Review & quality
19,016 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
ForeverAProgrammer/claude-devflow/skills/create-pr-github-git Skill
0★ repoCreate a GitHub pull request from the current branch, deriving the title and description from the branch's git history.
ForeverAProgrammer/claude-devflow/skills/create-pr-github Skill
0★ repoCreate a GitHub pull request from the current branch using a description provided by the user.
ForeverAProgrammer/claude-devflow/skills/fix-issue-github-auto Skill
0★ repoFully automate resolving a GitHub issue: create a linked branch, apply code changes, commit, open a PR, and resolve any conflicts.
ForeverAProgrammer/claude-devflow/skills/jira-ticket-git Skill
0★ repoTurn the current git changes into a well-formed Jira/Linear-style ticket with acceptance criteria.
ForeverAProgrammer/claude-devflow/skills/pr Skill
0★ repoGenerate a pull request title and description based on the summary or diff below. Use when the user wants to write a PR description.
ForeverAProgrammer/claude-devflow/skills/resolve-conflicts Skill
0★ repoRebase the current branch onto the target branch to resolve PR conflicts.
ForeverAProgrammer/claude-devflow/skills/review Skill
0★ repoReview code and provide structured feedback. Use when the user wants to review their changes, a file, or pasted code.
ForeverAProgrammer/claude-devflow/skills/standup-git Skill
0★ repoGenerate a standup update from yesterday's git commits. No input needed.
DerivativeLabs/skills/.claude/skills/decision-review Skill
0★ repoAudit decisions for judgment quality, compliance bias, and manipulation vulnerability. Inspired by Anthropic's Project Vend Phase 2 finding that helpfulness training creates exploitable attack surface.
bright-room/br-claude-plugins/plugins/dev-workflow/skills/review Skill
no license0★ repoPR 番号を指定してコードレビューを実施し、インラインコメントとして投稿する。コードベース全体のレビューも可能(ローカル出力)。
crustacean-dev/knowledge-skills/skills/clarify Skill
0★ repoAdversarial spec reviewer — runs 10 systematic checks against an existing .knowledge/features/<feature>/spec.md to find gaps, vague criteria, missing edge cases, constitution violations, scope leaks, and implementation details that leaked into the spec. Every FAIL comes with a concrete example and a fix proposal. ALWAYS use this skill when the user wants to validate, audit, challenge, stress-test, or review a feature spec before planning or implementation — whether they say "clarify", "clarify <feature>", "review the spec", "is the spec complete", "what's missing", "find gaps", "challenge the spec", "stress test", "audit the spec", "are we missing anything", "check the spec", or any variant asking about spec quality, completeness, or readiness. Also trigger when the user is about to move from spec to plan and wants confidence the spec is tight. This skill reads and updates spec.md ONLY — it does not create new specs (use /spec), produce plans or architecture (use /plan), break down tasks (use /tasks), write code (use /implement), or review implementation code (use /review, /challenge).
crustacean-dev/knowledge-skills/skills/implement Skill
0★ repoWrite code and tests for a single task from .knowledge/features/<feature>/tasks.md. Picks the next TODO task (or a specific TASK-N), reads its acceptance criteria, referenced user stories, plan, architecture, and conventions, then writes exactly the code and tests needed to satisfy the ACs. Updates task status to DONE when complete. Use this skill whenever the user wants to write code for a planned task — trigger phrases include "implement", "implement auth", "implement TASK-3", "build this", "code this task", "start building", "next task", "what's next to implement", "work on TASK-5", "implement the next task", or any variant asking to write code against a task breakdown. Also trigger for casual phrasing like "ok build it", "let's code the first task", "I finished planning, now write the code", or "pick up where we left off". This skill handles ONE task per invocation — it does NOT write specs (/spec), create plans (/plan), break down tasks (/tasks), review code (/review), challenge implementations (/challenge), do general refactoring, or add tests to existing code outside a task context. If the user asks to "add tests" or "refactor" without referencing a task from tasks.md, this skill should NOT trigger.
crustacean-dev/knowledge-skills/skills/review Skill
0★ repoCode review — check if implementation matches specs, conventions, and constitution. Use this skill ANY time the user wants to verify, check, audit, or review code that has been written. This includes explicit requests like "review", "review TASK-3", "review auth", "code review" AND indirect requests like "check my work", "check the code", "does this match the spec", "does this follow conventions", "is this clean", "sanity check", "look over the code", "did I miss anything", "any violations", "is the implementation correct", "can we merge this", "is TASK-N done", "are there constitution violations", "check test coverage". ALSO trigger after /implement completes to suggest a review. ALSO trigger when user mentions checking code against knowledge files, acceptance criteria, or convention conformity. This skill reads code and knowledge files, then produces a structured ✅/⚠️/❌ report with file:line references — it never modifies code. Do NOT trigger for spec review (/clarify), writing code (/implement), planning (/plan), task breakdown (/tasks), stress testing (/challenge), refactoring without task context, or adding tests outside a task.
agenticdevops/devops-execution-engine/skills/git-workflow Skill
no license0★ repoGit workflows, branching strategies, and DevOps practices
mickzijdel/airtable-utils/skills/airtable-standards-check Skill
0★ repoCheck an Airtable schema JSON file against the BlueDot Impact Airtable Standards. Use when the user wants to validate their Airtable base structure, find naming convention violations, or produce a standards compliance report.
JLugagne/claude-skills/dev/agile-team-v2/skills/tdd-pattern Skill
0★ repoUse this skill whenever you are running as the `red` or `green` agent on an agile-team-v2 task. Covers the discipline-based spec isolation between red and green (no private TASK*.md files exist; the only handoff is committed code/tests), the in-scope vs out-of-scope rules of the red/green pattern (applies to standard and architectural complexity features only — mechanical maintenance is a mono-agent task), the mono-assistant safeguard when one Claude instance must wear both hats sequentially (commit red first, fresh session before reading green-side material — `check.sh` audits this at sprint review), and the marker-based task lookup procedure (grep for `TODO(impl-<slug>, ac-<NNN>)` to locate the scaffolded body and its sibling test file). Loaded only by `red` and `green`. Other agents (architect, PM, sprint-planner, e2e-tester, reviewer, bug-detective) operate outside the live red/green isolation flow and do not need these rules.
JLugagne/claude-skills/dev/agile-team/skills/agile-project Skill
0★ repoUse this skill whenever you are working on a Go project following this agile workflow — features in .features/, sprints in .sprints/, ADRs in .adrs/, global architecture in .architecture/, per-feature ARCHITECTURE.md written by the Architect, tasks under .features/<slug>/tasks/ with scaffolding-first plus red/green triples (TASK.md shared + TASK-red.md + TASK-green.md), spec isolation between paired teammates, dispute arbitration by the sprint-planner, complexity-based agent assignment (scaffolder, red-opus/sonnet/haiku, green-opus/sonnet/haiku, e2e-tester, reviewer), PM and Architect roles for feature definition, and retro-driven sub-sprints for private-helper test coverage. Triggers: mention of sprint planning, feature breakdown, TASK.md / TASK-red.md / TASK-green.md / SCAFFOLD.md, SPRINT.md, REVIEW.md, RETRO.md, Definition of Ready, Definition of Done, blockers, questions, ADRs with revisit flag, dispute files in .disputes/, any of the sprint-planner/product-manager/architect/scaffolder/red-*/green-*/reviewer agents, agent teams, the scaffor tool, or any repository containing .features/ / .sprints/ / .adrs/ / .architecture/ directories. Also triggers for any Go file editing in such a project — all .go reads and edits must go through go-surgeon, never generic Edit/Write/Read. Consult this skill before planning a sprint, before starting any task, before writing a commit, before creating an ADR, before responding to a dispute, or whenever you need to know what artifact goes where.
JLugagne/claude-skills/dev/go-hexagonal/skills/go-reviewer Skill
0★ repoOrchestrates dual code review with consensus — two Sonnet reviewers (architecture+performance and security+data) run in parallel, Opus arbitrates only when they diverge. Creates fix/test task files.
miguel-herrero-systems/hrevn-surface-anthropic/.claude/skills/hrevn-verify-bundle Skill
0★ repoHREVN for Claude Code: verifiable workflow state via MCP, skills, and a local runner.
mvdmakesthings/skills/plugins/delivery/skills/qa Skill
no license0★ repoSoftware QA skill — validates that current code changes satisfy the linked Linear issue. Fetches the issue, reads acceptance criteria, executes the ticket's attached test plan when one exists (produced by /plan-qa), runs every test layer it finds, and uses Playwright to visually verify the UI against any design attachments on the ticket. Use whenever the user wants to QA a feature, verify a fix, check that code matches a ticket's acceptance criteria, run a pre-merge review, or confirm the UI looks right against a design. Trigger on — "/qa", "run QA", "QA this", "verify the feature", "does this match the ticket", "check AC", "acceptance criteria check", "visual QA", "playwright verify", "does this pass QA".
manabuozato/claude-academic-writing-ja/skills/literature-review Skill
0★ repoJapanese academic writing support skills and prompts for Claude - 日本語学術執筆支援ツールキット
manabuozato/claude-academic-writing-ja/skills/peer-review-prep Skill
0★ repoJapanese academic writing support skills and prompts for Claude - 日本語学術執筆支援ツールキット
khujta/gabe-suite/skills/gabe-commit Skill
no license0★ repoCommit quality gate — deterministic checks (incl. the >800-line size-budget check), interactive triage, defer/accept/fix per finding, evidence-triggered simplify pass, and retroactive docs-audit mode for accumulated documentation drift. Usage: /gabe-commit [commit message] | /gabe-commit docs-audit
khujta/gabe-suite/skills/gabe-review Skill
no license0★ repoCode review with risk pricing, confidence scoring, interactive triage, and deferred item tracking. Also checks plan alignment (is this diff on-scope?), detects stale verified topics, and proposes DECISIONS.md entries for architectural changes. Surfaces the cost of NOT fixing each finding. Usage: /gabe-review [target] or /gabe-review deferred
ortus-boxlang/skills/boxlang-developer/code-reviewer Skill
no license0★ repoUse this skill when reviewing BoxLang code for quality, correctness, security vulnerabilities, performance issues, style violations, or when providing structured code review feedback following BoxLang best practices and security guidelines.
pszypowicz/claude-skills/plugins/worktrees/skills/start-project Skill
0★ repoBatch-provision git worktrees for a set of planned tasks across one or more repos under ~/Developer/. Use whenever the user names a set of tasks or branches to work on, wants to "start a project", "kick off" or "begin" planned work, "set up worktrees for X/Y/Z", or otherwise wants isolated working copies to land commits against before a single-repo edit makes sense. Trigger even if the user doesn't use the exact word "worktree" - if they're framing upcoming work as a list of {repo, branch} pairs, this skill handles it. Do NOT trigger for inventory questions ("what worktrees do I have?" - that's `/worktree-status`), single-branch lookups ("where's the worktree for X?" - `/worktree-for`), or teardown ("clean up my worktrees" - `/worktree-cleanup`).
rvanbaalen/skills/plugins/cofounder/skills/check-in Skill
no license0★ repoRun a cadence-based check-in session (daily, weekly, monthly, or quarterly). Use when the user wants to check in, or when the cofounder agent detects a check-in session. Drives the conversation — don't wait for the user to set the agenda.
rvanbaalen/skills/plugins/cofounder/skills/review Skill
no license0★ repoReview current state, progress, and priorities. Use when the user wants an overview of where things stand, or when the cofounder agent needs to assess progress. Surfaces insights and flags issues proactively.
rvanbaalen/skills/plugins/commit/skills/commit Skill
no license0★ repoCommit changes using micro commits with conventional commit messages. Analyzes git diff, groups related files, and proposes commits for approval. Supports interactive and non-interactive (background) modes. Use when the user wants to commit their changes.
rvanbaalen/skills/plugins/cpr/skills/cpr Skill
no license0★ repoUser-invokable only via /cpr. Commit, Push, and Release in one command. Commits all changes as non-interactive micro-commits (conventional commits), pushes to remote, runs a review-and-fix loop on the pushed changes, then handles the full release-please cycle: waits for the PR, merges it, and monitors the release workflow to completion. Do NOT auto-trigger this skill.
rvanbaalen/skills/plugins/design-principles/skills/design-principles Skill
no license0★ repoTrigger this skill whenever the user wants to design, review, critique, or improve a user interface, screen, flow, component, or product experience — including mockups, prototypes, web/app UI, and design feedback. Use it when the user says things like "review this design", "is this good UX", "help me design a screen/flow", "what's wrong with this interface", or asks for design direction. Do NOT trigger for purely backend, data, or non-UI work.
rvanbaalen/skills/plugins/pm/skills/review Skill
no license0★ repoOn-demand progress analysis. Timeline health, estimation accuracy, blocker history, anti-pattern report, overrule analysis, and recommendations.
JasonLo/skill-sommelier/maintainer-skills/ssm-skill-validate Skill
0★ repoValidate all skills in this repo for frontmatter correctness, naming conventions, and structural rules. Use when adding a new skill, before releases, or in CI. Triggers on "validate skills", "lint skills", "check skills", "audit frontmatter", "skill validation", "pre-release check".
lokesh-go/llm-wiki/.claude/skills/lint Skill
0★ repoA personal, compounding tech knowledge base maintained by an LLM
payals/ai-skills-engine/dot_cursor/skills/development/code-review-checklist Skill
0★ repoComprehensive checklist for conducting thorough code reviews covering functionality, security, performance, and maintainability
The same file is in 4 other repositories
payals/ai-skills-engine/dot_cursor/skills/development/code-reviewer Skill
0★ repoComprehensive code review skill for TypeScript, JavaScript, Python, Swift, Kotlin, Go. Includes automated code analysis, best practice checking, security scanning, and review checklist generation. Use when reviewing pull requests, providing code feedback, identifying issues, or ensuring code quality standards.
The same file is in 4 other repositories
payals/ai-skills-engine/dot_cursor/skills/development/development/code-review-checklist Skill
0★ repoComprehensive checklist for conducting thorough code reviews covering functionality, security, performance, and maintainability
The same file is in 4 other repositories
payals/ai-skills-engine/dot_cursor/skills/development/development/code-reviewer Skill
0★ repoComprehensive code review skill for TypeScript, JavaScript, Python, Swift, Kotlin, Go. Includes automated code analysis, best practice checking, security scanning, and review checklist generation. Use when reviewing pull requests, providing code feedback, identifying issues, or ensuring code quality standards.
The same file is in 4 other repositories
payals/ai-skills-engine/dot_cursor/skills/development/git-commit Skill
0★ repoExecute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
payals/ai-skills-engine/dot_cursor/skills/development/using-git-worktrees Skill
0★ repoUse when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
The same file is in 5 other repositories
Verification before completion
payals/ai-skills-engine/dot_cursor/skills/development/verification-before-completion Skill
0★ repoUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
The same file is in 40 other repositories
payals/ai-skills-engine/dot_cursor/skills/workflow-automation/github-workflow-automation Skill
0★ repoAutomate GitHub workflows with AI assistance. Includes PR reviews, issue triage, CI/CD integration, and Git operations. Use when automating GitHub workflows, setting up PR review automation, creating GitHub Actions, or triaging issues.
The same file is in 3 other repositories
payals/ai-skills-engine/dot_cursor/skills/workflow-automation/n8n/n8n-validation-expert Skill
0★ repoInterpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, or the validation loop process.
The same file is in 1 other repository
Texarkanine/a16n/packages/cli/test/integration/fixtures/cursor-command-to-claude/to-claude/.claude/skills/review Skill
no license0★ repoInvoke with /review
Texarkanine/a16n/packages/plugin-claude/test/fixtures/claude-skills-complex/from-claude/.claude/skills/secure-deploy Skill
no license0★ repoSecure deployment workflow with pre-commit verification
arndvs/ctrlshft/skills/code-review Skill
0★ repoFocused review of staged or recent changes to find edge cases, logic errors, and integration risks before merging. Use when asked to 'do a code review', 'review my changes', 'review this PR', 'check my diff', 'review staged changes', or 'pre-merge review'.
arndvs/ctrlshft/skills/codebase-audit Skill
0★ repoRuthless codebase audit reporting only real problems. Use when asked to 'audit', 'code audit', 'codebase audit', 'review code', 'find bugs', or 'code review'.
arndvs/ctrlshft/skills/grill-me Skill
0★ repoInterview the user relentlessly about a plan or design until reaching shared understanding. Use when asked to 'grill me', 'interview me', 'ask me questions about this', or before writing a PRD to flesh out vague ideas.
arndvs/ctrlshft/skills/grill-with-docs Skill
0★ repoUse when stress-testing a plan against the project's domain model — grills the design, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise.
arndvs/ctrlshft/skills/press1-check Skill
0★ repoUse when Claude Code sessions had many manual approval ("press 1") prompts or when auditing hook permissions; identifies which Bash commands required approval.
arndvs/ctrlshft/skills/review-pr-copilot Skill
0★ repoAddress GitHub Copilot review comments on the active PR by triaging into confidence tiers, fixing in atomic commits, resolving threads, and re-requesting review.
dzivkovi/claude-skills/skills/slop-check Skill
no license0★ repoFresh-eyes logic-and-slop review of prose and copy. Catches writing that reads like fine English but is logically, mathematically, or definitionally wrong, plus internal contradictions, off-brand drift, and AI tells. NOT a fact-checker - run it as a logic gate AFTER the facts are verified, before publishing. Triggers: 'slop check', 'slop detector', 'logic and slop review', 'check this for AI slop', 'fresh-eyes review', 'is this writing logically sound', 'review my copy before publishing', 'catch contradictions and AI tells', 'gate A'. Works on one file or many (fans out one reviewer per file). Report-only - it never edits.
voxpelli/claude-git/skills/tag-audit Skill
0★ repoTriage and prune accumulated git safety tags using sort-by-SHA grouping and a per-tag decision tree (duplicate / branch-ref / intermediate-waypoint). Read-only by default; deletes only after explicit user confirmation. Use when stacked-rebase or surgical-fix sessions have accumulated multiple safety tags across namespaces (safety/*, pre-*, post-*, backup-*, stack-*), when /stack-cascade's Step 2 collision check blocks reuse of an OP_ID, or when auditing inherited tag soup. Pairs with /stack-cascade as post-success aftercare. Covers scenarios like: 'clean up safety tags', 'too many backup tags', 'prune accumulated tags', 'tag audit', 'tag-audit', 'safety tag cleanup', 'rollback anchor cleanup', 'which tags can I delete', 'tag namespace collision', 'OP_ID already has tags'.
AayushMS/deploy-skills/skills/verify-deployment Skill
0★ repoUse this skill when the user asks to "verify my deployment", "check if everything is working", "test my deployment", "check if my services are up", "run health checks", or when invoked by deploy-project as the final step after CI/CD setup. Reads DEPLOYMENT_DOCS/DEPLOYED_ENV.md for service URLs, runs HTTP health checks on all services, uses agent-browser to visually verify the frontend loads, tests cross-service connectivity (frontend calls backend, backend connects to DB), and prints a pass/fail summary table. Retries Render backend endpoints up to 3 times due to free tier cold starts.
hereshecodes/secureskills/skills/input-validation Skill
0★ repoUse when processing user input, form data, file uploads, or query parameters
uts58/my-random-skills/git-cleanup Skill
no license0★ repoSafely analyzes and cleans up local git branches and worktrees by categorizing them as merged, squash-merged, superseded, or active work.
The same file is in 3 other repositories
uts58/my-random-skills/second-opinion Skill
no license0★ repoRuns external LLM code reviews (OpenAI Codex or Google Gemini CLI) on uncommitted changes, branch diffs, or specific commits. Use when the user asks for a second opinion, external review, codex review, gemini review, or mentions /second-opinion.
The same file is in 3 other repositories
csmoove530/clawd-market/test-e2e/sample-skill Skill
0★ repoAI-powered commit message generator that follows conventional commits and best practices
Phoebe-WD/claude-skills/smart-commit Skill
no license0★ repoAnaliza los cambios staged y unstaged para recomendar si crear un solo commit o varios commits separados, y genera mensajes de commit apropiados. Usar cuando el usuario pida sugerencias de commit, quiera hacer commit, o pregunte como organizar sus commits.
desmondc9/agent-skills/analyze-value Skill
0★ repo估算一家企业、股票或现金流型资产的内在价值(估值)。基于吴军《财商训练课》「企业估值」方法论——撇开成本与历史价格,只看未来能持续产生多少自由现金流(FCF)以及风险有多大,用风险调整后的折现现金流(DCF)给出估值。Use whenever the user wants to value or estimate the worth of a company, stock, or cash-flow-generating asset (商铺/商业地产/写字楼/收租物业), or asks '这家公司值多少钱', '帮我估值', '内在价值', 'DCF估值', 'how much is X worth', 'intrinsic value', 'is X overvalued/undervalued', '现金流折现', '该不该按这个价格买'. Also use to sanity-check a fixed-income/理财/票据/债券 promise against the risk-free deposit baseline. Do NOT use for live trading signals, technical chart reading, portfolio allocation, or self-occupied home pricing (那看供需,不用这套现金流方法).