContext) → VettedContext.

jongwony/epistemic-protocols

Skill Claude CodeCodex

Detect application-context mismatch after execution. Fires when correct output may not fit the actual context. Type: (ApplicationDecontextualized, AI, CONTEXTUALIZE, Result) → ContextualizedExecution.

jongwony/epistemic-protocols

Skill Claude CodeCodex

Convergence-paced review-resolve loop over a change and its governing surfaces. Verifies each finding against the codebase and the base it is measured from, then re-reviews until each is disposed of.

LilMGenius/polysona

Skill Claude CodeCodex

Extract your persona into CLAUDE.md or AGENTS.md for use in any AI agent.

LilMGenius/polysona

Skill Claude CodeCodex

Start a deep psychology-based interview to extract your persona using 10 frameworks.

LilMGenius/polysona

Skill Claude CodeCodex

Show current persona health and content pipeline status.

syzkillall/comprehensive-thinking-skill

Skill Claude CodeCodex

A structured method for making careful judgments about difficult or uncertain problems, including technical and non-technical decisions.

skyf0xx/better-thinking

Skill Claude CodeCodex

Look up a named external framework (design thinking, lean startup, ...) in recipes/, then execute its mapped skill sequence stage by stage as a real orchestrated run rather than a reference doc. If no framework is named, list every recipe in recipes/README.md with a one-line description and run whichever one the user…

skyf0xx/better-thinking

Skill Claude CodeCodex

🧠 Classify an incoming task by its shape (decision, diagnosis, research, creative, communication, learning, negotiation) and its stakes, then select which skills to deploy at what depth. Use as the first move on any nontrivial task, before any substantive work begins.