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
timdevai/proteus/skills/community/from-alireza/c-level-advisor/c-level-agents/skills/cdo-review Skill
1★ repo/cs:cdo-review <plan> — Decision-driven Chief Data Officer interrogation of any plan that touches training data, data architecture, data productization, or data team hiring.
timdevai/proteus/skills/community/from-alireza/c-level-advisor/c-level-agents/skills/cfo-review Skill
1★ repo/cs:cfo-review <plan> — Numerate-skeptic interrogation of any plan that touches money. Unit economics, runway, dilution, capital allocation.
timdevai/proteus/skills/community/from-alireza/c-level-advisor/c-level-agents/skills/ciso-review Skill
1★ repo/cs:ciso-review <plan> — Risk-paranoid interrogation of any plan that touches data, compliance, or production access.
timdevai/proteus/skills/community/from-alireza/c-level-advisor/c-level-agents/skills/cmo-review Skill
1★ repo/cs:cmo-review <plan> — Narrative-first interrogation of positioning, ICP, message house, and channel mix.
timdevai/proteus/skills/community/from-alireza/c-level-advisor/c-level-agents/skills/cpo-review Skill
1★ repo/cs:cpo-review <plan> — JTBD-driven interrogation of product roadmap, PMF signal, and portfolio focus.
timdevai/proteus/skills/community/from-alireza/c-level-advisor/c-level-agents/skills/cro-review Skill
1★ repo/cs:cro-review <plan> — Pipeline-paranoid interrogation of revenue, win rate, NRR, and ramp time.
timdevai/proteus/skills/community/from-alireza/c-level-advisor/c-level-agents/skills/cto-review Skill
1★ repo/cs:cto-review <plan> — Architecture and scaling interrogation. Tech debt, scaling cliffs, team scaling, build-vs-buy.
timdevai/proteus/skills/community/from-alireza/c-level-advisor/c-level-agents/skills/gc-review Skill
1★ repo/cs:gc-review <plan> — General Counsel interrogation of contracts, IP, regulatory, term sheets, and employment-law surface.
timdevai/proteus/skills/community/from-alireza/c-level-advisor/c-level-agents/skills/vpe-review Skill
1★ repo/cs:vpe-review <plan> — Throughput-first VP of Engineering interrogation of any plan that touches delivery, eng hiring, team structure, or production discipline.
timdevai/proteus/skills/community/from-alireza/engineering-team/playwright-pro/skills/review Skill
1★ repoReview Playwright tests for quality. Use when user says "review tests", "check test quality", "audit tests", "improve tests", "test code review", or "playwright best practices check".
The same file is in 4 other repositories
timdevai/proteus/skills/community/from-alireza/engineering-team/self-improving-agent/skills/review Skill
1★ repoAnalyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics.
The same file is in 1 other repository
timdevai/proteus/skills/community/from-alireza/engineering-team/skills/adversarial-reviewer Skill
1★ repoAdversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
The same file is in 1 other repository
timdevai/proteus/skills/community/from-alireza/engineering-team/skills/code-reviewer Skill
1★ repoCode review automation for TypeScript, JavaScript, Python, Go, Swift, Kotlin. Analyzes PRs for complexity and risk, checks code quality for SOLID violations and code smells, generates review reports. Use when reviewing pull requests, analyzing code quality, identifying issues, generating review checklists.
The same file is in 1 other repository
timdevai/proteus/skills/community/from-alireza/engineering/agenthub/skills/agenthub Skill
1★ repoMulti-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.
The same file is in 4 other repositories
timdevai/proteus/skills/community/from-alireza/engineering/autoresearch-agent/skills/autoresearch-agent Skill
1★ repoAutonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.
The same file is in 4 other repositories
timdevai/proteus/skills/community/from-alireza/engineering/grill-me/skills/grill-me Skill
1★ repoInterview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
The same file is in 3 other repositories
timdevai/proteus/skills/community/from-alireza/engineering/grill-with-docs/skills/grill-with-docs Skill
1★ repoDocs-anchored grilling session — challenges a plan against the project's existing language (CONTEXT.md) and recorded decisions (docs/adr/), and updates those files inline as terminology and decisions crystallise. Use when user wants to stress-test a plan against documented domain language, or mentions "grill with docs".
The same file is in 3 other repositories
timdevai/proteus/skills/community/from-alireza/engineering/karpathy-coder/skills/karpathy-coder Skill
1★ repoUse when writing, reviewing, or committing code to enforce Karpathy's 4 coding principles — surface assumptions before coding, keep it simple, make surgical changes, define verifiable goals. Triggers on "review my diff", "check complexity", "am I overcomplicating this", "karpathy check", "before I commit", or any code quality concern where the LLM might be overcoding.
The same file is in 1 other repository
timdevai/proteus/skills/community/from-alireza/engineering/kubernetes-operator/skills/kubernetes-operator Skill
1★ repoUse when building a Kubernetes Operator — custom controllers that reconcile CRD state. Triggers on "build an operator", "CRD design", "reconcile loop", "controller-runtime", "kubebuilder", "operator-sdk", "metacontroller", "KOPF", "operator capability levels", or "custom resource". Ships CRD validator, reconcile-loop linter, and OperatorHub capability auditor (all stdlib Python), 4 references on the operator pattern + CRD design + reconcile patterns + tooling landscape, and a /operator-audit slash command. NOT a generic k8s skill — specifically the Operator pattern.
timdevai/proteus/skills/community/from-alireza/engineering/skills/api-design-reviewer Skill
1★ repoComprehensive REST API design review with automated linting, breaking-change detection, and design scorecards. Catches inconsistent conventions, missing versioning, and design smells before APIs ship. Use when reviewing a PR that adds or changes API endpoints, auditing an existing API for v2 migration, or establishing API standards for a team.
The same file is in 1 other repository
timdevai/proteus/skills/community/from-alireza/engineering/skills/changelog-generator Skill
1★ repoProduce consistent, auditable release notes from Conventional Commits. Separates commit parsing, semantic-bump logic, and changelog rendering for automated releases with editorial control. Use when cutting a release, generating CHANGELOG.md from git history, or automating release notes in CI.
timdevai/proteus/skills/community/from-alireza/engineering/skills/git-worktree-manager Skill
1★ repoRun parallel feature work safely with Git worktrees. Standardizes branch isolation, port allocation, environment sync, and cleanup so each worktree behaves like an independent local app. Optimized for multi-agent workflows where each agent or terminal session owns one worktree. Use when running multiple feature branches simultaneously, isolating experimental work, or coordinating multi-agent development across the same repo.
The same file is in 3 other repositories
timdevai/proteus/skills/community/from-alireza/engineering/skills/kubernetes-operator Skill
1★ repoUse when building a Kubernetes Operator — custom controllers that reconcile CRD state. Triggers on "build an operator", "CRD design", "reconcile loop", "controller-runtime", "kubebuilder", "operator-sdk", "metacontroller", "KOPF", "operator capability levels", or "custom resource". Ships CRD validator, reconcile-loop linter, and OperatorHub capability auditor (all stdlib Python), 4 references on the operator pattern + CRD design + reconcile patterns + tooling landscape, and a /operator-audit slash command. NOT a generic k8s skill — specifically the Operator pattern.
timdevai/proteus/skills/community/from-alireza/engineering/skills/pr-review-expert Skill
1★ repoUse when the user asks to review pull requests, analyze code changes, check for security issues in PRs, or assess code quality of diffs.
The same file is in 1 other repository
timdevai/proteus/skills/community/from-alireza/engineering/skills/skill-tester Skill
1★ repoValidate, test, and score the quality of skills within the claude-skills ecosystem. Comprehensive meta-skill: structure validation, Python script testing (syntax + imports + runtime + output format), multi-dimensional quality scoring with letter grades and tier classification (BASIC/STANDARD/POWERFUL). Use when authoring a new skill, auditing existing skills for tier promotion, setting up pre-commit hooks for skill quality, or integrating skill QA into CI.
timdevai/proteus/skills/community/from-alireza/productivity/reflect/skills/reflect Skill
1★ repoMid-conversation reflection skill that pauses execution and zooms out from detail-mode to honestly reassess direction, assumptions, and bias. Use when the user says 'reflect', 'take a step back', 'step back', 'zoom out', 'are we missing something', 'bigger picture', 'sanity check this', 'are we on track', 'are we overthinking this', 'forest for the trees', or any variation signaling intent to break out of detail-mode and reassess. Also trigger when the conversation has gone deep on implementation details without strategic check-in, or when the user shows signs of being stuck — that's often a signal the framing needs a reset, not more detail work. Intentionally low-intake: runs the 5-dimension analysis immediately when prior context is rich enough; asks one forcing clarifier only when invocation context is too thin to reassess from.
The same file is in 3 other repositories
timdevai/proteus/skills/community/from-alireza/research/dossier/skills/dossier Skill
1★ repoDecision-grade entity research skill — produces a hypothesis-tested dossier on a specific company, person, nonprofit, or government org, not a generic profile. Forcing intake makes the user state their hypothesis upfront (what they already believe and want to verify or disprove) so the dossier tests it rather than confirms it. Output is an editable Word document (.docx) with verdict on the hypothesis, identity facts, 12-month activity timeline, network signals, reputation signals, red flags, 3-5 conversation hooks tied to specific findings, and source-provenance audit log. Uses WebSearch + WebFetch + free APIs (SEC EDGAR, GitHub, ProPublica Nonprofit Explorer) as workhorses; optional BYOK MCPs (LinkedIn, Crunchbase, Apollo, Pitchbook, SimilarWeb) enhance coverage. Triggers: 'research [company]', 'dossier on [person/company]', 'background check on [entity]', 'prep me for a meeting with [person/company]', 'due diligence on [company]', 'what should I know about [entity]', 'research [person] before I [meet/hire/invest]', 'competitor research on [company]', 'investor diligence [company]', 'interview prep for [company]'. Honors sensitivity exclusions for journalism + personal-vetting contexts.
timdevai/proteus/skills/community/from-rohitg00/git-advanced Skill
1★ repoAdvanced git workflows including worktrees, bisect, interactive rebase, hooks, and recovery techniques
timdevai/proteus/skills/pr-reviewer Skill
1★ repoAlways-on multi-agent AI workstation for Claude Code. 142 specialist agents (ML, security, K8s, backend, frontend) · 366 curated skills · 200+ prompt templates · auto prompt-matcher · auto skill-matcher · MCP support · token router cuts Anthropic bill 6x via Kimi/Haiku/Ollama. LiteLLM · BYOK · MIT + Apache. One-line install.
Verification before completion
pgoell/pgoell-claude-tools/plugins/workbench/skills/verification-before-completion Skill
1★ repoUse when about to claim work is complete, fixed, passing, ready, or safe to merge, especially before commits, pushes, PRs, or handoff summaries.
unbias38/my-claude-skills/paper-language-pass Skill
1★ repoMulti-agent staged language polish for English-language academic manuscripts whose science is already settled (post peer-review). Runs seven parallel specialist subagents — consistency, tense, hedging, prose, coherence, abstract, and manuscript hygiene (reviewer-talk, sycophancy, implementation leakage) — each scanning the whole paper for one dimension. Venue- and discipline-agnostic — user provides venue rules (citation policy, tense, spelling, word limit, etc.) and the skill calibrates severity accordingly; unspecified rules fall back to general academic defaults with downgraded flags. Produces a unified, severity-ranked, numbered issue list, then waits for user approval before applying any fix. Use when the user has a near-final draft (.docx, .md, or .tex) and wants a systematic language pass. Trigger phrases include "language pass", "polish my paper", "proofread my manuscript", "tense check", "hedging check", "整篇 polish", "潤稿", "投稿前最後檢查".
Cryptolens/skills/skills/license-key-verification Skill
no license1★ repoHelp with Devolens/Cryptolens software licensing tasks centered on license key verification, activation, signature checks, product ID checks, expiration checks, and machine-binding assumptions. Use when Codex needs to design, implement, review, or explain license key verification across .NET, Python, Java, Node.js, and related integrations.
Sayemnyc/claude-skills-for-writers/skills/personal/weekly-review-helper Skill
1★ repoRun a Friday weekly review that actually changes how the next week goes. Walks the user through six questions, captures the answers, and produces a short plan for next week. Used when the user wants to do a weekly review but does not want a 90-minute productivity ritual. Designed to take 25 minutes maximum.
Github pages deploy verification
MrBinnacle/skills/skills/engineering/github-pages-deploy-verification Skill
1★ repoVerify a GitHub Pages (or any CDN-fronted) deploy actually serves new content. Poll on a marker that did not exist pre-deploy; avoid sleep-and-curl chains the agent harness blocks.
Parallel review disposition schema
MrBinnacle/skills/skills/orchestration/parallel-review-disposition-schema Skill
1★ repoUse when dispatching parallel agents to verify/adjudicate findings — adversarial verify, security disposition, design triage, council fires. Shared disposition schema so seat outputs join cleanly.
React native test android visually
lukas-hinterleitner/visual-app-skills/skills/react-native-test-android-visually Skill
1★ repoRun a React Native or Expo app on a connected Android device or emulator, capture real screenshots via adb, read the Metro + logcat logs, and verify the visible UI and runtime behavior match what a recent code change intended. Use whenever the user asks to "test the app", "run it on Android", "see the visual changes", "verify a UI fix", "check if my change works/renders", or otherwise wants empirical on-device confirmation that a React Native / Expo change rendered correctly — even when they don't say "screenshot" or "logs". Handles starting Metro and the native build, waiting for the bundle + first frame, navigating with adb input, capturing the screen, reading Metro/logcat output (ReactNative / ReactNativeJS, Hermes, red-box errors), and reporting a concrete verdict with evidence. Covers bare React Native and Expo (dev client + run:android). Optionally diffs against a Figma reference when one is provided. Android only (iOS needs a Mac).
bfowle/spirit-island/skills/si-rules-check Skill
no license1★ repoUse BEFORE writing any spirit-chapter Opening Strategy T1/T2/T3 blocks, Tempo Profile tables, or per-turn Energy/CP/elements claims. Returns the spirit's Wiki-verified starting state + growth-option decoder + legal-play-combination calculator, so the resulting turn-by-turn prose is mechanically valid rather than hallucinated. Resolves the class of bug caught on Shadows T1 (wrote "Concealing + Mantle" when Shadows starts 0E/1CP and neither G2 branch allows that combo).
feichangai-team/china-compliance-skills/skills/cn-compliance-guard Skill
1★ repoScan Chinese text for 200+ banned words across 6 legal categories (广告法/消费者权益保护法), check SEO compliance for 5 platforms (百度/小红书/抖音/淘宝/京东), and provide safe replacement suggestions. Detects 绝对化用语, 医疗效果承诺, 虚假宣传, 金融承诺, 诱导消费, 比较广告. Use when: checking Chinese marketing copy for legal compliance, reviewing product descriptions for advertising law violations, auditing content before publishing on Chinese platforms, replacing banned words with safe alternatives.
thepictishbeast/claude-tools/skills/double-check Skill
1★ repoRun the verification stack against work you just produced (code, configs, deps). Use after any substantive change, before reporting it done.
thepictishbeast/claude-tools/skills/loop-health Skill
1★ repoSingle-shot lint diagnostic across all active + paused loops and the history file. Reports missing canaries, oversized prompts, stale entries, orphan history events, malformed state files, and rotation candidates. Use when the user says "check loop health", "audit my loops", "lint my loop state", or "anything wrong with my loops?"
thepictishbeast/claude-tools/skills/regression-guard Skill
1★ repoGenerate a Rust #[test] skeleton that anchors a refactor commit. Reads the commit's diff, auto-detects the refactor pattern (let-else / let-Ok-else / warn-continue / SAFETY-annot / graceful-degrade / struct-update / error-return), emits a test fn skeleton with REGRESSION-GUARD docstring back-ref so reverting the fix surfaces the commit in test output.
diguike/book-claude-skill/examples/ch16-composition/parallel-review/review-security Skill
1★ repoSecurity-focused code review. Fork subagent for parallel execution. 安全专项审查。
diguike/book-claude-skill/examples/ch16-composition/parallel-review/review-style Skill
1★ repoStyle-focused code review. Fork subagent for parallel execution. 代码风格审查。
diguike/book-claude-skill/examples/ch16-composition/review-then-fix/code-review Skill
1★ repoReview code and output issues to a structured file for downstream processing. 代码审查并输出问题列表文件。
diguike/book-claude-skill/examples/ch24-extended-backend Skill
1★ repo审查后端 API 接口的设计和实现。当用户说'review 这个接口'、'检查 API 设计'、'看看这个 handler'时使用。
diguike/book-claude-skill/examples/ch24-graduation/changelog-generator Skill
1★ repoGenerate a changelog from git commits using conventional commit format. 从 git 提交记录生成 CHANGELOG。
diguike/book-claude-skill/skills/code-review-snapshots/v1-minimal Skill
1★ repo审查代码的质量、安全性和可维护性。当用户说'review 这段代码'、'帮我看看这个 PR'、'检查一下代码质量'时使用。
diguike/book-claude-skill/skills/code-review-snapshots/v2-structured-output Skill
1★ repo审查代码的质量、安全性和可维护性。当用户说'review 这段代码'、'帮我看看这个 PR'、'检查一下代码质量'、'这段代码有没有问题'时使用。
diguike/book-claude-skill/skills/code-review-snapshots/v3-dynamic-context Skill
1★ repo审查代码的质量、安全性和可维护性。当用户说'review 这段代码'、'帮我看看这个 PR'、'检查一下代码质量'、'这段代码有没有问题'时使用。
diguike/book-claude-skill/skills/code-review-snapshots/v4-external-knowledge Skill
1★ repo审查代码的质量、安全性和可维护性。当用户说'review 这段代码'、'帮我看看这个 PR'、'检查一下代码质量'、'这段代码有没有问题'时使用。
diguike/book-claude-skill/skills/code-review-snapshots/v5-pluggable-rules Skill
1★ repo审查代码的质量、安全性和可维护性。当用户说'review 这段代码'、'帮我看看这个 PR'、'检查一下代码质量'、'这段代码有没有问题'时使用。
diguike/book-claude-skill/skills/code-review-snapshots/v6-with-scripts Skill
1★ repo审查代码的质量、安全性和可维护性。当用户说'review 这段代码'、'帮我看看这个 PR'、'检查一下代码质量'、'这段代码有没有问题'时使用。
diguike/book-claude-skill/skills/code-review-snapshots/v7-log-and-scoring Skill
1★ repo审查代码的质量、安全性和可维护性。当用户说'review 这段代码'、'帮我看看这个 PR'、'检查一下代码质量'、'这段代码有没有问题'时使用。
diguike/book-claude-skill/skills/code-review-snapshots/v8-hooks Skill
1★ repo审查代码的质量、安全性和可维护性。当用户说'review 这段代码'、'帮我看看这个 PR'、'检查一下代码质量'、'这段代码有没有问题'时使用。
diguike/book-claude-skill/skills/code-review-snapshots/v9-subagent Skill
1★ repo审查代码的质量、安全性和可维护性。当用户说'review 这段代码'、'帮我看看这个 PR'、'检查一下代码质量'、'这段代码有没有问题'、'帮我 check 一下'时使用。
diguike/book-claude-skill/skills/code-review Skill
1★ repo审查代码的质量、安全性和可维护性。当用户说'review 这段代码'、'帮我看看这个 PR'、'检查一下代码质量'、'这段代码有没有问题'、'帮我 check 一下'时使用。
diguike/book-claude-skill/skills/commit-message Skill
1★ repo生成符合 Conventional Commits 规范的 commit message。当用户说'提交'、'commit'、'写个 commit message'时使用。
natthasath/natthasath-marketplace/plugins/projects/skills/checkpoint Skill
1★ repoสร้าง git safety commit ก่อนให้ Claude ทำงาน เพื่อป้องกัน code หาย ใช้ skill นี้ก่อนทุกครั้งที่จะให้ Claude implement หรือ refactor เช่น "checkpoint ก่อน", "เซฟ code ก่อน", "ก่อน implement ขอ checkpoint"
natthasath/natthasath-marketplace/plugins/projects/skills/start-task Skill
1★ repoเริ่มทำงาน task โดยย้าย task จาก backlog เข้า sprint และแนะนำชื่อ git branch ที่ควรสร้าง ใช้ skill นี้ก่อน /checkpoint และ /implement เช่น "เริ่ม task นี้", "start task", "จะทำ task นี้แล้ว"
nunoamorim99/agile-ledger/skills/agile-ledger Skill
1★ repoPlain-Markdown Scrum / Agile product-management system for Claude Code. Manage a product backlog of Epics and User Stories, plan and run sprints, drive a board, track velocity, cut Major.Minor releases, and keep GitHub branches/commits/PRs traceable to stories — all from slash commands, with no Jira and no database. Use this skill whenever the user mentions a backlog, epic, user story, sprint, sprint planning, standup, board, story points, velocity, acceptance criteria, definition of done/ready, release, changelog, roadmap, or wants to capture / triage / detail / ship a product idea, plan a sprint, open a PR for a story, or check what merged to main — even if they don't say "Agile-Ledger" explicitly. The `Agile-Ledger/` folder of Markdown files is the single source of truth; keep it true.