Review & quality
19,169 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
buildmoonshot/skillpacks/skills/engineering/intermediate/check-the-docs Skill
2★ repoUse when writing or modifying code that calls an external library, framework, SDK, or API — especially one that is niche, recently updated, or whose exact method names and parameters you are not certain of. Makes the agent confirm real, current API signatures before using them, instead of inventing plausible-but-wrong calls from memory.
buildmoonshot/skillpacks/skills/engineering/intermediate/commit-hygiene Skill
2★ repoUse when committing changes with git — staging files and writing commit messages. Makes the agent keep each commit focused on one logical change and write a clear, conventional message explaining why, instead of dumping unrelated edits into a single vague "update" commit.
Mikacr1138/claude-bug-bounty/skills/triage-validation Skill
2★ repoFinding validation before writing any report — 7-Question Gate (all 7 questions), 4 pre-submission gates, always-rejected list, conditionally valid with chain table, CVSS 3.1 quick reference, severity decision guide, report title formula, 60-second pre-submit checklist. Use BEFORE writing any report. One wrong answer = kill the finding and move on. Saves N/A ratio.
natuleadan/skills/skills/010108-version-control Skill
2★ repoConventional commit format, git staging safety, disaster recovery with git reflog, and commit message best practices.
Heet-P/skills/skills/impeccable Skill
no license2★ repoUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
The same file is in 67 other repositories
Heet-P/skills/skills/legal-check Skill
no license2★ repoFull-stack legal, privacy, and compliance audit engine for web applications and SaaS platforms. Use this skill when the user wants to audit a codebase for legal exposure, privacy risks, GDPR/CCPA compliance gaps, missing consent flows, unsafe data practices, cookie policy issues, payment/auth compliance, AI disclosure requirements, or platform liability risks. Trigger whenever the user says "audit my app for compliance", "check my codebase for privacy issues", "do a legal check", "GDPR audit", "privacy policy review", "terms of service check", "is my app compliant", or uploads/shares a codebase and asks about legal or privacy concerns. Also trigger proactively when reviewing any app that handles user accounts, payments, AI outputs, or file uploads — even if the user doesn't use the word "legal".
nicodiansk/turbocharge/skills/build Skill
2★ repoUse when you have an implementation plan ready to execute. Dispatches builder agents (Sonnet) per task with self-review. Opt-in review (single Sonnet task-reviewer, two verdicts) for high-risk tasks. Supports single-track and multi-track parallel execution.
nicodiansk/turbocharge/skills/review Skill
2★ repoUse before merging to verify completed work meets requirements and quality standards. Dispatches code-reviewer for holistic assessment of the full git diff against the original plan.
OpenSIN-AI/OpenSIN-Skills/engineering-team/adversarial-reviewer Skill
no license2★ 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
OpenSIN-AI/OpenSIN-Skills/engineering-team/code-reviewer Skill
no license2★ 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
OpenSIN-AI/OpenSIN-Skills/engineering-team/playwright-pro/skills/review Skill
no license2★ 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
OpenSIN-AI/OpenSIN-Skills/engineering-team/self-improving-agent/skills/review Skill
no license2★ repoAnalyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics.
The same file is in 1 other repository
OpenSIN-AI/OpenSIN-Skills/engineering/agenthub Skill
no license2★ 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
OpenSIN-AI/OpenSIN-Skills/engineering/api-design-reviewer Skill
no license2★ repoAPI Design Reviewer
OpenSIN-AI/OpenSIN-Skills/engineering/autoresearch-agent Skill
no license2★ 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
OpenSIN-AI/OpenSIN-Skills/engineering/git-worktree-manager Skill
no license2★ repoGit Worktree Manager
OpenSIN-AI/OpenSIN-Skills/engineering/karpathy-coder Skill
no license2★ 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
OpenSIN-AI/OpenSIN-Skills/engineering/pr-review-expert Skill
no license2★ 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
OpenSIN-AI/OpenSIN-Skills/operations/browser-automation/check-my-dev-in-web Skill
no license2★ repoFast web-app verification workflow for local dev, preview deployments, and static builds without heavy browser automation. Prioritizes cheap checks first: diagnostics, build, HTTP smoke, asset verification, webhint, and Lighthouse. Escalate to a real browser only when cheaper signals cannot explain the failure.
OpenSIN-AI/OpenSIN-Skills/operations/planning/check-plan-done Skill
no license2★ repoDEPRECATED — Use /plan instead. Unified plan-and-execute workflow merged into /plan.
OpenSIN-AI/OpenSIN-Skills/operations/planning/plan Skill
no license2★ repoUltimate plan-and-execute skill v2. 13 stages: Check, Research, Dependency Analysis, Plan Draft, Estimation & Risk, Critical Review, Quality Score, Approval & Decision Register, GitHub Sync, What-If Simulation, Execute, Auto Re-Plan, Verify, Post-Mortem & Learn. Adds: Plan JSON Schema, Dependency DAG, 3-Point Estimation (PERT), Monte Carlo, Risk Scoring (0-100), OKR Framework, Decision Register, Assumptions Log, Plan Quality Score (0-100), Auto Re-Plan Triggers, Plan Templates, Multi-Stage Approval, What-If Simulation, Post-Mortem Learning Loop, Blocker Detection, Plan Versioning, Continuous Planning Mode. Replaces /check-plan-done, /omoc-plan-swarm, /biometrics-plan.
imamirezaei/Product-Team-Claude-Skills/policy/product-designer/skills/implementation-review Skill
no license2★ repoUse this skill when the designer wants to verify that what engineering implemented matches the Figma design. Reads both Figma and the codebase, compares them, and produces a gap report. Triggers: 'does the implementation match the design', 'check what was built against Figma', 'review the implemented component', 'QA the dev output', 'does the code match my design'.
imamirezaei/Product-Team-Claude-Skills/policy/product-designer/skills/vuetify-constraint-check Skill
no license2★ repoUse this skill to verify that every UI component in a design can be implemented with Vuetify 3. Triggers: 'check Vuetify compatibility', 'can this be built with Vuetify', 'verify component coverage', 'are there any Vuetify gaps', or when running as step 1 in the /design-handoff chain.
imamirezaei/Product-Team-Claude-Skills/policy/product-manager/skills/scope-check Skill
no license2★ repoUse this skill when a feature that is already defined or in progress has grown beyond its original boundaries. This is a scope creep intervention tool — not an initial scoping tool. Triggers: 'this feature keeps growing', 'engineering said there is too much work', 'I want to reduce scope', 'this is taking longer than expected', 'we keep adding things to this feature', 'management is adding requirements mid-sprint'. Do NOT use for initial feature definition — use problem-framing for that. The difference: problem-framing defines scope upfront; scope-check catches and trims scope that has already drifted.
imamirezaei/Product-Team-Claude-Skills/policy/shared/skills/design-system-check Skill
no license2★ repoUse this skill when the PM or designer is planning a new feature and needs to know what UI components already exist in the design system before requesting new ones. Triggers: 'what components do we have', 'do we need to build this UI from scratch or do we have a component', 'I want to make sure we are not building something that already exists', 'the designer said we need a new component', or any situation where UI/UX planning requires knowing what already exists.
imamirezaei/Product-Team-Claude-Skills/policy/shared/skills/prompt-optimizer Skill
no license2★ repoAnalyze, critique, and rewrite user prompts to maximize clarity, specificity, and output quality for Claude (both claude.ai and Claude Code). Use this skill whenever the user says "بهینه کن", "prompt رو بهتر کن", "این prompt خوبه؟", "optimize this prompt", "improve my prompt", "review my prompt", "critique this prompt", "rewrite this prompt", "پرامپتم رو ببین", "نقد کن", "چطور بهترش کنم", or pastes a prompt and asks for feedback. Also trigger when the user shares a prompt draft and asks "what's wrong with this" or "how can I get better results". Even if the user just pastes a prompt without explicit instruction but the context suggests they want improvement, use this skill.
WhatIfWeDigDeeper/agent-skills/skills/peer-review Skill
2★ repoGet a fresh-context review of staged changes, branches, PRs, or file sets. Delegates to a fresh-context reviewer by default; routes to external LLM CLIs (Copilot, Codex, Gemini) when --model specifies one. Use when: user says "peer review" (e.g. "peer review PR 5", "peer review staged", "peer review this branch"), "fresh review", "another set of eyes", "sanity check", "quick review before I push", or routes to an external model ("review with Gemini", "review with Copilot", "review using Codex"). Do NOT trigger on bare "review" phrases (e.g. "review my changes", "review PR N", "review staged") — those route to code-review.
WhatIfWeDigDeeper/agent-skills/skills/pr-comments Skill
2★ repoMy Agent Skills I've created for Claude Code and can, in principle, be used with other coding assistants
WhatIfWeDigDeeper/agent-skills/skills/pr-human-guide Skill
2★ repoMy Agent Skills I've created for Claude Code and can, in principle, be used with other coding assistants
WhatIfWeDigDeeper/agent-skills/skills/ship-it Skill
2★ repoCreate branch, commit, push, and open a pull request. Use when: user says "ship it", "ship this", "create a PR", "open a PR", "push and PR", or wants to go from uncommitted changes to an open pull request.
felipecabargas/gambit/skills/sprint-review Skill
2★ repoGenerate a professional sprint review report for stakeholders — PMs, leadership, and cross-functional teams. Use this skill whenever a user wants to write up a sprint, summarize what the team shipped, produce a sprint retrospective document, recap what was completed in an iteration, or create a sprint summary for leadership. Triggers include: "write my sprint review", "generate a sprint recap", "create a sprint report", "summarize what we shipped this sprint", "help me write up our sprint for stakeholders", or any mention of sprint outcomes, velocity reports, or iteration summaries — even if they don't use the word "skill" or "report". Also trigger when a user pastes a list of tickets/tasks and asks for a write-up or summary.
felipecabargas/gambit/skills/verify-acceptance-criteria Skill
2★ repoVerify acceptance criteria quality and identify gaps. Use this skill whenever you need to evaluate acceptance criteria (ACs) to ensure they meet quality standards. Trigger on: "review these ACs", "check if these acceptance criteria are good", "validate my user story criteria", "improve our acceptance criteria", "audit these requirements", "do these ACs pass review", or similar requests. Also use proactively when someone shares acceptance criteria that look hastily written or vague. The skill analyzes criteria against five key dimensions (clarity, testability, outcome-focus, measurability, independence), scores issues by severity (critical/major/minor), and generates a structured report. It can also rewrite poor criteria into better ones or convert them to user story format.
rudrathegreat/Astronomy-AI-Toolkit/skills/literature/literature_review_builder Skill
no license2★ repoA catered AI toolkit for astronomers
rudrathegreat/Astronomy-AI-Toolkit/skills/software_engineering/scientific_code_reviewer Skill
no license2★ repoA catered AI toolkit for astronomers
jeonnoin-alt/Eureka/skills/receiving-research-review Skill
2★ repoUse when receiving research review feedback, before implementing suggestions — requires verification against actual data and scientific reasoning, not performative agreement
jeonnoin-alt/Eureka/skills/requesting-research-review Skill
2★ repoUse when an experiment phase is complete, before drawing conclusions, before writing results, or before claiming findings are publication-ready
Verification before publication
jeonnoin-alt/Eureka/skills/verification-before-publication Skill
2★ repoUse before claiming results are publication-ready, before submitting manuscripts, or before sharing findings externally — requires fresh verification evidence for every claim
dversoza/claude-skills/pr-feedback Skill
no license2★ repoAddress PR review feedback including inline threads, general comments, bot-generated reviews, PR description findings, and CI failures. Use when asked to handle, address, resolve, respond to, or work through PR review comments, review feedback, or CI check failures. Triggers on requests like "address PR comments", "handle review feedback", "resolve PR reviews", "fix review comments", "go through PR feedback", "check CI failures".
haidrrrry/loop-engineering-skills/skills/loop-verifier Skill
2★ repoVerify agent work against project gates before declaring it done. Use this skill whenever working in a project with a .loop/GATES.md file, whenever finishing any coding task inside a loop, whenever the user asks "is this actually done", "verify this", "check your work", or before emitting any VERDICT line. Also use it when a task involves tests, refactors, bug fixes, or dependency updates, when deciding whether work should be escalated to a human, and when the user asks to "audit my loop", "check loop readiness", or evaluate their loop setup.
zachjxyz/jvn/template/.claude/skills/review-checklist Skill
2★ repoCode review standards and checklist for the code-reviewer agent
rampstackco/claude-skills-starter/skills/qa-testing Skill
2★ repoRun QA testing on a page, feature, or full site at one of three depth tiers (smoke, standard, full). Use this skill whenever the user asks to test a page, audit a site, check for bugs, verify a deploy, run a QA sweep, or review accessibility, performance, or SEO basics. Triggers on test, QA, audit, verify, check, is it working, does it look right, broken, 404, image not loading, post-deploy check, regression test. Also triggers proactively after any significant code change or new page launch where verification matters.
The same file is in 1 other repository
raja21068/AutoResearch/skills/aris/auto-review-loop-llm Skill
2★ repoAutonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
The same file is in 1 other repository
raja21068/AutoResearch/skills/aris/auto-review-loop-minimax Skill
2★ repoAutonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
The same file is in 1 other repository
raja21068/AutoResearch/skills/aris/auto-review-loop Skill
2★ repoAutonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
The same file is in 1 other repository
raja21068/AutoResearch/skills/aris/citation-audit Skill
2★ repoZero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports. Uses a fresh cross-model reviewer with web/DBLP/arXiv lookup to catch hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations (cite present but the cited paper does not establish the claim). Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.
raja21068/AutoResearch/skills/aris/comm-lit-review Skill
2★ repoCommunications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary. Search Zotero, Obsidian, and local paper folders first when available, then search IEEE Xplore, ScienceDirect, ACM Digital Library, and broader web in that order.
The same file is in 3 other repositories
raja21068/AutoResearch/skills/aris/kill-argument Skill
2★ repoTwo-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues. Use when user says "kill argument", "adversarial review", "hostile review", "rebuttal preparation", "reviewer-2 simulation", or before submitting a theory paper that has already passed standard review rounds.
raja21068/AutoResearch/skills/aris/novelty-check Skill
2★ repoVerify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.
The same file is in 1 other repository
raja21068/AutoResearch/skills/aris/paper-claim-audit Skill
2★ repoZero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh cross-model reviewer with NO prior context to prevent confirmation bias. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.
The same file is in 1 other repository
raja21068/AutoResearch/skills/aris/patent-novelty-check Skill
2★ repoAssess patent novelty and non-obviousness against prior art. Use when user says "专利查新", "patent novelty", "可专利性评估", "patentability check", or wants to evaluate if an invention is patentable.
The same file is in 1 other repository
raja21068/AutoResearch/skills/aris/patent-review Skill
2★ repoGet an external patent examiner review of a patent application. Use when user says "专利审查", "patent review", "审查意见", "examiner review", or wants critical feedback on patent claims and specification.
The same file is in 1 other repository
raja21068/AutoResearch/skills/aris/proof-checker Skill
2★ repoRigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (Codex GPT-5.4 xhigh), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.
raja21068/AutoResearch/skills/aris/research-review Skill
2★ repoGet a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
The same file is in 1 other repository
raja21068/AutoResearch/skills/aris/skills-codex-claude-review/auto-review-loop Skill
2★ repoAutonomous multi-round research review loop. Repeatedly reviews using Claude Code via claude-review MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
The same file is in 1 other repository
raja21068/AutoResearch/skills/aris/skills-codex-claude-review/novelty-check Skill
2★ repoVerify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.
The same file is in 3 other repositories
raja21068/AutoResearch/skills/aris/skills-codex-claude-review/research-review Skill
2★ repoGet a deep critical review of research from Claude via claude-review MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
The same file is in 3 other repositories
raja21068/AutoResearch/skills/aris/skills-codex-gemini-review/auto-review-loop Skill
2★ repoAutonomous multi-round research review loop. Repeatedly reviews using Gemini via gemini-review MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
The same file is in 1 other repository
raja21068/AutoResearch/skills/aris/skills-codex-gemini-review/novelty-check Skill
2★ repoVerify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.
The same file is in 3 other repositories
raja21068/AutoResearch/skills/aris/skills-codex-gemini-review/research-review Skill
2★ repoGet a deep critical review of research from Gemini via gemini-review MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
The same file is in 3 other repositories
raja21068/AutoResearch/skills/aris/skills-codex/auto-review-loop-llm Skill
2★ repoAutonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
The same file is in 1 other repository