Review & quality
19,289 rows, by stacks then stars
1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid
devrimcavusoglu/skern/tests/manual/scenarios/09-template-skills/templates/code-review Skill
7★ repoMass Skills Manager for Agents on AI Driven Development
MShekow/package-version-check-mcp/io.github.MShekow/package-version-check-mcp MCP server
7★ repoReturns the latest package / dependency / tool versions for Python, NPM, Go, Docker, Helm, etc.
paarths-collab/github-pr-context-mcp/io.github.paarths-collab/github-pr-context-mcp MCP server
7★ repoAI code review grounded in your repo history. Supports Test Gen and Security Audits.
viacheslav-tronko/claude-code-harness/.claude/skills/concept-explanation Skill
6★ repoClaude Code Harness
Nolpak14/getregdata/skills/australia-abn-lookup Skill
6★ repoOfficial business-registry data for AI agents - KYC/AML, beneficial owners (UBO), insolvency, credit risk and adverse-media screening across Europe, the US, the UAE, Africa and Latin America. Start with a one-call Poland KYB verdict: one NIP or KRS in, one verdict out. Sourced via Apify; pay-per-result.
PleasePrompto/domain-check-skill/skills/domain-check Skill
6★ repoAsk your AI coding agent if a domain is free — and get a real answer. Works for any TLD, including .de / .eu / .at / .ch where most checkers give up. Plugin for Claude Code, extension for Gemini CLI, skill for Codex & OpenCode. Pure Python, zero setup.
jeltehomminga/figma-design-skills/skills/design-fidelity-verify Skill
6★ repoTwo composable Claude Code skills for design-to-code fidelity: extract exact specs from Figma, then verify the running web or mobile app matches them.
BackToCimaCoppi/Praxis/skills/adversarial-review Skill
6★ repo给「AI 驱动开发」立规矩的 Claude Code skill 方法论库:七层文档治理 · 对抗评审闭环 · 任务总控三驾马车,外加 goal 自主执行契约、测试三件套、老代码考古等共 23 个 skill —— 让 AI 写代码又快又不失控。
ni032mas/agent-skills-ru/skills/ru-legal-contract-review Skill
6★ repoRussian AI agent skills for legal, compliance, business, product and engineering workflows
loremaster-ai/loremaster/client-template/.claude/skills/backlog-complete Skill
6★ repoAI scrum-master / PM skill pack for Hermes Agent — living project wiki (lore vault), human-approval gates, conflict detection
ldilov/harness-forge/skills/api-contract-review Skill
6★ repoAI coding agent runtime that makes LLMs understand your codebase with repository-aware context, memory, and continuous learning
motiful/self-review Skill
6★Structured alignment audit for AI agents and creators. Checks drift across 4 pillars and 6 dimensions — from design currency to artifact verification. Report-only, never auto-fixes.
Antimatter code quality review
CheckPickerUpper/skills/skills/engineering/antimatter-code-quality-review Skill
6★ repoAgent skills for correctness-first engineering.
NguyenAn2812/scientific-research-helper Skill
6★Claude Skill for scientific research, thesis, and academic paper writing. Analyzes documents, provides detailed feedback, suggests structural improvements, citations, and academic language enhancement.
dynobox/dynobox/.agents/skills/commit Skill
6★ repoCross-harness testing for multi-step agent flows
mainframecomputer/skills/skills/review-as Skill
6★ repoAgent skills from the Mainframe team
HystonKayange/skill-probe/examples/sample-skills/.claude/skills/commit-writer Skill
6★ repoRuntime-agnostic, co-loaded-aware auditor for AI agent skill libraries — measures which skill actually fires, with statistical confidence + a Bayesian fix-loop.
APareek89/power-coding Skill
6★Mindful-coding OS for any LLM coding agent (Claude Code, Codex, Gemini CLI) — the Five Forces: session handoff, eval loops, vibe-debugging diagrams, FMEA failure scans + a pre-commit secret gate. Plain markdown, no daemons.
swatchdog-dev/swatchdog-mcp/dev.swatchdog/validator MCP server
no license6★ repoOn-demand drift checks: declared CSS color, radius, spacing & type vs your own tokens or a pack
noordeen123/culprit/io.github.noordeen123/culprit MCP server
6★ repoDeterministic, offline root-cause analysis and pre-commit fix verification for coding agents.
tercel/code-forge Skill
no license5★Complete development workflow — from TDD-driven implementation plans to execution, debugging, code review, git worktree management, branch lifecycle, and parallel agent dispatch.
aleksandr-chaika/flutter-clean-arch-skills/skills/flutter-guide Skill
5★ repoComplete Flutter development pipeline — Clean Architecture + BLoC + Maestro QE. Autonomous agents for PM, dev, review, testing
hughedward/gitflow-skills/skills/gitflow Skill
5★ repogitflow-skills - Git Flow workflow for Claude Code & OpenClaw. No extra tools needed, pure Git implementation.
kimon1230/claude_extensions/skills/code-review Skill
5★ repoCustom hooks, skills, and rules for Claude Code: adds automatic Python formatting, context persistence across sessions, parallel subagent workflows, and a status line.
netopsengineer/axiom/plugins/axiom-git/skills/commit-message Skill
5★ repoAxiom is a curated marketplace of shared plugins for Claude Code and Codex.
patrickserrano/lacquer/core/skills/advisor-checkpoint Skill
5★ repoGo CLI + profile templates that standardize how Claude Code works across every project
leodisa/compliance-review-skill/plugins/compliance-review/skills/compliance-review Skill
5★ repoClaude skill on a repeatable, evidence-based gap analysis of a code repository against the EU AI Act, GDPR, and the NIS2 Directive (EU 2022/2555)
Aidress skill verify transact and rate an unknown agent
Aidress-ai/aidress-skill-verify-transact-and-rate-an-unknown-agent Skill
5★Discover, Verify, Transact, and Rate an Unknown AI Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for logistics agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
jeeinn/claude-skills/php-code-review Skill
5★ repoclaude skills for my work
Tuminha/dental-ai-skills/clinical-evidence-reviewer Skill
5★ repoAI Skills for Dentists - Research critique, clinical evidence review, and content creation tools for Claude Desktop and Codex
yuangao-tum/rebuttal-skills/skills/nlp-rebuttal Skill
5★ repoClaude Code skills for writing peer-review rebuttals: process + tactics (write-rebuttal) and 28 per-concern answer templates (nlp-rebuttal)
goingli0324/web-security-reviewer Skill
5★Claude Code skill: defensive security review of your own code (Apps Script, frontend, backend)
mryo0826/aidd-practice-guide/.claude/skills/requirements-review Skill
no license5★ repoアジャイル/スクラムの規律を、AIとの協働に適用する — Claude Code / Agent Skills を活用したAI駆動開発(AIDD)の実践ガイド
danygiguere/audit-skills/.agents/skills/audit-api-validation Skill
5★ repoLanguage- and framework-agnostic audit checklists for AI coding agents — security, correctness, and operability. Works with Claude Code, GitHub Copilot, Cursor, Codex CLI, OpenCode, and any agent that can read files.
Far-200/think-before-code/skills/code-review-coach Skill
5★ repoSocratic Agent Skills for learning problem-solving and software-engineering judgment — one question at a time.
disruptionjoe/caret/research/reports/gstack-caret-it-tests/raw Skill
5★ repoCaret^ cuts repeated agent instructions down to compact notation. Across our sample set, prompt length was reduced by 95.8% by rewriting agent skill and persona files using Caret notation. This is for you if you ever draft or use Markdown files as agent skills or personas. If you design harnesses, it is a no brainer.
zephexMCP/agent-skills/skills/zephex Skill
5★ repozephex Hosted MCP skill pack 10 tools, 13 editors (Claude Code, Cursor, VS Code + 10 more). Live repo analysis package upgrades, codebase scoping. No token waste.
iktakahiro/python-fastapi-ddd-skill/.codex/skills/commit Skill
no license5★ repoA practical template for Building AI Agent Skills with Python, FastAPI, and Domain-Driven Design (DDD).
ghillb/swarmux/.agents/skills/swarmux-release-playbook Skill
5★ repoAgent-first tmux async task orchestration CLI
sdcrd/trust-guard Skill
no license5★Post-edit verification that catches silent AI coding failures before they reach production. Zero executable code. Works with 30+ agents.
Gingg7260/affiliate-skills Skill
5★Automate affiliate marketing with 45 AI skills for research, content, pages, tracking, and optimization across any AI agent
NegusNati/verify-et-api/skills/verify-et-api Skill
5★ repoAgent skill for integrating and debugging the Verify.et transaction verification API
twk0672005/sentence-to-site/skills/adversarial-quality-loop Skill
5★ repoOne sentence in, a verified website out. Agent skills that close the gap between vibe coding and software engineering - so people with no coding background can build a website that holds up.
Love-Ash/archforge/skills/archforge-pptx-lint Skill
5★ repoThe preflight linter for AI-generated PowerPoint: silent font fallback (deep CJK coverage), collisions, off-canvas text, and AI tells in built .pptx files
recallnet/codecontext/.claude/skills/context-diff Skill
no license5★ repoForce agents to read critical context left by other agents, enforced by linting and freshness checks.
mataeil/OODA-loop/skills/check-tests Skill
5★ repoAutonomous operations layer for Claude Code — opens small reviewable PRs for your live side project and re-orients from which ones you merge or reject. HALT file + hard cost cap; you stay in command.
colinwilliams91/gaitor-orchestrator-cli/.agents/skills/checkpoint-commit Skill
5★ repoCLI for AIDDLC -- Scaffolded, parallelized, context aware agent runtime in seconds.
sergeyklay/.agents/.agents/skills/babysit-pr Skill
5★ repoMy personal, curated set of artifacts for AI coding agents
Vambrocop/EvidenceForge/skills/environment-life-review-forge Skill
5★ repoAgent skills for systematic review, meta-analysis, umbrella review, and AI-assisted evidence synthesis.
zyl100200/clean-commit-skill Skill
5★Keep AI noise out of your git history. A cross-platform agent skill that blocks Co-Authored-By bots, generator footers, and model-name watermarks in commit messages — so git log, git blame, and changelogs stay signal, not spam.
PCI DSS v4.0.1 Compliance Checker
shyshlakov/pci-dss-mcp/io.github.shyshlakov/pci-dss-mcp MCP server
5★ repoPCI DSS v4.0.1 compliance scanner for Go payment services, delivered as an MCP server
mdrobniu/xsoar-pack-dev-skill Skill
4★Claude Code skill for Cortex XSOAR content pack development lifecycle
AsteroidHunter/did-ai-write-this/src Skill
4★ repoA Pangram CLI tool / claude code skill for your agents to detect AI generated text
Kaspa sovereign architect engine
gryszzz/Kaspa-Ai-Agent-Skill/skills/public/kaspa-sovereign-architect-engine Skill
no license4★ repoKaspa sovereign architect engine ; engineering skill for AI agents, with source-gated protocol intelligence and release packaging.
tinoimammp/vantage-security-agent/skills/vantage Skill
4★ repoAI-powered vulnerability scanner plugin for Claude Code with 28 agents statically scan web & mobile repos for OWASP Top 10 / Mobile Top 10 vulnerabilities, validate findings, and optionally auto-fix them. No live requests, ever.
zb-sj/review-buddy Skill
no license4★Chunked interactive PR review — walks you through PRs chunk by chunk, surfaces existing reviewer feedback, and helps post thoughtful comments without cognitive overload.
Klionskiy/claude-mobile-mvp-skills/plugins/mobile-mvp-product/skills/appstore-mvp-review Skill
4★ repoClaude Code skills for designing mobile MVPs in Figma, generating SwiftUI from Figma, and reviewing App Store readiness.
junyoung2015/pr-review-skill/skills/pr-review Skill
4★ repoAI-powered PR review pipeline for Claude Code. Turns 30-45 min code reviews into ≤ 8 min structured reviews.
SreeDharshan-GJ/experiment-audit/dev/experiment-audit-plugin/skills/experiment-audit Skill
4★ repoScientific Research Reasoning Engine for analyzing experimental evidence, evaluating scientific claims, and generating structured research reports.
WillInvest/ClaudeX/skills/build Skill
4★ repoMulti-model collaboration for Claude Code: Codex as second-opinion reviewer in brainstorming + autonomous Codex-writes / Opus-reviews plan→impl pipeline.