Review & quality
19,178 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
uwuclxdy/agenticat/skills/name-check Skill
5★ repoSuggests project/crate/plugin names and checks availability across registries (crates.io, npm, PyPI, AUR, GitHub, domains). Use before naming, renaming, or publishing anything.
VersoXBT/claude-initial-setup/skills/code-review/automated-review-setup Skill
4★ repoSet up automated code quality tools: ESLint, Prettier, pre-commit hooks, and CI linting. Activate whenever the user sets up a new project, asks about code formatting, configures linters, sets up Git hooks, or mentions Husky, lint-staged, CODEOWNERS, or pre-commit hooks. Also activate when discussing consistent code style enforcement.
The same file is in 2 other repositories
VersoXBT/claude-initial-setup/skills/code-review/pr-standards Skill
4★ repoEnforce pull request best practices: size limits, description templates, testing requirements, and review workflows. Activate whenever the user creates a PR, asks about PR best practices, sets up PR templates, discusses code review turnaround, or mentions PR size, review requirements, or branch protection rules.
The same file is in 2 other repositories
VersoXBT/claude-initial-setup/skills/code-review/review-checklist Skill
4★ repoSystematic code review checklist with severity classification. Activate whenever the user asks for a code review, wants feedback on their code, submits a PR for review, or asks what to look for when reviewing code. Also activate when writing review comments or discussing code quality standards.
VersoXBT/claude-initial-setup/skills/core-workflow/branching-strategy Skill
4★ repoGuide git branching strategies, branch naming, and merge/rebase decisions. Use when the user creates branches, asks about Git Flow vs trunk-based development, discusses merge vs rebase, or is setting up a new repository's branching model.
The same file is in 2 other repositories
VersoXBT/claude-initial-setup/skills/core-workflow/commit-conventions Skill
4★ repoEnforce conventional commits format with proper types, scopes, and breaking change notation. Use when the user is committing code, writing commit messages, asks about commit format, or when you are about to create a git commit. Always apply this skill before running git commit.
The same file is in 2 other repositories
VersoXBT/claude-initial-setup/skills/fastapi/pydantic-validation Skill
4★ repoValidate data with Pydantic v2: BaseModel, Field validators, model validators, computed fields, discriminated unions, and custom types. Use when the user defines API schemas, validates input data, works with Pydantic models, or asks about data validation in Python. Trigger when you see dict-based data handling that should use Pydantic models.
The same file is in 2 other repositories
VersoXBT/claude-initial-setup/skills/hooks/hook-recipes Skill
4★ repoReady-to-use hook recipes for common Claude Code automation: prettier on edit, tsc check, console.log warning, git push review, doc blocker. Use when the user wants a specific hook example, asks "how do I auto-format" or "block markdown creation", or needs a hook for a common development workflow.
VersoXBT/claude-initial-setup/skills/security/input-validation-guide Skill
4★ repoValidate and sanitize all user input using schema validation libraries. Activate whenever the user writes form handlers, API endpoints, request parsers, data processing functions, or any code that accepts external input. Also activate when the user asks about validation libraries like Zod, Joi, or Pydantic, or discusses input sanitization.
irfad7/claude-power-skills/skills/code-review Skill
4★ repoWhen the user wants a thorough code review of changes, a PR, a file, or a feature branch. Use when the user says "review this," "code review," "check my code," "what's wrong with this," "review my PR," "look over this," "critique this," "review before merge," or when submitting code for quality assessment. Performs multi-pass review covering correctness, security, performance, maintainability, and edge cases.
irfad7/claude-power-skills/skills/security-review Skill
4★ repoWhen the user wants a security audit, vulnerability assessment, or security hardening of their codebase. Use when the user says "security review," "security audit," "check for vulnerabilities," "is this secure," "pen test," "OWASP," "find security issues," "harden this," "check for leaks," "secrets scan," or before deploying any user-facing application. Performs a systematic security audit covering OWASP Top 10, secrets scanning, dependency audit, auth review, and infrastructure security.
irfad7/claude-power-skills/skills/session-review Skill
4★ repoWhen ending a work session and wanting to capture what was accomplished, what was learned, and what to do next. Use when the user says "session review," "what did we do," "wrap up," "summarize session," "weekly review," "retrospective," "what happened today," "debrief," or at natural session endings. Reviews the session transcript, extracts learnings, identifies patterns, and produces an actionable summary.
rfxlamia/pocketto/skills/create-pr Skill
4★ repoOpens a GitHub PR for the current branch linked to the Pocket issue (Pocket Enterprise). User-triggered recorder — commits traveling state, formats a structured PR body, discovers or creates the PR, and records it in .pocket-meta.json. Trigger on "create-pr", "open a PR", "create pull request", or when pocket-development offers it after a phase completes in enterprise mode.
rfxlamia/pocketto/skills/pocket-review Skill
4★ repoPost-phase batch reviewer. User invokes after pocket-development marks all phase tasks DONE. Main agent runs preflight and dispatches parallel reviewer subagents (one per task). Returns PHASE_REVIEWED or PHASE_BLOCKED; on an all-REVIEW_PASS phase it chains to pocket-closing after one confirmation.
rfxlamia/pocketto/skills/structured-research Skill
4★ repoStandalone skill for validating an explicit assumption with structured research. Use when a user holds a belief that is still an assumption — a technical claim, a library's behavior, a "this is probably how X works" — and wants it investigated methodically before it leaks into planning or code. Recommends a research methodology (non-binding) and returns an evidence-backed, graded verdict (Confirmed / Refuted / Inconclusive). Trigger on "structured-research", "validate this assumption", "is it true that", "research whether", "verify my assumption", "check this claim", "I assume X — is that right?". Standalone like bug-hunting / hotfix / brand-design — no pipeline required.
josephneumann/claude-corps/skills/milestone-review Skill
4★ repoIterative review-fix loop for accumulated milestone/branch changes. Runs parallel reviewers, fixes findings autonomously, repeats until clean. Use after multiple tasks merge to a milestone branch, or before merging to main. Invoke with /milestone-review --base-branch main. Supports --dry-run and --max-iterations.
josephneumann/claude-corps/skills/multi-review Skill
4★ repoThis skill should be used when the user wants a comprehensive code review using multiple specialized reviewers in parallel. Invoked with /multi-review or when user asks for 'thorough review', 'full code review', or 'review from multiple perspectives'. Use --plan <path> to review an implementation plan pre-coding.
josephneumann/claude-corps/skills/plan-design-review Skill
4★ repoScored design plan review: 7 UI/UX dimensions rated 0-10, explains what would make each a 10, then fixes the plan. Run after /spec for UI-heavy features, or standalone on any plan with UI scope.
josephneumann/claude-corps/skills/plan-eng-review Skill
4★ repoInteractive engineering plan review: architecture, code quality, tests, performance. One issue per question. Run after /spec before implementation, or standalone on any plan.
josephneumann/claude-corps/skills/product-review Skill
4★ repoProduct-taste review that challenges 'are we building the right thing?' Interrogation mode with recommended answers, assumption mapping (V/U/Vi/F), devil's advocate challenges, and alternatives analysis. Four modes: EXPAND / HOLD / REDUCE / DESIGN. Run before /spec or standalone.
josephneumann/claude-corps/skills/retro Skill
4★ repoEngineering retrospective analyzing git commit history for shipping metrics, work patterns, and trends. Persistent history with trend tracking. Use weekly to review shipping velocity, or after milestones. Invoke with /retro [7d|14d|30d|24h] or /retro compare to see trends.
The same file is in 2 other repositories
josephneumann/claude-corps/skills/verify Skill
4★ repoUse when making any completion claim, reviewing findings, or processing agent reports
The same file is in 2 other repositories
pinguding/Project-Machine-in-the-loop/skills/en/jarvis Skill
no license4★ repoA watch loop that polls git change volume in a self-paced manner and automatically runs the jarvis-once one-shot review when new change has accrued since the last review, a risk path changed, or a new commit appeared. Repetition rides on /loop's self-paced mode, so it must be launched as /loop /jarvis. There is no fixed line/file threshold. Configure strength preset, polling intervals, paths, and risk paths via args (key=value). When called without args, it asks for strength once on first run (previous settings auto-restore from .jarvis/args). Right after first load it polls quickly for a short while (warmup). Use for "jarvis", "change-detection review loop", "jarvis watch" requests.
LevNas/ccmemo/skills/review-knowledge Skill
4★ repoReview and maintain the knowledge base — find stale entries, orphan entries without connections, missing links between related entries, and generate topic summaries. Supports the "internalization" phase of knowledge management by surfacing knowledge for periodic review and reflection.
Maudeunfledged834/startup-founder-skills/skills/code-review Skill
4★ repoWhen the user asks for a code review, shares code for feedback, or says "review this", "check my code", "what's wrong with this". Also activate when reviewing a pull request or diff.
Maudeunfledged834/startup-founder-skills/skills/contract-review Skill
4★ repoWhen the user needs to review an existing contract, assess risk in proposed terms, or evaluate a contract before signing.
Maudeunfledged834/startup-founder-skills/skills/review-mining Skill
4★ repoWhen the user wants to research customer pain points, complaints, or sentiment using review platforms like Trustpilot, G2, Capterra, or app stores. Also use when the user mentions "what are users saying", "competitor reviews", "pain points", or "voice of customer research".
Maudeunfledged834/startup-founder-skills/skills/security-review Skill
4★ repoWhen the user needs a security assessment — threat modeling, vulnerability review, auth flow audit, dependency scanning, or says "is this secure", "review for vulnerabilities", "threat model", "security audit", "pen test prep".
oyusypenko/creo/skills/creo-design-review Skill
4★ repoComprehensive UI/UX design review with Playwright. Evaluates responsive design (375-1920px), WCAG AA accessibility, Nielsen's 10 heuristics, component consistency, and visual polish. Trigger keywords: design review, UI review, accessibility audit, responsive check, heuristic evaluation.
kelegele/oh-my-pm/skills/requirement-review Skill
4★ repo促进需求评审会议和干系人对齐。当用户需要与干系人评审需求、对功能达成一致、运行 PRD 评审,或说"评审这个 PRD"、"获得批准"、"需求评审会议"时使用。即使没有明确说"需求评审",当用户正在准备干系人会议或需要对需求达成一致时也应激活。
YousefNabil-SOC/claude-apex/skills/gs-guard Skill
4★ repoFull safety mode - careful (destructive-command warnings) plus freeze (directory-scoped edits). CARL TRIGGERS: guard mode, safety on, lock everything down, prod safety. SOURCE: garrytan/gstack/guard, integrated as gs-guard on 2026-05-29.
YousefNabil-SOC/claude-apex/skills/gs-plan-design Skill
4★ repoDesigner-eye plan review - rates each design dimension 0-10 and flags AI slop. CARL TRIGGERS: design plan review, rate this design plan, design critique, design quality check, plan-mode design review. SOURCE: garrytan/gstack/plan-design-review, integrated as gs-plan-design on 2026-05-29.
YousefNabil-SOC/claude-apex/skills/gs-review Skill
4★ repoPre-landing PR review - gstack staff-engineer code review army. CARL TRIGGERS: review the code, audit this branch, check this PR, find bugs, code review, review my changes. SOURCE: garrytan/gstack/review, integrated as gs-review on 2026-05-29.
ralvarezdev/ralvaskills/skills/personal/uru-thesis-reviewer Skill
4★ repoContinuous-feedback reviewer for URU (Universidad Rafael Urdaneta) theses. Emits ordered `.md` diff files (- old / + new) the author applies manually — never edits the `.docx`. Covers substance, structure, prose, citations vs `NORMAS_URU_2020`. Tracks issues across sessions via stable IDs and carry-forward. Use when the user shares a thesis or chapter.
ralvarezdev/ralvaskills/skills/quality/api-contract-reviewer Skill
4★ repoReviews REST + gRPC contracts for stability, versioning, completeness, backwards compatibility. References rest-api-architect / protobuf-architect / grpc-architect for rules; runs `buf breaking` / `openapi-diff`. Severity-keyed findings. Use when reviewing a new endpoint, proto change, or before a breaking-change release.
ralvarezdev/ralvaskills/skills/quality/performance-reviewer Skill
4★ repoCross-language perf review — N+1, missing indexes, blocking I/O in async, allocation hot paths, unbounded memory, slow algorithms. Findings grounded in EXPLAIN / pprof / py-spy / metrics. Use when reviewing for perf or investigating a slow endpoint.
ralvarezdev/ralvaskills/skills/quality/security-reviewer Skill
4★ repoCross-language security review — injection, auth/authz, secrets, insecure defaults, deserialization, CSRF/SSRF/IDOR, dep vulns. Emits a Critical/High/Medium/Low report with file:line + fixes. Use when auditing a PR or pre-release.
ralvarezdev/ralvaskills/skills/workflows/commit-author Skill
4★ repoGenerate concise Conventional Commits messages from a staged diff. Enforces full type set, imperative subject lines, no AI co-author attribution. Use when user wants to commit, asks for a commit message, mentions "commit", or invokes /commit.
ralvarezdev/ralvaskills/skills/workflows/grill-with-docs Skill
4★ repoGrilling session that challenges an existing plan or design against the project's domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when a plan or design already exists and needs stress-testing; if no plan exists yet, use feature-planner first.
soden46/syarif-laravel-ai-skills/skills/code-review-requests Skill
4★ repoRequest effective code reviews-specify focus areas, provide context, ask for architectural feedback, reference Laravel conventions
TheAIbreakfastclub/scientific_english_agents-public/skills/critical-reviewer Skill
no license4★ repoSimulates a rigorous but constructive journal peer reviewer and coaches students on critical reading and on writing structured peer reviews (PPP format). Use whenever someone asks for a review, a peer review, a critique, feedback on a paper or section, or wants to practise responding to reviewer comments.
SkillMedev/fiction-writers-room/skills/manuscript-reviser Skill
4★ repoUse when revising fiction prose that ALREADY EXISTS - a second/third-draft pass on a chapter or scene, a continuity or POV-consistency check, fixing a scene that drags, cutting dead weight, or tightening overwritten prose at the line level. Do NOT use to draft a brand-new scene from nothing (use Fiction Scene Writer), to build or mimic an author's voice (use Ghostwriter), or for neutral encyclopedic prose (use Wikipedia Style Writer); to outline or re-architect the plot at the beat level, use Story Structure Architect.
The same file is in 1 other repository
nahiddotai/operator-powers/plugins/operator-powers/skills/weekly-review Skill
4★ repoRun a focused weekly review when the user wants to assess what moved, what drifted, what to stop, what the week taught them, and the next week's one priority.
dongzhigang13305312738-art/paper-skills/grammar-checker-guide Skill
no license4★ repoUse grammar and style checking tools to polish academic manuscripts
The same file is in 1 other repository
dongzhigang13305312738-art/paper-skills/literature-review-writing Skill
no license4★ repoStructure and write comprehensive literature reviews for any field
The same file is in 1 other repository
dongzhigang13305312738-art/paper-skills/literature-review Skill
no license4★ repoConduct comprehensive literature reviews using multi-perspective dialogue simulation. Generate diverse expert personas, conduct grounded Q&A conversations, and synthesize findings into structured knowledge. Use when starting a new research project or writing a survey section.
The same file is in 1 other repository
dongzhigang13305312738-art/paper-skills/paper-audit Skill
no license4★ repoReviewer-style audit and submission gate for academic papers in .tex, .typ, or .pdf. Use for peer-review critique, readiness/gate decisions, blocker triage, revision roadmaps, journal-style reports, and re-audits. Do not use for source editing, sentence polishing, bibliography search, or compile repair.
dongzhigang13305312738-art/paper-skills/paper-revision Skill
no license4★ repoRevise papers based on reviewer feedback. Map reviewer concerns to specific sections, apply targeted edits, run additional experiments if needed, and verify improvements. Use after receiving peer review with revision requests.
The same file is in 1 other repository
dongzhigang13305312738-art/paper-skills/rebuttal-writing Skill
no license4★ repoWrite point-by-point rebuttals to reviewer comments. Extract concerns from reviews, generate evidence-based responses, and format as a structured rebuttal document. Use after receiving peer review feedback.
The same file is in 1 other repository
dongzhigang13305312738-art/paper-skills/research-citation-check Skill
no license4★ repo当用户明确要求"核查/优化综述 `{主题}_review.tex` 的正文引用"、"运行 research-citation-check",或要求使用旧名 check-review-alignment skill 时使用。通过宿主 AI 的语义理解逐条核查引用是否与文献内容吻合,只在发现致命性引用错误时对"包含引用的句子"做最小化改写,并优先复用 `research-literature-review` 的渲染脚本输出 PDF/Word,过渡期允许 fallback 到旧名 systematic-literature-review。核心原则:不为了改而改,无法确定是否为致命性错误时保留原样并在报告中警告。⚠️ 不适用:用户只是想生成系统综述正文(应使用 research-literature-review);用户只是想新增/核对 BibTeX 条目(应使用专门的 bib 管理流程)。
dongzhigang13305312738-art/paper-skills/research-literature-review Skill
no license4★ repo当用户明确要求"做系统综述/文献综述/related work/相关工作/文献调研",或要求使用旧名 systematic-literature-review skill 时使用。AI 自定检索词,多源检索→去重→AI 逐篇阅读并评分(1–10分语义相关性与子主题分组)→按高分优先比例选文→自动生成"综/述"字数预算→资深领域专家自由写作(固定摘要/引言/子主题/讨论/展望/结论),保留正文字数与参考文献数硬校验,强制导出 PDF 与 Word。支持多语言翻译与智能编译(en/zh/ja/de/fr/es)。
dongzhigang13305312738-art/paper-skills/self-review Skill
no license4★ repoAutomatically review an academic paper using the NeurIPS review form with three reviewer personas, ensemble scoring, and reflection refinement. Extracts text from PDF, runs structured review, and outputs actionable feedback. Use when the user wants to review a paper before submission or get feedback on a draft.
The same file is in 1 other repository
CyrilLeMat/temper-skills/examples/dog_food/output/dog-food Skill
4★ repoFrozen, deterministic decision (no LLM): maps food_item, food_form, dog_weight_kg, dog_breed, quantity_grams to one of no — toxic to dogs, never feed, no — concentrated form multiplies toxin and fat dose per gram, no — low-fat/sugar-free peanut butter may contain xylitol; check the label, caution — large dose relative to body weight, unknown — a valid dog weight is required to assess this quantity, yes — standard peanut butter is safe in moderation, if xylitol-free, yes — safe in moderation, yes — apple flesh only; never the core or seeds, no — when in doubt, do not feed; verify with a vet. Use when this decision must be made consistently and auditably — extract the features, call can_dog_eat(), and relay its verdict without overriding it.
Ldxs001/workbuddy-skills/skills/git-sync Skill
4★ repo全平台统一发布工具。支持 skills 和 agents 的 Gitee/GitHub/ClawHub/SkillHub/PyPI 同步与 Release 创建,LLM 驱动的文件过滤与脱敏。
escoffier-labs/skillet/skillet/skills/check Skill
4★ repoA skillet full of agent skills that actually ship work. Production-tested SKILL.md workflows for audits, security, releases, and handoffs.
escoffier-labs/skillet/skillet/skills/grill Skill
4★ repoA skillet full of agent skills that actually ship work. Production-tested SKILL.md workflows for audits, security, releases, and handoffs.
escoffier-labs/skillet/skillet/skills/line-check Skill
4★ repoA skillet full of agent skills that actually ship work. Production-tested SKILL.md workflows for audits, security, releases, and handoffs.
escoffier-labs/skillet/skillet/skills/plate Skill
4★ repoA skillet full of agent skills that actually ship work. Production-tested SKILL.md workflows for audits, security, releases, and handoffs.
escoffier-labs/skillet/skillet/skills/reel-check Skill
4★ repoA skillet full of agent skills that actually ship work. Production-tested SKILL.md workflows for audits, security, releases, and handoffs.
escoffier-labs/skillet/skillet/skills/review Skill
4★ repoA skillet full of agent skills that actually ship work. Production-tested SKILL.md workflows for audits, security, releases, and handoffs.