10,338 tagged Code review, measured the same way as everything else here.
Browse within: LLM 140ai-coding 136cli 125agent 94skills 92agents 88agentic-ai 85claude-code-plugin 83javascript 60copilot 55claude-code-skills 50opencode 47openai 42plugin 41
mhrsdev/AI-Agent-Skills-Library
Skill Claude CodeCodex
Audit designs against 19 rules across Figma files and code (HTML/CSS/React/Vue/Tailwind). Auto-detects framework and design system (MUI, Chakra, shadcn/ui, Ant Design, Radix, Bootstrap). Runs code superpowers across all 19 categories: aria, focus, contrast, tokens, responsive, motion, forms, navigation, spacing…
Skill Codex
Learn how a GitHub user reviews code from up to a year of their real review comments, then review a change as that person — in chat only, never posted to GitHub. Invoked bare, it ensures the profile exists and is current, then immediately reviews. Use when the user asks to "review this as me" or "like me", asks what a…
Skill Claude Code
A Japanese-language repository audit skill that checks software against the IEEE-CS/ACM Software Engineering Code of Ethics and against deceptive interface patterns. An audit is a documented inspection based on evidence.
Skill Claude CodeCodex
Evaluate whether AdCP (Ad Context Protocol, agenticadvertising.org) — or a concrete AdCP implementation such as a seller agent, buyer agent, or orchestrator — is safe, interoperable, operationally viable, and ready for pilot or production use. Combines a weighted decision scorecard, hard safety gates that override any…
Skill Claude CodeCodex
Channel operator (IRC handle @techlead) for the mARC agent team. Compiles chat demands into ready-to-execute work, records them on the GitHub Project board/Issues, and dispatches to specialists (@dev, @sre, @design, @sec, @rev, @research). Invoke with /tech-lead to turn discussion into tracked, delegated tasks.
Skill Claude CodeCodex
Guide for using openlens to review code. Triggers on: "review my code", "check for bugs", "security scan", "run openlens", "set up code review", "openlens".
Skill Claude Code
Root-cause analysis and QA review for a PR, branch, or stack trace. Detects bugfix vs feature, then for a bugfix finds the commit that introduced the bug (the suspect set, via git blame/log), the bug's life story (intent, releases it shipped in, hotspot recurrence, fix completeness), and explains why it broke; for a…
Skill Claude CodeCodex
Run a structured codebase audit — map architecture, assess health (compliance / tests / docs), perform deep analysis (security / performance / code quality), and synthesize a prioritized roadmap. Use this skill when the user says things like 'audit the codebase', 'understand this project', 'find problems', '/audit'…
ZeusYue/acceptance-driven-development-skill
Skill Claude CodeCodex
Use when the user explicitly asks to compare or reuse lessons across projects, inspect another project's documented history, or refresh/rebuild the shared expmemory.md cache. Also use when ADD requests an approved global-cache refresh after project finalization. Do not use for ordinary coding, small changes, or…
valon-technologies/mine-best-practices
Skill Claude Code
Extract best practices from PR review comments to build a curated library for code review automation.
Skill Codex
Turn exact or picked GitHub issues into independently reviewed draft PRs using isolated Ponytail developers and reviewers. Use for issue-to-PR runs, picked batches, or continuation; batches default to parallel.
Skill Claude Code
A diagram-making workflow that turns confirmed process, architecture, and data-flow descriptions into animated, looping GIFs. It uses SVG as an intermediate format and checks the rendered result before delivery.
Skill Claude Code
Review code for correctness, security, TypeScript quality, and performance. Run before any PR or deploy.
Skill Claude CodeCodex
Run nerviq on the current repo and summarize the score, top gaps, and next command.
Skill Claude CodeCodex needs its repo
Run the structured adversarial Claude review flow, including optional focus text and stricter challenge-oriented output.
Skill Claude CodeCodex
Generate and incrementally maintain an interactive architecture map plus a per-module code-quality audit (health scores 0-100, smell findings, lines-of-code, and a clickable dependency graph) for any codebase. Use when the user wants to visualize a project's functional modules, audit or score code quality, check…
Skill Claude CodeCodex
· Build/review AI apps: LLMs, RAG, embeddings, agents, evals, local inference. Triggers: 'llm', 'rag', 'embedding', 'openai sdk', 'agent loop', 'fine-tune', 'ollama', 'vllm'. Not for MCP (use mcp).
Skill Claude CodeCodex
A method for reviewing code, bugs, diffs, branches, and pull requests. A diff is the set of changes between two versions of code, and a pull request is a proposed change submitted for review.
Skill Claude Code
Pre-production code review against a user-chosen healthy point. Use whenever a user wants to review a branch before shipping, asks if code is ready to merge, wants blockers identified before a PR lands.
Skill Claude Code
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
unrealandychan/clean-code-skill
Skill Claude CodeCodex
Use when reviewing code for Clean Code, DDD, Harness Engineering, or Agentic Engineering issues. Covers readability, maintainability, testability, observability, and AI-agent guardrails.
Skill Claude CodeCodex
Compare current code changes against a PRD to find gaps, deviations, and opportunities. Use before opening a PR, after finishing a feature, or to verify requirement coverage.
Skill Claude CodeCodex
Clean-code engineering standards for writing, refactoring, and reviewing code in any programming language. Use this whenever the user asks to write clean code, follow clean-code principles, refactor for clarity, improve naming, reduce complexity or duplication, separate concerns, tighten error handling, work…
Skill Codex
Run a bounded SPEC → BUILD → REVIEW → REPAIR workflow until verified or blocked. Explicit invocation only: $specloop in Codex or /specloop in Claude Code.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: