metacognition
Checks task understanding, evidence, scope, and stopping conditions at decision-changing moments. Use when starting repository work, changing task type, encountering unexpected evidence, or completing a meaningful phase.
38,472 Skills
Search uses this published catalog; rankings and counts are snapshots.
Checks task understanding, evidence, scope, and stopping conditions at decision-changing moments. Use when starting repository work, changing task type, encountering unexpected evidence, or completing a meaningful phase.
Applies repository-aware TDD, observable test design, and applicable quality checks. Use when changing behavior, writing tests, or reviewing test quality.
Selects the narrowest sufficient test boundary from requirements, repository evidence, and maintenance cost. Use when deciding integration or E2E coverage.
Scaffold a new OKF knowledge bundle in this project — run when starting a wiki or adding a bundle under knowledge/.
Answer from the knowledge bundle. Use when the user asks what they/the project know about something, wants to look something up, explore connections, or compare
Generate unit and UI tests for specified code with edge cases and mocks. Triggers: "generate tests", "write tests", "add tests", "test coverage".
Codebase analysis with A-F grades explained in plain language for non-technical stakeholders. Self-contained iOS/Swift audit. Triggers: "plain talk", "plain talk report card", "stakeholder report", "non-technical audit".
Pre-release checklist: version bump, changelog, privacy manifest, store metadata, archive readiness. Triggers: "release prep", "prepare release", "ready to ship", "pre-release checklist".
Plan refactoring with blast radius analysis, dependency mapping, and rollback strategy. Triggers: "refactor", "safe refactor", "restructure", "rename type", "extract protocol".
Evidence-first deep reading for books, articles, PDFs, and document sets. Extract core claims, argument structure, supporting evidence, source locations, confidence levels, knowledge maps, and recall questions. Use when the user asks to deep-read, analyze an article, extract clai
Conduct a bounded 3-turn adversarial code review debate (Author vs. Skeptic) to uncover subtle edge cases and race conditions under 1,500 tokens.
Two-model pipeline routing high-level design to an Architect model, and mechanical search/replace edits to an Editor model to cut costs by 70%+.
Catalog captured:2026-11-21