Review & quality
19,195 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
AndrewNgGirl/SkillLens/skills/skill-scorer/examples/mega-pipeline/agents/typing Skill
45★ repoUse when the parent pipeline routes a typing-related PR review request. Reads the diff and emits structured typingFindings using the typing specialist heuristics.
AndrewNgGirl/SkillLens/skills/skill-scorer/examples/mega-pipeline/agents/xss Skill
45★ repoUse when the parent pipeline routes a xss-related PR review request. Reads the diff and emits structured xssFindings using the xss specialist heuristics.
AndrewNgGirl/SkillLens/skills/skill-scorer/examples/pr-pipeline Skill
45★ repoUse when the user wants to review a GitHub pull request through a multi-stage pipeline. Routes through reviewer, summarizer, and final report stages.
AndrewNgGirl/SkillLens/skills/skill-scorer/examples/pr-pipeline/agents/reviewer Skill
45★ repoUse when the parent pipeline routes a PR review request. Reads diff and produces a Pydantic ReviewReport.
AndrewNgGirl/SkillLens/skills/skill-scorer/examples/pr-reviewer Skill
45★ repoUse when the user asks to review, audit, comment on, or 评审 / 审查 a GitHub Pull Request. Generates structured review comments covering team-specific code style, naming, and structural conventions — complements (not replaces) bug-finding tools like Copilot Code Review or CodeQL.
gmaxxxie/ai-native-product-agent-skills/skills/p0b-real-needs-validator Skill
no license45★ repo真需求判断五问验车器。AI 时代最危险的不是没有需求,而是伪需求太容易长得像真需求。 基于《AI rebuild product needs》工具卡。
P12a contemplation prerequisite check
gmaxxxie/ai-native-product-agent-skills/skills/p12a-contemplation-prerequisite-check Skill
no license45★ repo检查方法使用的前提是否成立——识别情境变化、验证假设前提、重配适用方法
gmaxxxie/ai-native-product-agent-skills/skills/p13h-validation-market Skill
no license45★ repo九步后段——怎么验证、怎么进入市场、反馈回路的决策框架
gmaxxxie/ai-native-product-agent-skills/skills/p2e-shadow-validation Skill
no license45★ repo'AI Native 产品方法论——影子验证的实操 Skill。
KevinKE93/Dev_Agent_OPC/dev-agent/skills/git-workflow-and-versioning Skill
no license45★ repoStructures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.
Xopoko/build-swift-apps/skills/appstore-review-readiness Skill
45★ repoValidate App Store submission readiness and execute prepared review actions with current `asc` commands. Use after appstore-release-planner chooses the review path, or when the user directly asks to validate, stage, submit, monitor, cancel, or repair ASC review blockers.
Xopoko/build-swift-apps/skills/appstore-screenshot-validator Skill
45★ repoResize, strip alpha, color-convert, validate, and upload App Store screenshots using current `asc screenshots` size data and macOS `sips`.
tikoci/routeros-skills/routeros-syntax-inspection Skill
44★ repoInspecting and validating RouterOS command/script syntax against a live device via /console/inspect (highlight, completion, syntax, child) and :parse IL. Use when: validating RouterOS commands before execution, explaining or linting RouterOS scripts, building syntax-aware tooling (LSP servers, validators, agent explain/check commands), interpreting highlight token streams or :parse intermediate language, discovering enum values or argument schemas, or when the user mentions console/inspect, highlight tokens, parseIL, or RouterOS script validation.
Aurite-ai/agent-verifier/skills/verify-patterns Skill
44★ repoVerify AI agent patterns including loop safety, retry limits, tool consistency, context size, and graph cycle analysis. Use when asked to "verify agent patterns", "check loops", "verify tools", or "check retry limits".
The same file is in 1 other repository
Aurite-ai/agent-verifier/skills/verify-quality Skill
44★ repoVerify code quality including naming conventions, organization, documentation, and general best practices. Use when asked to "verify quality", "check code quality", or "review code organization".
The same file is in 1 other repository
Aurite-ai/agent-verifier/skills/verify-security Skill
44★ repoVerify code for security issues including hardcoded secrets, input validation, error exposure, and dependency vulnerabilities. Use when asked to "verify security", "check for secrets", or "scan for vulnerabilities".
The same file is in 1 other repository
Frictionless tabular validation starter
ma-compbio-lab/SkillFoundry/skills/data-acquisition-and-dataset-handling/frictionless-tabular-validation-starter Skill
44★ repoA framework for discovering, compiling, and validating reusable skills for scientific agents.
Precommit regression testing starter
ma-compbio-lab/SkillFoundry/skills/meta-maintenance/precommit-regression-testing-starter Skill
44★ repoA framework for discovering, compiling, and validating reusable skills for scientific agents.
Numerical benchmarking and verification starter
ma-compbio-lab/SkillFoundry/skills/scientific-computing-and-numerical-methods/numerical-benchmarking-and-verification-starter Skill
44★ repoA framework for discovering, compiling, and validating reusable skills for scientific agents.
Semantic scholar review paper mining starter
ma-compbio-lab/SkillFoundry/skills/scientific-knowledge/semantic-scholar-review-paper-mining-starter Skill
44★ repoMine likely review, survey, and meta-analysis papers from a local metadata set using deterministic title and abstract heuristics aligned with Semantic Scholar review-search workflows.
itallstartedwithaidea/agent-skills/skills/claude-mythos/verification-loops Skill
44★ repoVerification Loops are systematic evaluation pipelines that validate agent outputs at every stage of execution.
The same file is in 1 other repository
itallstartedwithaidea/agent-skills/skills/software-dev/code-review Skill
44★ repoCode Review enforces a structured pre-merge quality gate with a checklist-driven evaluation, severity-classified findings, and mandatory resolution tracking.
itallstartedwithaidea/agent-skills/skills/software-dev/git-worktrees Skill
44★ repoGit Worktrees enables parallel development by maintaining multiple checked-out branches simultaneously in separate directories.
AsiaOstrich/universal-dev-skills/skills/commit-standards Skill
no license43★ repoFormat commit messages following conventional commits standard. Use when: writing commit messages, git commit, reviewing commit history. Keywords: commit, git, message, conventional, 提交, 訊息, feat, fix, refactor.
AsiaOstrich/universal-dev-skills/skills/git-workflow-guide Skill
no license43★ repoGuide Git branching strategies, branch naming, and merge operations. Use when: creating branches, merging, pull requests, Git workflow questions. Keywords: branch, merge, PR, pull request, GitFlow, GitHub Flow, 分支, 合併, 工作流程.
sequenzia/agent-alchemy/claude/cs-tools/skills/verify Skill
43★ repoVerify a competitive programming or LeetCode solution for correctness, edge cases, and performance. Use when asked to "verify my solution", "check my code", "is this solution correct", "test my solution", "review my competitive programming answer", "validate my algorithm", or any solution verification request.
The same file is in 2 other repositories
sequenzia/agent-alchemy/claude/dev-tools/skills/release-python-package Skill
43★ repoPrepare and execute a Python package release with verification steps. Use for releasing Python packages with uv and ruff.
The same file is in 2 other repositories
sequenzia/agent-alchemy/claude/git-tools/skills/git-commit Skill
43★ repoCommit staged changes with conventional commit message. Use when user says "commit changes", "commit this", "save my changes", or wants to create a git commit.
The same file is in 2 other repositories
sequenzia/agent-alchemy/claude/plugin-tools/skills/dependency-checker Skill
43★ repoAnalyzes the Agent Alchemy plugin ecosystem to detect dependency issues across all plugin groups
The same file is in 2 other repositories
cgallic/kai-cmo-harness/harness/skills/kai-daily-ad-review Skill
no license43★ repoDaily ad performance check-in across platforms. Pulls live metrics from Meta, Google, and LinkedIn via deterministic scripts, compares against benchmarks and previous period, flags overspend/underperformers/policy issues, and outputs a quick daily summary with action items. Use when "daily ad review", "how are my ads doing today", "ad check-in", "morning ad report", "daily ad summary", "check ad performance", "ad dashboard", "daily ads", or any request for a recurring or quick-glance ad performance review.
cgallic/kai-cmo-harness/harness/skills/kai-gate Skill
no license43★ repoRun Kai CMO Harness quality gates on content. Scores Four U's (Unique/Useful/Ultra-specific/Urgent), checks for banned words and AI slop, runs SEO lint for search content. Use when "score this", "quality check", "run quality gates", "check this content", "four u's score", "banned word check", "SEO lint", or any request to validate content quality before publishing.
PangenomeAI/academic-skills-food-nutrition/agri-review Skill
43★ repoMulti-reviewer peer-review system for agricultural manuscripts. Simulates an editorial panel — a coordinating editor, three domain reviewers (methodology, domain/novelty, integrity/ethics) and a devil's advocate — plus a formatting check against the target journal, all acting as senior agricultural scientists. Same machinery as food-review, including the knowledge_builder that reads the cited sources and key field literature first, grounded in agriculture literature (Q1/Q2 preferred, Q4 avoided) and agricultural standards for field trials, experimental unit and pseudoreplication, animal ethics and soils. Triggers: review my agronomy paper, peer review agricultural manuscript, referee report soil science, critique my crop paper, pre-submission review agriculture, mock review animal science.
PangenomeAI/academic-skills-food-nutrition/food-review Skill
43★ repoMulti-reviewer peer-review system for food & nutrition manuscripts. Simulates an editorial panel — a coordinating editor, three domain reviewers (methodology/statistics, domain/novelty, integrity/ethics), and a devil's advocate — plus a formatting-compliance check against the target journal (APA 7.0 by default, or a specific journal via journal-selector). Grounds the panel first: reads the manuscript's cited sources and the field's key literature into a knowledge base, so novelty and correctness are judged from evidence, not impression. Use for pre-submission review, reviewer reports, mock peer review, or a critique before submitting. Triggers: review my paper, peer review, referee report, reviewer reports, critique my manuscript, pre-submission review, is my paper ready, mock review, editorial review, assess novelty and rigor.
sequenzia/agent-alchemy/ported/20260304-102613/dev-tools/skills/code-reviewer Skill
42★ repoReviews code implementations for correctness, security, maintainability with confidence-scored findings (converted from agent)
sequenzia/agent-alchemy/ported/20260304-102613/git-tools/skills/git-commit Skill
42★ repoCommit staged changes with conventional commit message. Use when user says "commit changes", "commit this", "save my changes", or wants to create a git commit.
sequenzia/agent-alchemy/ported/20260305-085418/dev-tools/skills/release Skill
42★ repoPrepare and execute a Python package release with verification steps. Use for releasing Python packages with uv and ruff.
sequenzia/agent-alchemy/ported/20260305-085418/git-tools/skills/git-commit Skill
42★ repoCommit staged changes with conventional commit message. Use when user says "commit changes", "commit this", "save my changes", or wants to create a git commit.
sequenzia/agent-alchemy/ported/20260305-191444/skills/git-commit Skill
42★ repoCommit staged changes with conventional commit message. Use when user says "commit changes", "commit this", "save my changes", or wants to create a git commit.
sequenzia/agent-alchemy/ported/20260305-191444/skills/release Skill
42★ repoPrepare and execute a Python package release with verification steps. Use for releasing Python packages with uv and ruff.
sequenzia/agent-alchemy/ported/20260310/all/skills-flat/code-reviewer Skill
42★ repoReviews code implementations for correctness, security, maintainability with confidence-scored findings (converted from agent)
sequenzia/agent-alchemy/ported/20260310/all/skills-flat/git-commit Skill
42★ repoCommit staged changes with conventional commit message. Use when user says "commit changes", "commit this", "save my changes", or wants to create a git commit.
sequenzia/agent-alchemy/ported/20260310/all/skills-flat/release Skill
42★ repoPrepare and execute a Python package release with verification steps. Use for releasing Python packages with uv and ruff.
sequenzia/agent-alchemy/ported/20260310/all/skills-nested/git-commit Skill
42★ repoCommit staged changes with conventional commit message. Use when user says "commit changes", "commit this", "save my changes", or wants to create a git commit.
sequenzia/agent-alchemy/ported/20260310/all/skills-nested/release-python-package Skill
42★ repoPrepare and execute a Python package release with verification steps. Use for releasing Python packages with uv and ruff.
sequenzia/agent-alchemy/ported/20260310/all/skills/git-commit Skill
42★ repoCommit staged changes with conventional commit message. Use when user says "commit changes", "commit this", "save my changes", or wants to create a git commit.
sequenzia/agent-alchemy/ported/20260310/all/skills/release Skill
42★ repoPrepare and execute a Python package release with verification steps. Use for releasing Python packages with uv and ruff.
sequenzia/agent-alchemy/ported/20260310/flat/dev-tools/skills/code-reviewer Skill
42★ repoReviews code implementations for correctness, security, maintainability with confidence-scored findings (converted from agent)
sequenzia/agent-alchemy/ported/20260310/flat/dev-tools/skills/release Skill
42★ repoPrepare and execute a Python package release with verification steps. Use for releasing Python packages with uv and ruff.
sequenzia/agent-alchemy/ported/20260310/flat/git-tools/skills/git-commit Skill
42★ repoCommit staged changes with conventional commit message. Use when user says "commit changes", "commit this", "save my changes", or wants to create a git commit.
sequenzia/agent-alchemy/ported/20260310/full/dev-tools/skills/release Skill
42★ repoPrepare and execute a Python package release with verification steps. Use for releasing Python packages with uv and ruff.
sequenzia/agent-alchemy/ported/20260310/full/git-tools/skills/git-commit Skill
42★ repoCommit staged changes with conventional commit message. Use when user says "commit changes", "commit this", "save my changes", or wants to create a git commit.
sequenzia/agent-alchemy/ported/20260310/nested/dev-tools/skills/release-python-package Skill
42★ repoPrepare and execute a Python package release with verification steps. Use for releasing Python packages with uv and ruff.
sequenzia/agent-alchemy/ported/20260310/nested/git-tools/skills/git-commit Skill
42★ repoCommit staged changes with conventional commit message. Use when user says "commit changes", "commit this", "save my changes", or wants to create a git commit.
stjbrown/agent-knowledge/skills/kb-lint Skill
42★ repoPortable Agent Skills for building and maintaining Open Knowledge Format project wikis in plain Markdown.
TheStack-ai/swing-skills/skills/swing-research Skill
41★ repoDeep research with cross-verification and source tiering. Use when investigating technologies, comparing tools, fact-checking claims, evaluating architectures, or any task requiring verified information. Triggers on "조사해줘", "리서치", "research", "investigate", "fact-check", "비교 분석", "검증해줘".
The same file is in 2 other repositories
TheStack-ai/swing-skills/skills/swing-review Skill
41★ repoDevil's Advocate stress-testing for code, architecture, PRs, and decisions. Surfaces hidden flaws through structured adversarial analysis with metacognitive depth. Use for high-stakes review, stress-testing choices, or when the user wants problems found deliberately. NOT for routine code review. Triggers on "스트레스 테스트", "stress test", "devil's advocate", "반론", "이거 괜찮아", "문제 없을까", "깊은 리뷰", "critical review", "adversarial".
The same file is in 2 other repositories
tdimino/claude-code-minoan/skills/core-development/test-harness-auditor Skill
41★ repoAudit a repo's test, lint, type-check, static analysis, build, and debug infrastructure for AI coding agents. Generate scored reports and optimized configs for the lint-on-write hook. Triggers on audit tests, test harness, lint setup, check test infrastructure, entering a new repo.
tdimino/claude-code-minoan/skills/design-media/design-critique Skill
41★ repoEvaluate design from a UX perspective with Nielsen's heuristics scoring, anti-pattern detection, persona-based testing, and actionable feedback. Report-only. Triggers on critique, UX review, design feedback, how does this look, evaluate the design, component review.
Uxcel-Lab/product-skills/pm/deliverables/product-spec Skill
41★ repoWrite a product requirements document (PRD) or spec anchored to a validated problem, with measurable requirements and surfaced risks — or review an existing one. Trigger when asked to write a PRD, product spec, user stories, technical requirements, or to review/critique an existing spec document.
Uxcel-Lab/product-skills/pm/deliverables/roadmap Skill
41★ repoCreate or critique a product roadmap — outcome-oriented, theme-based, confidence-aware (Now-Next-Later) roadmaps tied to strategy, instead of dated feature lists. Gates format and detail by audience and planning horizon. Trigger when the user asks to build, write, review, or restructure a product roadmap, quarterly/annual plan, Now-Next-Later view, or roadmap presentation.