Review & quality
19,471 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
web3blind/hermes-skill-quality-gate Skill
no license0★Public Hermes skill export prepared from a private Hermes skill.
0xLucas0x/pharos-agent-action-kit/pharos-allowance-guard Skill
0★ repoComposable Pharos Agent Skills: the missing ERC20 approval layer + safe multi-step DeFi plays + approval security auditor. Built on the official pharos-skill-engine.
in-asanz/internet-research-review Skill
no license0★Codex skill for high-quality public internet research review without paid APIs.
shuymn/skills/skills/adversarial-verify Skill
no license0★ repoPersonal agent skills
jpoindexter/self-insight-agent-skills/skills/si-blame-the-task Skill
0★ repoAI agent metacognition skills distilled from David Dunning's Self-Insight (2005): calibration, Dunning–Kruger awareness, the outside view, and feedback discipline for Claude Code, Codex, and compatible AI agents.
daniil2711/claude-vibe-workflows/skills/bug-review Skill
0★ repoМетод вайб-кодинга из альманаха Сухарева, упакованный в скиллы и авто-подсказчик для Claude Code: /prd, /bug-review, /sec-audit
frankxai/marine-agent-skills/skills/ethics-check Skill
0★ repoClaude Code skill pack for contributing schema-valid, sourced, ethics-checked artifacts to the Blue Life Commons / Ocean Intelligence System.
KaiSky0823/ks-deep-claim-audit Skill
no license0★Claude Code skill · 对别人宣称的 GitHub 项目/AI工具/产品/数据·性能·热度做深度地毯式核查,客观判真伪夸大,出逐条 verdict 报告
sergiobuilds/ux-workflow-check Skill
0★Find what users need but nobody wrote down. A forcing agent skill: intent-first, first-person UX gap discovery. Cross-agent (Claude/Codex/Gemini/Grok). MIT.
kmloureiro/agent-verify Skill
0★Token-minimal CLI verification harness for AI coding agents. Build the check with the feature; agents read PASS/FAIL, not DOM dumps. ~20 tokens, not 20,000.
lucasheriques/codescene-skill/skills/codescene-code-health Skill
0★ repoAgent Skill for CodeScene Code Health workflows
nikhonit/llm-mentions-skills/skills/mentions-check Skill
0★ repoAgent skills to track brand mentions, ranks & citations across ChatGPT, Claude, Gemini & Perplexity — AI brand monitoring + GEO for Claude, Cursor & any agent
krkrkrr/skills/skills/deps/conventional-changelog Skill
no license0★ repoMy agent skills
agent-packs/registry/plugins/eng-leader-workflows/.claude-plugin/skills/leadership-review Skill
no license0★ repoCurated registry of Agent Packs — packs, skills, and plugins for AI coding agents
mihirparmar-ai/agent-skills/wiki-lint Skill
no license0★ repoThe AI operating stack behind a real luxury travel advisory: editor-layer architecture + sanitized production Claude Code skills
mfraunhofer/claude-skills/check-domain Skill
0★ repoReusable Agent Skills for Claude Code
quiet-build/skills/skills/engineering/rebase-and-verify Skill
0★ repoReusable AI-agent skills maintained by quiet-build. Install: npx skills@latest add quiet-build/skills
jbegarek/potato-review-skill/potato-review Skill
0★ repoHarsh evidence-first POTATO review skill for academic, source, document, code, and project audits
smanaton/git-coach/skills/git-drill Skill
0★ repoHands-on git coaching skills for AI coding agents: real commands, plain-English why, undo-first recovery, and safe practice drills.
unopim/agent-skills/skills/unopim-code-review Skill
0★ repoAgent skills for UnoPim — domain-specific context for AI agents (Claude Code, Cursor, Windsurf) working in an UnoPim PIM codebase. Install: npx skills add unopim/agent-skills
ikhattab/agent-pr-review/skills/agent-pr-review Skill
0★ repoAgent Skill for reviewing AI-generated pull requests — triage, red flags, CI gaming, duplication, and workflow security.
Shaelz/codebase-trellis-skill/skills/codebase-trellis Skill
0★ repoA context-preserving Git/GitHub safety skill for AI coding agents.
maorodriguez/specgate/skills/specgate Skill
0★ repoValidated, auditable AI code generation as an Agent Skill — write code or review a PR, verify every API exists, and emit a decision trace.
payne0420/claude-ultracode-agents/codex-exec Skill
0★ repoClaude Code skills for delegating to external coding agents (Codex, Cursor, opencode), plus an ultracode workflow orchestration layer
TheophilusChinomona/idev/skills/api-contract-validation Skill
0★ repoClaude Code plugin: token-optimized dev workflow — cached project context, pattern scanners, build & wiring verification, session persistence, self-review. 23 skills, 3 agents, 4 commands.
harismh/agentic-council/council Skill
0★ repoAgent Skill that gathers independent analysis from existing skills, each in fresh context, then synthesizes different points of view.
JAlex1201/PR_Author_Best_Practices_Skill/.github/skills/pr-best-practices Skill
0★ repoA Claude Code skill for authoring strong pull requests - titles, descriptions, scoping, reviewer selection, and responding to feedback
maxgfr/ultraindex/skills/ultraindex Skill
0★ repoIndex a whole repo (code + docs) into a navigable, AI-analyzed encyclopedia — map + per-module entries + typed link-graph — so an AI works in huge codebases without filling its context. One auto-routing skills.sh skill with grounded, citation-checked analysis and optional local (Ollama) semantic search.
Incierge3789/aegis-boundary-skills/skills/aegis-boundary Skill
0★ repoCrawlora-org/crawlora-skills/skills/app-review-mining Skill
0★ repoCrawlora Agent Skills — structured public web data (search, e-commerce, social, finance, app stores, media, reviews) via the Crawlora REST API. Installable in any agent with the skills CLI or as a Claude Code plugin marketplace.
web3blind/hermes-skill-web3-risk-check Skill
no license0★Public Hermes skill export prepared from a private Hermes skill.
Modular robust systems architect
savedpixel/modular-robust-systems-architect Skill
0★AI agent skill for implementing modular, robust software architecture with scoped codebase discovery, clean boundaries, contracts, validation, migration safety, and verification.
jovd83/skill-vetting-reporter Skill
0★Security & trust vetting for AgentSkills: mandatory open-source scanner gate (Cisco, NVIDIA SkillSpector, Snyk, sentry), OWASP Top 10 for Agentic Applications mapping, and tiered review reports.
jamieafk/fable-check/skill Skill
0★ repoExtensive code review powered by Claude Fable 5 — a skill for Claude Code and Codex. Inspired by openai/codex-plugin-cc.
222-glitch/ship-check/ship-check Skill
no license0★ repoFree Claude Code skill: a scored 10-category production-readiness audit for Python scripts — findings cite file:line, no vague advice.
NPJigaK/unified-adversarial-review-skill/skills/unified-adversarial-review Skill
no license0★ repoPortable read-only Agent Skill for deep pre-ship adversarial review of code changes, plans, and ship-blocker risks.
lonelydoctor/survey-linter Skill
0★Audit your survey for biased questions before you send it — a Claude skill + zero-dependency CLI.
web3blind/hermes-skill-portfolio-review Skill
no license0★Public Hermes skill export prepared from a private Hermes skill.
JAlex1201/pr-review/.github/skills/pr-review Skill
0★ repoA Claude Code skill for writing collaborative code review comments
Nick2bad4u/git-commit-logically/skills/git-commit-logically Skill
no license0★ repoAn open-agent skill for committing outstanding git changes into coherent local commits.
Melmonster13/antigravity-skills-project/.agents/skills/database-schema-validator Skill
no license0★ repoTest bench for custom developer-agent skills: SQL schema validation, Conventional Commits formatting, JSON-to-Pydantic conversion, and license-header injection.
hoangCreative/ground-or-abstain Skill
0★A verification discipline for AI assistants: ground every load-bearing claim in a real source consulted now, or abstain. Community-first, never training memory. Origin: the Vietnamese discipline xac tin.
PabloViniegra/setup-graphify/skills/setup-graphify Skill
no license0★ repoAgent skill to integrate Graphify knowledge graph into any project
thdelmas/immune-check Skill
0★Immune Check — a pre-flight reflex that scans any outbound artifact for secrets/PII before it leaves the body. Stack-agnostic. The defense organ alongside octopus + rem-sleep.
shivamnegi92/yesman/skills/yesman-check Skill
0★ repoYour AI agent is a yes-man. This fixes it. No empty praise, no hype, no 'You're absolutely right!'. Works in Claude Code, Cursor, Codex, Copilot, Windsurf, Cline, Kiro, and more.
Determining git commit messages
brlin-tw/determining-git-commit-messages Skill
no license0★Provide guidelines on how to determine appropriate git commit messages that are compliant with project standards. It should be used when generating, modifying, or reviewing git commit messages.
Munizada/project-audit-council/plugins/project-audit-council/skills/project-audit-council Skill
0★ repoEvidence-based multi-pass repository audits for Codex, Claude Code, and Agent Skills-compatible coding agents.
linkyourskill-ai/lys-docs/.claude/skills/verify-course-content Skill
0★ repoPersona onboarding courses (AI tutor) for the LinkYourSkill platform — German-first with English mirror, authored with the lys-teach skill.
igapyon/miku-prompt-lint-skills/skills/igapyon-miku-prompt-lint Skill
0★ repoAgent Skill for reviewing prompts, context packages, and Agent Skill bundles for structure, clarity, and practical quality risks.
quantum-box/agent-packages/plugins/quantum-box/skills/adr-check Skill
no license0★ repoDistribution repository for agent skills and plugins
prasadmogulothu/agent-skills/ai-proxy-guard Skill
0★ repoReusable, token-optimized agent skills for autonomous development with Hermes, Claude Code & OpenCode. Multi-model orchestration patterns — context-checkpointing, human review gates, RLS security, GDPR consent, AI cost control, and test-fix loops. Framework-agnostic, agentskills.io compatible.
LevyBytes/AI-SKILL-git Skill
0★Agent Kaizen skill for Claude Code & Codex: faithful, task-routed Git reference, commands, flags, config keys & refspecs; staging, committing, branching, merging, rebasing, cherry-pick, revert, reset, stash, tags; log/diff/blame/bisect; remotes & push/pull; revision syntax; hooks, submodules, worktrees, reflog recovery.
DovahkiinYuzuko/map-pin-on-the-git Skill
0★[ENG]An AI agent skill to automatically generate documentation from Git commit logs as the Single Source of Truth (SSOT). / [JPN]GitのコミットログをSSOTとしてドキュメントを自動生成し思考プロセスを管理するAIエージェント用スキル
github-yjc/anlin-skill Skill
no license0★Agent skill for writing in Anlin's voice — 知乎摆烂写手风格模仿。Reverse-engineered from 38 original articles through systematic corpus analysis, blind audits, and iterative refinement.
AutoCAD AccoreConsole headless
Abo-Eyad/AutoCAD-AccoreConsole-headless Skill
0★An Agent Skill for trustworthy headless verification of AutoCAD & Civil 3D plugins — crash-marker liveness, determinism gating, and an evidence-gated pass/fail checklist.
dvnc-labs/design-md-drift-check Skill
0★Check DESIGN.md drift against real frontend tokens, components, and UI patterns.
Relocation logistics orchestrator
satishTheLegend/relocation-logistics-orchestrator Skill
0★Plan a cross-state or international move end to end: housing, healthcare/records transfer, licenses, taxes, schools, and a dated checklist.
royashbrook/trustmebro Skill
0★the end of 'trust me bro' , an agent skill + zero-dep node CLI that adds verified citation links to your markdown/html posts. every link resolves or gets flagged, and it never rewrites a word.
Uzu83/ai-agent-skills/skills/init-ai Skill
0★ reposharklandy/claude-code-starter-kit/skills/domains/code-review Skill
0★ repoSkills, subagents et templates /goal//loop//schedule prêts à l'emploi pour Claude Code — installables en une commande via /plugin marketplace add