Total 52,935 skills, Code Quality has 2396 skills
Showing 12 of 2396 skills
Identify refactoring opportunities by surfacing architectural friction. Apply the deletion test, deep-modules vocabulary, and seams analysis. Each opportunity becomes its own evanflow-writing-plans cycle. Use when reviewing code for refactoring, when a file has grown too large, or when architecture concerns surface during feature work.
Fix Python code formatting issues using the Ruff formatter. Use when: (1) Formatting errors are detected by ruff format --check, (2) Python files need to be formatted to match project style, (3) Pre-commit hooks or CI fail due to formatting issues.
Build a compilable type-level skeleton from a high-level architecture spec before writing any implementation logic. Use when you have an architectural assessment, design doc, or restructuring plan and need to prove the new architecture is sound before migrating code. Also use when asked to "scaffold the new architecture", "create type stubs", "build the shell", "flesh out this spec", "skeleton the modules", or any request to turn architectural intent into verified structure. This skill follows the "Human Builds the Shell" paradigm: types are hard constraints that the compiler enforces, so if the skeleton compiles, the architecture is structurally sound. Especially valuable for large refactors where you don't trust agents to maintain coherence.
Use when the user asks to fix, debug, or make a specific feature/module/area work end-to-end. Triggers: 'make X work', 'fix the Y feature', 'the Z module is broken', 'focus on [area]'. Not for quick single-bug fixes — this is for systematic deep-dive repair across all files and dependencies.
Use skill if you are writing or reviewing framework-agnostic TypeScript and need strict typing, tsconfig/lint decisions, safer refactors, or guidance on generics, unions, and typed boundaries.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Sign, verify, and track fix-marker regressions over time using a deterministic Ed25519 witness manifest. Works in any project — clone the toolkit, run init, register fixes, regen on each release.
Use when writing, fixing, or editing TypeScript data models, DTOs, discriminated unions, classes, object boundaries, optional fields, null or undefined absence, repeated conditionals, impossible states, or object-chain access.
This skill should be used when the user wants to review code, audit a diff, get a second opinion on changes, or run an adversarial review of files in the current working tree. Common triggers include "review this code", "audit this diff", "find issues in", "second opinion on this", "harsh review of", "adversarial review", and "security review of". Picks one or more reviewer personas (adversarial, security, architecture, performance). Reviews local files, `git diff`, or `git diff --staged` only — does not fetch external content. Runs in one of four modes: single-agent (one persona in the current agent), cross-model handoff (independent second opinion via another local AI CLI, with secret-shield preflight + prompt-shield wrap), multi-bg-agent (one persona per parallel background subagent), or agent-team (Claude Code Teams or equivalent on supporting agents). Skip when the user wants formatting fixes (use a linter) or refactoring patterns (use ts-best-practices or ts-best-practices-functional).
Govern inline documentation coverage and comment quality in repo-owned source files. Use when Codex needs to audit or fix file headers, type docs, function or method contract docs, non-obvious inline comments, generated-file exclusions, or repo documentation rules for TypeScript, JavaScript, and Swift projects, including setting up a reusable docs/rules policy in a project-agnostic way.
Simplify existing code without changing behavior. Focus on local complexity reduction such as flattening nesting, extracting readable helpers, removing dead code, consolidating obvious duplication, and improving names. Use when the user explicitly asks to simplify, clean up, or reduce complexity in existing code.
Runs validator checks only without AI reviews for requests such as "run validator checks", "check without reviews", or "validate before commit without AI review".