Review & quality
19,040 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
wjlgatech/design-anything/skills/construction-ready-check Skill
no license1★ repoRun the construction ready gate on a structured layout (rooms + openings JSON): clearance tables, habitability, daylight, egress connectivity, module grid. Trigger: "is this floor plan code-sane", "check my layout", "validate this plan". NOT a permit, NOT a PE stamp — jurisdiction codes override.
wjlgatech/design-anything/skills/garment-ready-check Skill
no license1★ repoRun the pattern gate on a garment marker (pieces placed on fabric): valid pieces + grain, fabric fit, seam allowance, marker efficiency (zero-waste as a number), human-fit tables. Trigger: "is this pattern cuttable", "check my marker", "validate this sewing pattern". NOT a drape simulator and NOT a grading service (yet).
wjlgatech/design-anything/skills/print-ready-check Skill
no license1★ repoRun the machine-checkable ready gate on an STL and report READY/NOT-READY with per-gate evidence (watertight, normals, bed-fit, min-feature). Trigger: "is this printable", "check my STL", "why does my print fail". NOT a slicer and NOT a substitute for material/temperature tuning.
wjlgatech/design-anything/skills/scene-ready-check Skill
no license1★ repoRun the scene gate on a glTF 2.0 file: structure validity (buffers/accessors consistent), triangle budget vs declared target platform, true scale in meters, collision geometry present. Trigger: "is this scene game-ready", "check my glTF", "validate this level". NOT a performance profiler and NOT an art review — materials, draw calls, and taste live in the engine.
YosukeIida/personal-agent-skills/codex-pr-review Skill
no license1★ repoGitHub PR(単一または複数)を codex exec で系統的にレビューし、批判的トリアージを経て 修正まで回すためのオーケストレーション規約。「PR を codex でレビューして」「この PR 一覧を codex-pr-review でやって」「#69 をレビューして修正まで」などで発動。 司令塔(メインセッション: Fable/Opus)が PR ワーカー subagent(opus/sonnet)を起動し、 ワーカーが codex exec を呼ぶ3層構成が標準。レビュー指摘は鵜呑みにせず本 skill の トリアージ基準で判断する。※対話中の自ブランチの軽いレビューは plugin の /codex:review、 working diff の品質レビューは /code-review が担当。本 skill は PR 単位の レビュー〜修正ループ専用。
YosukeIida/personal-agent-skills/commit Skill
no license1★ repo変更を conventional commits 規約でコミットする skill。「commitして」「コミットして」 「commit, pushして」「pushも」「それで commitして」などの指示、または /commit で発動。 差分を意味単位に分割し、リポジトリ既存のコミットスタイル(type/scope の使い方)を 踏襲したメッセージを生成する。指示に「push」が含まれれば push まで行う。
YosukeIida/personal-agent-skills/overleaf-review-fetch Skill
no license1★ repoOverleafプロジェクトのレビューパネル(インラインコメント)を Chrome Canary 専用プロファイル + browser-use で 開き、指導教員などのコメントを全件取得して、リポジトリの慣習に合わせた notes ディレクトリに日付付き Markdown として保存する。特定のリポジトリ構成に依存しない汎用skill。 「先生のコメント取って」「overleafのレビュー確認して」「supervisor commentをまとめて」 「査読コメントを取得して」などで起動。 ※対応方針の検討・修正の実装は範囲外(取得〜md化まで)。修正計画のドラフトは既存の academic-paper 系 skill や通常の対話で行う。
yyqqCoding/engineering-flow-skills/skills/review Skill
1★ repoReview a diff, branch, pull request, or work-in-progress change without applying fixes.
Paldom/noslop/skills/deslop-verify Skill
1★ repoVerifies a before/after pair of texts with a deterministic script - asserts code, quotes, numbers, links, and identifiers survived an edit; flags negation flips and over-correction. Use when the user asks to verify or compare an edited draft against the original, or whether a rewrite changed facts. Requires both versions. Not for scoring a single text or producing rewrites.
Paldom/noslop/skills/slop-lint Skill
1★ repoScores copy 0-100 for clusters of AI-writing tells with a deterministic script - genre-aware soft thresholds, span-anchored findings, CI gating via exit codes. Use when the user asks to scan, score, lint, check, or gate text for AI slop or AI-sounding patterns. Detect-only - not for rewriting text, verifying an edit, authorship accusations, or code linting.
zgzdhr/zhishuo-workflows/skills/zhishuo-close-project Skill
1★ repoUse when a software, data, research, or content project reaches a stage boundary and the user asks to 收口, hand off, pause, archive, or verify it can be resumed. Audit the real project root, entrypoints, outputs, validation, Git state, failure recovery, and uncommitted files. Do not use for ordinary implementation, PDF ingestion, video transcription, or document revision.
lihongqing2001-gif/chinese-thesis-production-skills/skills/thesis-literature-review Skill
1★ repoPlan, search, verify, synthesize, and deepen a Chinese STEM thesis literature review using authoritative reviews, primary studies, standards, statistics, and traceable figure candidates. Use for field mapping, subsection research, review structure, contradiction analysis, source-packet drafting, or controlled handoffs to ChatGPT and other web research interfaces.
lihongqing2001-gif/chinese-thesis-production-skills/skills/thesis-review-revision Skill
1★ repoProcess supervisor, defense, blind-review, or journal-style comments against a Chinese thesis with traceable minimal changes. Use when comments must be mapped one by one, the latest manuscript must not be directly edited, only specified passages may change, revisions must be shown in red or as paste-ready text, or unresolved evidence and formatting issues require a separate report.
ImYourBoyRoy/agent-continuity-stack/skills/verify-software-change Skill
1★ repoDesign and run risk-based verification after software or infrastructure changes, or when asked whether work is fixed or ready. Respect repository-specific remote, hardware, staging, and production constraints.
Aiweline/WelineFramework/.codex/skills/fenxiang-update Skill
1★ repoLoad ONLY when the user says passphrase 分项. Commit and push the current core repo (Windows default E:\WelineFramework\DEV-workspace; macOS default script repo such as /Users/weline/Project/Official/框架), then run php bin/w core:update -b <branch> in the configured child projects under E:\WelineFramework\Framework-Official on Windows, or discovered child projects under /Users/weline/Project/Official on macOS; each child project commits and pushes only framework changes produced by core:update, then reloads WLS if it is running. If the user says only 分项, use dev; if the user says 分项 <branch>, use that branch. Canonical skill: dev/ai/skills/CI发布工程师-分项更新/SKILL.md
authenticfake/clike/extensions/vscode/templates/harper-init/.clike/skills/gate-risk-reviewer Skill
1★ repoEnforce evidence-based promotion decisions and prevent risky or ambiguous KIT outputs from being promoted.
authenticfake/clike/extensions/vscode/templates/harper-init/.clike/skills/vendor/bmad/qa-risk-review Skill
1★ repoClike is an AI-native developer experience layer AI Native Pipeline principles and from some visionar on internet
JarrydAdaens/agentic_rails_tooling/archived/skills/mermaid-validation Skill
1★ repoUse this skill when validating a Mermaid graph fragment before accepting mapper output or merging partials. It checks structure, scope, and reference plausibility, then returns pass or fail with concrete reasons.
HikaruEgashira/agent-skills/wf/skills/commit-push-pr-flow Skill
1★ repoタスク完了後に自律的に実行する必要があるフロースキルです。 Trigger: task completed, ready to submit code
The same file is in 3 other repositories
HikaruEgashira/agent-skills/wf/skills/process-commit Skill
1★ repoPRを作成する前の分割commitが必要な時に自律的に呼び出す必要があるスキルです。 Trigger: need split commit, prepare commit, organize commit
The same file is in 3 other repositories
HikaruEgashira/agent-skills/wf/skills/review-flow Skill
1★ repoPR作成後に自律的に実行する必要があるフロースキルです。 Trigger: review, pr created, pr open
The same file is in 3 other repositories
puku0x/agent-skills-test/.claude/skills/git-branch Skill
1★ repoCreate Git branches with automatic type detection and project-specific naming conventions. Use when asked to "create a branch", "make a new branch", "create branch for changes", or when ready to organize code changes into a new branch. Supports feat, fix, docs, refactor, test, build, ci, chore, revert, and perf branch types with automatic type selection based on changed file patterns.
puku0x/agent-skills-test/.claude/skills/git-commit Skill
1★ repoCreate Git commit messages following Conventional Commits format with automatic type and scope detection. Use when asked to "commit changes", "create a commit", "write commit message", or when ready to commit staged code. Supports feat, fix, docs, refactor, test, build, ci, chore, and revert types with project-specific scope determination based on file paths and directory structure.
puku0x/agent-skills-test/.github/skills/gh-default-branch Skill
1★ repoRetrieve the default branch name of the current Git repository using GitHub CLI. Use when asked "What is the default branch?", "Get the default branch", "What is the main branch?", "Show me the base branch", "get repo default branch", or when git operations require the default branch name (creating PRs, comparing branches, checking out base branch). Returns branch names like main, master, or develop using GitHub CLI.
puku0x/agent-skills-test/.github/skills/git-branch Skill
1★ repoCreate Git branches with automatic type detection and project-specific naming conventions. Use when asked to "create a branch", "make a new branch", "create branch for changes", or when ready to organize code changes into a new branch. Supports feat, fix, docs, refactor, test, build, ci, chore, revert, and perf branch types with automatic type selection based on changed file patterns.
puku0x/agent-skills-test/.github/skills/git-commit Skill
1★ repoCreate Git commit messages following Conventional Commits format with automatic type and scope detection. Use when asked to "commit changes", "create a commit", "write commit message", or when ready to commit staged code. Supports feat, fix, docs, refactor, test, build, ci, chore, and revert types with project-specific scope determination based on file paths and directory structure.
jovd83/playwright-skill/coverage_plan/review Skill
1★ repoCoverage-plan review skill for Playwright work. Use when Codex needs to present a proposed coverage plan, surface assumptions and tradeoffs, collect user feedback, and secure explicit approval before large implementation or documentation work.
rexedge/paystack/skills/paystack-transfers Skill
no license1★ repoPaystack Transfers API — send money to bank accounts and mobile wallets. Initiate single and bulk transfers, finalize OTP-verified transfers, list, fetch, and verify transfer status. Use this skill whenever implementing payouts, disbursements, vendor payments, withdrawal flows, or any feature that sends money from your Paystack balance to recipients. Also use when you see references to transfer_code, TRF_ prefixed codes, the /transfer endpoint, or need to handle transfer OTP verification.
rexedge/paystack/skills/paystack-verification Skill
no license1★ repoPaystack Verification API — KYC verification tools for resolving bank accounts, validating account ownership, and looking up card BIN information. Use this skill whenever verifying bank account details before transfers, confirming account holder names, validating customer identity for compliance, looking up card brand/type/bank from BIN, or implementing KYC flows. Also use when you see references to /bank/resolve, /bank/validate, /decision/bin endpoints, or need to match account numbers to names.
yasserstudio/gpc-skills/gpc-monetization Skill
1★ repoUse when managing in-app purchases, subscriptions, pricing, or Real-Time Developer Notifications in Google Play. Make sure to use this skill whenever the user mentions gpc subscriptions, gpc iap, gpc purchases, gpc pricing, gpc rtdn, in-app products, base plans, subscription offers, one-time products, consumable products, purchase verification, purchase acknowledgement, purchase token, subscription cancellation, subscription deferral, voided purchases, refunds, regional pricing, currency conversion, price migration, SKU management, monetization, revenue, billing, subscription analytics, churn, trial conversion, subscriber count, RTDN, Real-Time Developer Notifications, Pub/Sub notifications, subscription events, purchase events — even if they don't explicitly say 'monetization.' Also trigger when someone wants to create or update subscriptions, manage base plan lifecycle (activate/deactivate), set up introductory offers, verify server-side purchases, handle refunds, convert prices across regions, sync IAP products from files, migrate subscribers to new prices, view subscription analytics, decode Pub/Sub notification payloads, or check RTDN topic configuration. For release management, see gpc-release-flow. For CI automation, see gpc-ci-integration.
yasserstudio/gpc-skills/gpc-preflight Skill
1★ repoUse when scanning an AAB or APK for Google Play policy compliance before submission, or checking signing key consistency across releases. Trigger when the user mentions preflight, compliance check, policy scan, pre-submission check, signing key consistency, certificate mismatch, or wants to verify their AAB/APK meets Google Play requirements. Also trigger for questions about restricted permissions, target SDK requirements, 64-bit compliance, hardcoded secrets detection, or Data Safety form reminders.
thada2402/AutoResearchClaw/researchclaw/skills/builtin/experiment/systematic-review Skill
1★ repoStructured methodology for comprehensive literature review following PRISMA guidelines. Use during literature search and screening stages.
Dispatching code review subagents
fightZy/simple-skills/.agents/skills/dispatching-code-review-subagents Skill
1★ repoUse when preparing to delegate code review to subagents — after implementation milestones, before merging complex changes, or when the diff spans multiple domains.
MatrixFounder/Universal-skills/skills/skill-validator Skill
1★ repoUse when auditing a new or existing skill for security vulnerabilities, malware (bash scripts), and structural compliance.
Agentprivacy lattice coherence
mitchuski/agentprivacy-skills/agentprivacy-skills-v5/meta/agentprivacy-lattice-coherence Skill
1★ repoThe canonical encoding of the 6-dimension sovereignty lattice and the discipline for keeping every repo in the suite agreeing on it. Activates when assigning or auditing a vertex, when a persona's vertex number and dimension-meaning seem to disagree, when reconciling the grimoire / spellweb / tomes / docs before a pin, when a new mage is seated, or when a vertex reading (binary, dimensions, stratum, complement) needs verification. Carries the standing rule: meaning is the invariant; the vertex is DERIVED from meaning under the canonical encoding. Ships a runnable coherence linter (`scripts/lattice_coherence_audit.py`).
Agentprivacy wiki offline check
mitchuski/agentprivacy-skills/agentprivacy-skills-v5/wikis/agentprivacy-wiki-offline-check Skill
1★ repoReviewing a fedwiki plugin, FastAPI endpoint, script, or skill for Offline Edit Mode correctness — what breaks or misleads when wiki-local diverts the public domains to the local mirror. Part of the git-less onboarding/distribution layer kept by the Librarian 🗃️ in the Tower's Wikis.
WE3io/lightweight-ai-development-agent-skills/skills/safety-lens Skill
no license1★ repoDetect risk or uncertainty and pause execution. Use before or after plans, commands, diffs, or implementation to surface unclear requirements or risky actions. Trigger phrases: "check for risks", "is this safe", "review for safety", "check safety", "risk check", "safety review", "is this risky", "check risks", "review risks", "safety check", "verify safety", "check if safe", "assess risk", "risk assessment", "safety assessment".
bingooyong/agent-skills/skills/api-design-reviewer Skill
no license1★ repoReview API designs for consistency, backward compatibility, security, and extensibility. Use when (1) designing new API endpoints or interfaces, (2) reviewing existing API changes for breaking changes, (3) establishing API design standards, (4) auditing API surface for security and evolution readiness. Outputs structured review findings with severity and recommendations.
bingooyong/agent-skills/skills/code-review-checklist Skill
no license1★ repoGenerate structured code review checklists tailored by language, framework, and change type. Use when (1) preparing for a code review and needing a systematic checklist, (2) reviewing PRs for specific concern areas like security, performance, or maintainability, (3) establishing team-level review standards. Outputs categorized checklist items with severity and rationale.
bingooyong/agent-skills/skills/commit-message-craftsman Skill
no license1★ repoGenerate well-structured commit messages from staged changes. Use when (1) crafting commit messages that follow Conventional Commits or team-specific formats, (2) summarizing complex multi-file changes, (3) ensuring commit history is searchable, (4) splitting large changes into logical commits. Outputs commit messages with type, scope, and body based on actual diffs.
choutos/agent-skills-spec/examples/infrastructure-check Skill
1★ repoRun periodic infrastructure health checks across servers. Use for scheduled monitoring, daily health reports, or when asked to verify system status. Triggers on: health check, infra check, server status, monitoring, systems check.
choutos/agent-skills-spec/examples/pr-review Skill
1★ repoReview pull requests for code quality, correctness, and maintainability. Use when asked to review a PR, check a diff, or provide code feedback. Triggers on: review, PR, pull request, code review, diff, merge request.
yu-iskw/coding-agent-fabric/.claude/skills/lint-and-fix Skill
1★ repoRun linters and fix violations, formatting errors, or style mismatches using Trunk. Use when code quality checks fail, before submitting PRs, or to repair "broken" linting states.
yunseo-kim/agent-toolbox/.agents/skills/git-master Skill
no license1★ repoMUST USE for ANY git operations. Atomic commits, rebase/squash, cherry-pick, worktree, reflog recovery, and history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with task(category='quick', load_skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'cherry-pick', 'worktree', 'reflog', 'who wrote', 'when was X added', 'find the commit that'.
yunseo-kim/agent-toolbox/catalog/skills/code-reviewer Skill
no license1★ repoThorough code review with focus on security vulnerabilities, performance issues, and best practices using prioritized rule-based analysis
yunseo-kim/agent-toolbox/catalog/skills/create-pr Skill
no license1★ repoCreate GitHub pull requests with Conventional Commits-formatted titles and structured PR bodies. Use when creating PRs, submitting changes for review, or when the user says /pr or asks to create a pull request.
yunseo-kim/agent-toolbox/catalog/skills/fact-checker Skill
no license1★ repoSystematic fact verification and misinformation identification using evidence-based analysis with confidence ratings and source evaluation
yunseo-kim/agent-toolbox/catalog/skills/frontend-code-review Skill
no license1★ repoReview frontend code (React, TypeScript, CSS) for code quality, performance, and best practices. Supports pending-change reviews and focused file reviews with urgency-based findings and structured output templates.
yunseo-kim/agent-toolbox/catalog/skills/js-docs-fact-check Skill
no license1★ repoVerify technical accuracy of JavaScript documentation by checking code examples, MDN/ECMAScript compliance, and common misconceptions. Use before publishing, after major edits, or during periodic accuracy audits.
yunseo-kim/agent-toolbox/catalog/skills/seo-review Skill
no license1★ repoPerform a focused SEO audit on documentation and content pages to maximize search visibility, featured snippet optimization, and ranking potential. Use when publishing new pages, optimizing underperforming content, or running periodic content audits.
CleanSlice/skills/conventional-commits Skill
no license1★ repoWrite git commit messages following Conventional Commits v1.0.0. Use when committing changes, choosing commit types, or indicating breaking changes.
medy-gribkov/arcana/skills/code-reviewer Skill
1★ repoCode review workflow for local changes and remote PRs. Reviews focus on correctness, maintainability, security, and test coverage with concrete examples and inline comments.
medy-gribkov/arcana/skills/frontend-code-review Skill
1★ repoReview React/TypeScript frontend code against code quality, performance, and business logic rules. Provides structured findings with file paths, line numbers, and suggested fixes.
medy-gribkov/arcana/skills/git-workflow Skill
1★ repoGit workflow automation with conventional commits, merge vs rebase decision trees, worktrees, SSH signing, and monorepo sparse checkout patterns.
medy-gribkov/arcana/skills/go-linter-configuration Skill
1★ repoConfigure and troubleshoot golangci-lint for Go projects. Includes complete .golangci.yml examples, import resolution fixes, CI optimization, and linter selection workflows.
medy-gribkov/arcana/skills/security-review Skill
1★ repoCode security review covering OWASP Top 10, injection prevention (SQL, XSS, command injection), authentication and authorization patterns, secrets management, dependency vulnerability scanning, input validation, CORS, CSRF, rate limiting, and security headers. Language-agnostic with examples in JavaScript, Python, and Go. Use when reviewing code for security or hardening an application.
sadiksaifi/skills/snap-pr Skill
no license1★ repoCreate or update a GitHub pull request from the current branch's committed work. Use when the user wants to open a PR, refresh the current branch PR, push committed work, or prepare a reviewer-ready PR title and body.
sadiksaifi/skills/snap-resolve Skill
no license1★ repoResolve GitHub PR feedback and failing checks. Use when the user wants review comments addressed, CI failures fixed, reviewer replies posted, or addressed review threads resolved.
sadiksaifi/skills/snap-review Skill
no license1★ repoReview a GitHub pull request in read-only mode for material bugs, regressions, missing tests, architecture drift, security/privacy risk, performance risk, and merge blockers. Use when the user wants a PR reviewed before merge or before posting feedback.
iplaylf2/coding-profile/profile/agent/skills/constraint-review Skill
no license1★ repoUse when the user needs to evaluate, decide, or change how a supporting constraint or defensive measure in code or prose serves an artifact's primary responsibility, including its validity, scope, disposition, or owning boundary. Do not use when the relevant constraint decisions—including validity, scope, behavior, disposition, required outcome or reader effect, and owning boundary—are settled and the request only implements or edits the constraint, or when the request only makes a structural placement decision after responsibilities are settled.