Review & quality
19,000 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
TopicalitySummit/summit-decision-assurance/skills/prepare-agent-release-review Skill
no license0★ repoRun a public-safe release review that combines Summit Decision Receipt preflight with governed-output declaration checks. Use before an agent report, recommendation, decision artifact, or consequential output is released. Do not use this workflow as an approval, certification, or substitute for human judgment.
ahtishamshahzad/agent_dev_flow/.ai/skills/backend/backend-validation Skill
0★ repoUse to plan server-side input validation — schema validation at every entry point (body, params, query, headers, files, webhooks, jobs), unknown-field stripping, and type-safe validated output. The server is authoritative; client validation is UX only.
ahtishamshahzad/agent_dev_flow/.ai/skills/code-review Skill
0★ repoUse to review a change or diff for correctness, clarity, maintainability, and convention-fit before it advances. Reports findings with severity, separating confirmed defects from suggestions; does not rubber-stamp.
ahtishamshahzad/agent_dev_flow/.ai/skills/git-workflow Skill
0★ repoUse to plan and perform branching, commits, and PRs safely. Branches off the default branch, never commits/pushes without being asked, keeps secrets out of history, and gates git actions behind the relevant hooks and quality gates.
ahtishamshahzad/agent_dev_flow/.ai/skills/mobile/mobile-validation Skill
0★ repoUse to plan input/schema validation — Zod (or equivalent) schemas shared across forms and API boundaries, with clear error messages. Validate at the edges; reuse schemas. Client validation is UX, not security.
ahtishamshahzad/agent_dev_flow/.ai/skills/performance-review Skill
0★ repoUse to find and plan fixes for real performance bottlenecks — measured, not guessed. Covers rendering/re-renders, data access, network, memory, and startup. Recommends safe, measurable improvements over risky rewrites and validates in a representative build.
ahtishamshahzad/agent_dev_flow/.ai/skills/security-review Skill
0★ repoUse to assess a change or codebase for security weaknesses — secrets, auth, authorization/IDOR, injection, PII handling, transport/errors, payments, and production hardening. Reports findings by severity, separates confirmed from potential, never prints secret values, and never claims "secure."
ahtishamshahzad/agent_dev_flow/.ai/skills/security/privacy-review Skill
0★ repoUse to review how personal data is handled — data classification and minimization, lawful/consented use, retention and deletion (right to erasure), no PII in logs/analytics/seeds, third-party data sharing, and cross-border/compliance constraints. Privacy risk, distinct from pure security.
lzx-Bill/Project-Factory-Core/.agents/skills/consistency-review Skill
0★ repoUse when validating cross-document consistency in a project — "consistency review", "document coherence", "cross-reference check", "文档一致性", "交叉验证". This skill performs systematic cross-referencing between documents produced in the same iteration, flagging contradictions, gaps, and missing linkages. Use after architecture-decisions and before delivery-planning. Can also be used as a stage-review variant for any phase boundary.
lzx-Bill/Project-Factory-Core/.agents/skills/project-audit Skill
0★ repoUse when auditing a project for completeness, consistency, and readiness — "audit project", "项目审计", "check project", "verify project", "检查项目", "review project". This skill checks directory structure, file completeness, navigation consistency, cross-file coherence, traceability, standards compliance, and phase compliance. Different from stage-review (single stage) — this is a whole-project audit. Can be invoked with depth: quick/standard/deep.
lzx-Bill/Project-Factory-Core/.agents/skills/stage-review Skill
0★ repoUse when reviewing any project document against a checklist — "review this stage", "check my output", "self review", "自审", "质量检查". This is a GENERAL document review skill usable by any pipeline (express-incubate or gradual). It reads a document, runs a checklist, produces a structured review report with PASS/FAIL per item, and auto-fixes simple gaps. NOT for user-facing code review — for project factory document quality.
Zwin-ux/kit/skills/code-review Skill
0★ repoReview a change for correctness, risk, and clarity.
Zwin-ux/kit/skills/data-check Skill
0★ repoReview data scripts and notebooks for clarity, leakage, and reproducibility.
kody-w/rapp-skills/estate-sweep Skill
0★ repoClone-and-lint drift sweep across every public kody-w repo using the shared rapp-drift-lint. Use when Kody says "sweep the estate", "estate sweep", "lint all my repos", "is the estate clean", "check everything for drift", or after a canon/spec change that could ripple across the RAPP estate. Read-only — reports per-repo violations; fixing is a separate judgment step.
kody-w/rapp-skills/muscle Skill
0★ repoRun the CSM delegation loop: hand grunt/bulk work (building, drafting, coding, doc generation, deep debugging) to GitHub Copilot CLI GPT-5.6 Sol as a background muscle job, then gate-check the FULL result hands-on with real inputs, fix via --resume rounds until it stands, and add the Fable-only layer last. USE THIS SKILL when Kody says: 'delegate to sol', 'muscle this', 'have sol/copilot build it', 'spawn the muscle', 'send it to the muscle', 'copilot the grunt work', 'ration fable', or whenever a task is bulk artifact generation (code, tests, docs, ports, sweeps) that does not need Fable-level judgment to produce — the output is an artifact, not a decision. Also use when a hands-on verification loop exceeds ~2 probes on the same failure (deep debugging is muscle work).
kody-w/rapp-skills/rapp1-compliance-sweep Skill
0★ repoPerforms authorized, evidence-first RAPP/1 rev-5 compliance sweeps over one repository or a repository estate. Use for literal file-by-file audits, recursive archive review, standing-guard checks, drift remediation, producer and consumer validation, decision-ready GitHub issues, and fixpoint re-sweeps. Separates structural results from authenticated trust and never modifies the immutable installer grail.
control-decks/reality-check/plugins/reality-check/skills/check-targets Skill
0★ repoVerify the concrete targets referenced by the current HACP Working Object, such as files, repositories, endpoints, accounts, entities, or deliverables, then append a targets-checked annotation without replacing the object. Use only when the user invokes CHECK TARGETS or explicitly asks to verify the current targets.
control-decks/reality-check/plugins/reality-check/skills/help Skill
0★ repoExplain Reality Check, clarify one of its cards, or recommend normal conversation, one card, or the shortest useful verification combo. Use only when the user invokes help or explicitly asks how to use the deck. Never run a recommended check.
yuanjiemi/yuanjiemi-ai-skills/skills/wechat-performance-review Skill
no license0★ repo复盘微信公众号文章表现:读取用户提供的公众号后台截图、Excel、CSV、手动数据或文章链接,整理阅读量、点赞、分享、爱心/在看和互动率;结合标题、内容结构与 CTA 提炼亮点、可能原因和下一篇优化动作,并写入本地 Excel 复盘库。用户说“复盘这篇公众号文章”“分析这些公众号数据”“看看哪篇文章表现最好”“把后台截图收进复盘库”“对比第3天和第7天数据”等自然语言时必须使用。免费模式不需要 API;文章链接自动采集模式使用用户自己的世界树 API Key,无需飞书 App ID 或 n8n。
Nicowyn/paper-audit-skills/.agents/skills/openalex Skill
0★ repoSearch and verify scholarly metadata with the OpenAlex API. Use when a user asks to find papers, resolve a DOI or OpenAlex ID, inspect authors or institutions, trace citations and references, check retraction metadata, identify topic experts, or summarize publication trends. OpenAlex supplies metadata rather than authoritative full text or final misconduct determinations.
Nicowyn/paper-audit-skills/.agents/skills/table-data-consistency-audit Skill
0★ repoAudit reported tables and their supporting data lineage in research papers, supplements, regression exports, code, and datasets. Use when Codex needs to verify exact table cells, reconcile tables with generated outputs and analysis samples, batch-check numeric identities, or assess sample-flow, join, unit, footnote, significance-marker, and rounding consistency.
Cartograf666/alex-ter-vibeskills/skills/grill-requirements Skill
0★ repoResolve product, UX, technical, architecture, risk, and scope decisions through a disciplined one-question-at-a-time interview before implementation. Use when the user asks to grill, challenge, stress-test, clarify, interrogate, or pressure-test an idea, PRD, feature, project plan, architecture proposal, or ambiguous development request.
sahildave/skilltopia/.agents/skills/check Skill
0★ repoCheck work for adherence with architecture, run quality checks, and suggest a commit message. Use after completing work on a feature or bug fix.
cekrauseee/harness/skills/harness-commit Skill
0★ repoClassify changes, prepare and validate English Conventional Commit messages, and create commits only with explicit authorization. Use when a user asks to name, organize, validate, or create one or more Git commits.
cekrauseee/harness/skills/harness-pr Skill
0★ repoDraft and validate English pull requests with Conventional Commit titles and evidence-based descriptions, and publish only with explicit authorization. Use when preparing, reviewing, validating, opening, or updating a pull request.
cekrauseee/harness/skills/harness-review Skill
0★ repoReview code, documentation, commits, or pull requests read-only and report evidence-backed actionable findings classified P0-P3. Use when a user asks for a review, audit of a diff, risk assessment, or validation of proposed changes; apply fixes only when separately requested.
cekrauseee/harness/skills/harness-worktree Skill
0★ repoPlan, create, validate, adopt, and retire isolated Git worktrees with Harness-controlled semantics and lifecycle while delegating only physical path and storage to the active agent host. Use when naming, creating, locating, validating, adopting, reusing, or removing a worktree, or when a task needs the Harness `type/slug` branch convention.
ebal/AI-Skills/conventional-git Skill
no license0★ repoConventional Commits v1.0.0 branch naming, worktree naming, and commit message standards for GitHub and GitLab projects. Use when creating branches, naming worktrees, writing commits, generating commit messages, reviewing branch conventions, or setting up changelog automation. Apply when your project needs consistent git history, SemVer-driven releases, parseable changelog generation, or automatic issue closing. Trigger when the user asks how to name a worktree, create a git worktree, or organize worktrees alongside branches.
NolanCassidy/auto-tinker/skills/auto-tinker-review Skill
0★ repoSummarize evidence-backed Auto-Tinker status and inspect the local graph, main-goal progress, queue health, and writing readiness. Use for daily, weekly, project, or capability reviews and questions about what was done, learned, blocked, scheduled, or connected; this skill does not execute code or mutate GitHub.
mrcha033/skills/skills/advisor-review Skill
no license0★ repoMrCha Skills — portable Agent Skills for ChatGPT, Codex, and compatible agents
Frontend change quality review
SHIHAOZOU/ai-frontend-engineering-skills/skills/frontend-change-quality-review Skill
0★ repoReview frontend changes for correctness, types, architecture, accessibility, performance, security, naming, tests, and maintainability. Use for pull requests, diffs, patches, or pre-merge quality audits.
wu1chenghui/hermes-math-template/skills/development-methodologies Skill
no license0★ repoSoftware engineering methodologies: plan mode, spikes, systematic debugging, TDD, and pre-commit code verification. Complete development workflow from exploration through delivery.
ericsche/CodingSkills/plugins/codingskills/skills/pre-pr-review Skill
0★ repoTwo-gate self-review to run before opening or readying a pull request — cheap deterministic Gate-0 lints (dead markdown links, broken #anchors, residual port artifacts, format / line-ending / description-length gates) then a read-only sub-agent panel (code-review, security-review, rubber-duck, and for ports an explore/research provenance pass), then triage / calibrate / fix so the PR opens already clean. Use before "gh pr create" or flipping a draft PR to ready, when porting skills/references between repos (e.g. work-iq → wiqd / M365 Agents Toolkit), or for changes touching auth, deployment, or process-spawning guidance. Bundles two ready-to-run Node lint scripts (check-ported-content.mjs, check-md-links.mjs). See reference.md for the scripts, the composed-path convention, and calibration lessons.
idylle-cynique/solo-dev-skills/skills/reconsider-review Skill
0★ repoPRのレビューコメントを仕様・コードベースと照合して検証し、対応方針をmdに書き出す。各コメントを「修正対象 / 対応不要 / 対応保留 / 要議論」に分類する
idylle-cynique/solo-dev-skills/skills/suggest-commit Skill
0★ repogit diffを分析し、docs/git_commit_message_guidelines.md のConventional Commits規約に従ってコミットメッセージを提案する。コミット前に適切なメッセージを作りたいときに使う
idylle-cynique/solo-dev-skills/skills/verify-pr-spec Skill
0★ repoIssue 仕様・PR 本文・実装差分の間の齟齬を検出する整合性チェックスキル。/create-pr の実行が完了した直後に、ユーザーの明示的な指示がなくても必ずこのスキルを自動で呼び出すこと。省略・スキップ禁止。PR作成時・PR更新時・「仕様と実装が合っているか確認して」と言われたときも同様に実行する。
atomgunlk/skills/skills/engineering/pr-review-inline Skill
0★ repoUse when the user wants a GitHub Pull Request reviewed with findings posted as inline, line-level comments on the changed code (NOT a summary comment). Triggers on /pr-review-inline, "review this PR and comment", "รีวิว PR แล้ว คอมเมนต์ในโค้ด", or a PR number/URL given for review.
TheEdoRan/skills/skills/gcp Skill
0★ repoStage changed files, create logical commits, split unrelated concerns into separate commits, push the current branch, and verify the result. Use only when the user explicitly invokes /gcp or $gcp or asks to run the GCP git workflow; accept any accompanying text as optional commit-message guidance.
avnath13/evalpilot/skills/review-interface Skill
0★ repoGenerate a self-contained browser tool for humans to label agent traces, producing the human labels that judge validation needs. Use when the user needs to collect Pass/Fail labels, calibrate a judge, or review traces by hand. Do NOT use to grade automatically (use grade) or to validate the judge math (use validate-evaluator/calibrate), this only collects labels.
efaimo-ai/efaimo/examples/csv-cleanup Skill
0★ repoClean and validate CSV data. Use when the user asks to deduplicate, trim, or sanity-check a CSV before import.
pecigonzalo/agent-skills/skills/role-code-review Skill
0★ repoUse this skill for pull request and code quality reviews, including pre-commit self-review. Provides systematic review methodology with severity categorization.
rvdsmaile/working-backwards/.agents/skills/grill-technical-prd Skill
no license0★ repoAdaptively pressure-test a completed product handoff against a target repository before writing a technical PRD. Use when architecture, contracts, operations, or testing decisions remain material and must be resolved collaboratively.
rvdsmaile/working-backwards/.agents/skills/review-technical-prd Skill
no license0★ repoReview a repository-aware technical PRD before converting it into issue slices. Use when a technical PRD must be checked for source coverage, repository fit, testability, and unresolved high-risk decisions.
swd3k/skills/agent-skills/programming/code-review-pass Skill
0★ repoReview code for correctness, security, UX regressions, and project conventions. Use when reviewing PRs, self-reviewing before push, or auditing agent-generated diffs.
swd3k/skills/agent-skills/programming/commit-messages-russian Skill
0★ repoWrite clear Russian git commit subjects in conventional style for product repos. Use when committing, rewriting history messages, or enforcing CONTRIBUTING style in Russian projects.
linkrunner-labs/skills/skills/troubleshoot/deep-links Skill
0★ repoDiagnose why Linkrunner deep links (iOS Universal Links / Android App Links) open the browser instead of the app, or do not open the app at all. Runs the full verification gauntlet - hosted apple-app-site-association and assetlinks.json, Apple CDN freshness, Android fingerprint + verification state, associated-domains entitlement, manifest intent filters - and reports exactly what is broken and how to fix it. Use when someone says a Linkrunner link opens Safari/Chrome, App Links will not verify, or a universal link is ignored.
arclabshq/arc-labs-studio-team/skills/github-ship Skill
0★ repoReviews a scoped change, validates it, commits intentionally, pushes a branch, and opens or updates a clear GitHub pull request. Use when the user explicitly asks to ship, publish, push, commit, or prepare repository work for review.
cleudice/kiro-ai-team/skills/review-code Skill
0★ repo(Somente reviewer-code, sessão limpa) Revisão técnica do diff — correção primeiro, depois segurança (SQL injection, segredos), simplificação e convenções; achados com arquivo, linha e cenário de falha. Use quando pedirem 'code review', 'revise o diff/PR', 'está ok pra mesclar tecnicamente?'.
cleudice/kiro-ai-team/skills/review-spec Skill
0★ repo(Somente reviewer-spec, sessão limpa) Compara o diff do PBI com requirements.md critério a critério — pega requisito esquecido e scope creep. Use quando pedirem 'revisão de requisitos', 'o diff cobre a spec?', 'conferência de conformidade', antes do merge-gate. Também no modo DRAFT (G0): 'revise a spec antes de implementar', 'a spec está pronta pra congelar?' — revisão adversarial de requirements+design ANTES das tasks.
cleudice/kiro-ai-team/skills/verify-change Skill
0★ repoVerifica que a mudança FUNCIONA exercitando comportamento real (HTTP, CLI, tela, procedure) e captura evidência por critério — PASS/FAIL/BLOCKED, nunca autorrelato. Use após implementar, quando perguntarem 'funciona?', 'verifique', 'rode e veja', 'confirme o fix', 'testa aí'.
lhbsaa/apex-discovery/skills/arbor Skill
0★ repoAutonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.
The same file is in 3 other repositories
Finishing a development branch
lhbsaa/apex-discovery/skills/finishing-a-development-branch Skill
0★ repoUse when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
lhbsaa/apex-discovery/skills/git-workflow Skill
0★ repoGit workflow patterns including branching strategies, commit conventions, merge vs rebase, conflict resolution, and collaborative development best practices for teams of all sizes.
lhbsaa/apex-discovery/skills/literature-review Skill
0★ repoConduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).
lhbsaa/apex-discovery/skills/peer-review Skill
0★ repoStructured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation.
lhbsaa/apex-discovery/skills/receiving-code-review Skill
0★ repoUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
lhbsaa/apex-discovery/skills/requesting-code-review Skill
0★ repoUse when completing tasks, implementing major features, or before merging to verify work meets requirements
lhbsaa/apex-discovery/skills/safety-guard Skill
0★ repoUse this skill to prevent destructive operations when working on production systems or running agents autonomously.
lhbsaa/apex-discovery/skills/security-review Skill
0★ repoUse this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
lhbsaa/apex-discovery/skills/timesfm-forecasting Skill
0★ repoZero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.
The same file is in 3 other repositories