Total 50,370 skills, Code Quality has 2287 skills
Showing 12 of 2287 skills
Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
Use when the user asks to review pull requests, analyze code changes, check for security issues in PRs, or assess code quality of diffs.
Split a large ***plain module into smaller modules grouped by logical domain. The resulting modules are connected via a requires chain so that functionality is 100% preserved. Use when a module has grown too large and its functional specs span multiple distinct concerns that would be clearer as separate modules.
Analyze a functional spec to determine if it is too complex for the renderer. A spec is too complex if it would produce more than 200 lines of code changes. Use after drafting a new functional spec (during `add-functional-spec`, or per spec during `add-functional-specs`) to verify it fits within the complexity limit before inserting it.
Code review closeout for Claude Code, Codex, OpenCode, and DeepSeek TUI: local dirty changes, branch vs main, parallel tests.
Use this skill when > Configure automated code quality checks at commit time using Husky and lint-staged. Sets up pre-commit hooks for formatting (Prettier), type checking, and tests. Adapts to existing project configurations and omits missing scripts gracefully.
Use this skill when > Identify architectural friction and propose deepening opportunities — refactors that turn shallow modules into deep ones for better testability and AI-navigability. Use when improving architecture, finding refactoring opportunities, consolidating tightly-coupled modules, or making a codebase more testable.
Builds and queries code knowledge graph for dependency analysis, references, implementations, and architecture overview. Use when starting work on unfamiliar codebase or before refactoring.
Use when reviewing a PR/MR diff and producing a structured finding list — covers security, logic, performance, cross-file impact, test coverage, and spec compliance. Posts a sticky summary comment plus inline review comments to the PR. NOT for writing PR descriptions, design reviews requiring business judgment, or deep CVE/supply-chain audits.
Build and maintain project-specific review policy for `agentic-review` by combining repository docs (`AGENTS.md`, `ENGINEERING.md`, `CONTEXT.md`/`CONTEXT-MAP.md`, ADRs), repository-mined conventions, and structured user input, then writing machine-usable policy files under `<docs-dir>/review/policies/`, including audit-governance metadata consumed by `agentic-review`. Use when the user wants architecture integrity checks (onion/clean/hexagonal), module-specific review rules, dependency-direction policy, naming/inheritance convention enforcement, stricter project/domain review standards, or explicit auditability requirements for specialist review coverage.
Analyze code for logic bugs, error handling issues, and edge cases. Detects off-by-one errors, null handling, race conditions, and incorrect error paths. Use when reviewing core business logic or complex algorithms.
arthrod's coding philosophy and dispatcher. Universal red-green TDD, stacked PRs, test-always, evidence-before-claims. Routes to conejo-code (active coding), conejo-frontend (strict UI), conejo-merge (calm PR/merge). Use when starting any coding work or deciding how to approach a task.