Code Quality

codacy-automation helps Claude run Codacy workflows through Composio Rube MCP by discovering live tool schemas, checking the Codacy connection, and executing safer automation steps.

zero-hallucination-coder is a Code Generation skill for safer repository changes. It guides agents through Discuss, Map, Decompose, Execute, and Verify steps to avoid invented APIs, imports, paths, and placeholder code. Best for high-risk auth, database, migration, API, or multi-file work; skip it for trivial edits.

self-eval is a prompt-only Claude Code skill for honest post-work review. It uses two-axis scoring, devil's advocate reasoning, score persistence, and anti-inflation checks to evaluate AI work quality after tasks, code reviews, or work sessions.

pr-review-expert helps agents run structured GitHub PR and GitLab MR reviews with blast radius analysis, security checks, breaking-change detection, test coverage review, and prioritized merge-ready findings.

focused-fix is a Claude skill for deep feature or module repair. Use it when an area is broken end-to-end and needs scope mapping, dependency tracing, tests, logs, and a repair plan before code edits—not for quick one-line bugs.

karpathy-coder helps AI coding agents expose assumptions, avoid over-abstraction, keep diffs surgical, and define verifiable goals. Includes SKILL.md, references, expected JSON outputs, and Python checks for assumptions, complexity, diff noise, and goal verification.

adversarial-reviewer is a prompt-only Claude skill for adversarial code review. It reviews diffs, commits, or files through Saboteur, New Hire, and Security Auditor personas, classifies severity, and returns BLOCK / CONCERNS / CLEAN merge guidance. Best for pre-merge reviews of risky changes; it has no external dependencies.

The check skill reviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits. Use it when you need a disciplined check for Code Review before merge or release, with safety gates for dirty and untracked worktrees. It is not for exploring ideas, debugging root causes, or prose review.

typescript-magician helps solve hard TypeScript problems: deep generic design, strict typing cleanup, compiler errors, type guards, and advanced type transformations. Use it for typescript-magician usage when you need type-safe code generation, `any` removal, `infer`, conditional types, mapped types, template literal types, branded types, or utility types.

The kaizen skill guides small, safe code improvements for refactoring, architecture, workflow fixes, error handling, and validation. It favors iterative changes, design-time prevention, and minimal scope. Use it when you want a practical kaizen guide that improves code without over-engineering.

icpg adds a WHY layer to code understanding with ReasonNodes, formal contracts, and drift detection. Use it for code review, refactoring, and pre-task analysis when you need intent, ownership, and risk context before changing code.

rails-conventions is a practical Rails 8.x skill for building and reviewing production backend code. Use it to match local conventions for models, controllers, routes, Hotwire, jobs, APIs, testing, security, and performance. It is especially useful for backend development where the rails-conventions guide should follow the app’s existing patterns instead of generic defaults.

moyu-strict is a strict anti-over-engineering skill for Code Editing. It helps agents keep changes narrow, confirm scope before edits, avoid new abstractions, and skip unrequested tests, docs, dependencies, or rewrites. Use it when you want the smallest safe diff and predictable review.

moyu-ko is a code-editing skill that keeps changes minimal, scoped, and review-friendly. It helps avoid overengineering by editing only requested files, using the simplest fix, and asking when scope is unclear. Use the moyu-ko skill when you want precise diffs, focused bug fixes, and a practical moyu-ko guide for disciplined code edits.

moyu-en is a restraint-first skill for code editing. It helps keep changes surgical, avoid over-engineering, and limit diffs to exactly what the user asked for. Use moyu-en when you need precise, small patches, narrow scope control, and a better guide for minimal code updates.

The commit-hygiene skill helps you keep Git work atomic, reviewable, and easy to revert. Use it for commit boundaries, PR size limits, and stacked PR decisions. It is a practical commit-hygiene guide for Git workflows when a change set is growing too large.

code-review is a mandatory review workflow for code changes before commits and deploys. It helps teams run a structured /code-review step, choose an engine, and get actionable feedback instead of a generic pass. Ideal for pre-merge checks, release candidates, and high-stakes refactors.

github-pr-review is a GitHub PR review skill for collecting inline comments, PR-level review bodies, and replies, then organizing feedback by severity so you can fix blockers first. Use it to resolve PR comments, respond to reviewers, and update the branch with targeted commits and thread replies. It fits the github-pr-review guide for authenticated GitHub CLI workflows.

code-review is an AI-powered CodeRabbit skill for reviewing changed code, PRs, staged commits, and diff ranges. It helps catch bugs, security issues, and quality risks, then groups findings by severity so agents can act on them quickly. Use it for structured code review instead of generic critique.