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
TheWatcher01/skills/.claude/skills/git-cleanup Skill
0★ repoSafely analyzes and cleans up local git branches and worktrees by categorizing them as merged, squash-merged, superseded, or active work.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
TheWatcher01/skills/.claude/skills/mastra-workflows Skill
0★ repoBuild DAG workflows with Mastra 1.x (@mastra/core/workflows). Use when implementing workflow orchestration with directed acyclic graphs, step chaining, parallel execution, branching, loops, error handling, suspend/resume, or streaming. Triggers on tasks involving createStep, createWorkflow, .then(), .parallel(), .branch(), .foreach(), .dountil(), .dowhile(), .map(), workflow state management, or Mastra step composition.
TheWatcher01/skills/.claude/skills/second-opinion Skill
0★ 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
TheWatcher01/skills/.claude/skills/skill-improver Skill
0★ repoIteratively reviews and fixes Claude Code skill quality issues until they meet standards. Runs automated fix-review cycles using the skill-reviewer agent. Use to fix skill quality issues, improve skill descriptions, run automated skill review loops, or iteratively refine a skill. Triggers on 'fix my skill', 'improve skill quality', 'skill improvement loop'. NOT for one-time reviews—use /skill-reviewer directly.
The same file is in 1 other repository
TheWatcher01/skills/.claude/skills/smart-commit Skill
0★ repoAutomates intelligent Git commits by analyzing unstaged/staged changes, grouping files by logical development concern, and committing sequentially with descriptive Conventional Commit messages. Includes pre-commit security audit protecting against credential leaks and large binary commits. Use when the user says "commit", "smart commit", "save changes", "push", "git commit", or similar.
adryanmoldokkr32-pixel/awesome-claude-skills/changelog-generator Skill
no license0★ repoAutomatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
The same file is in 14 other repositories
Google address validation automation
adryanmoldokkr32-pixel/awesome-claude-skills/composio-skills/google-address-validation-automation Skill
no license0★ repoAutomate Google Address Validation tasks via Rube MCP (Composio). Always search tools first for current schemas.
The same file is in 5 other repositories
adryanmoldokkr32-pixel/awesome-claude-skills/composio-skills/postgrid-verify-automation Skill
no license0★ repoAutomate Postgrid Verify tasks via Rube MCP (Composio). Always search tools first for current schemas.
The same file is in 5 other repositories
shenxianpeng/skills/skills/github-review Skill
no license0★ repoPersonal AI artifacts, agent skills, and reusable workflows
pessini/aria/backend/agents/n8n_agent/skills/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 3 other repositories
mattharbord/kairo-agents/skills/kairo-risk-review Skill
0★ repoRun a focused Kairo risk review for an in-progress or release-candidate tool and produce actionable warnings, required evidence requests, and non-blocking go/no-go guidance. Use when the PM asks for a risk pass, write-path safety check, known-gap review, release-readiness review, or conflict check between speed and reliability. Do not use as a formal compliance or certification audit.
Finishing a development branch
northseadl/skillwisp/skills/@obra/finishing-a-development-branch Skill
0★ repoUse when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
The same file is in 17 other repositories
northseadl/skillwisp/skills/@obra/receiving-code-review Skill
0★ repoUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
The same file is in 28 other repositories
northseadl/skillwisp/skills/@obra/requesting-code-review Skill
0★ repoUse when completing tasks, implementing major features, or before merging to verify work meets requirements
The same file is in 11 other repositories
northseadl/skillwisp/skills/@obra/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 12 other repositories
Verification before completion
northseadl/skillwisp/skills/@obra/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
northseadl/skillwisp/skills/@openai/yeet Skill
0★ repoUse only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).
The same file is in 5 other repositories
iceflower/agent-skills/chaos-engineering Skill
0★ repoChaos engineering principles and practices for building resilient systems. Covers tools such as Chaos Monkey, Gremlin, and Litmus for fault injection, blast radius analysis, steady state hypothesis definition, experiment design, failure mode validation, and game day planning. Use when designing reliability testing, running fault injection experiments, defining steady state hypotheses, or planning chaos game days to verify system resilience.
iceflower/agent-skills/code-review Skill
0★ repoCode review checklist, comment guidelines, and PR review best practices. Covers PR review workflows, code suggestions, nitpick vs blocking review classification, LGTM criteria, review checklist (correctness, security, performance, readability), and constructive feedback patterns. Use when reviewing pull requests, providing code suggestions, or establishing a team code review process and review comment conventions.
iceflower/agent-skills/git-workflow Skill
0★ repoGit commit conventions, branch strategy, and collaboration workflow rules. Covers conventional commits, commit message formatting, squash merge, rebase, interactive rebase, branch naming conventions, merge conflict resolution, cherry-pick, git bisect, and pull request workflows. Use when committing code, managing branches, resolving merge conflicts, or defining a team Git branching strategy.
prof-ramos/skills/autoreview-agnostic/opencode/skills/autoreview Skill
0★ repoCloseout structured code review. Use after non-trivial edits before commit/ship, or to review a local branch/PR/commit. The reviewer is read-only, returns a JSON findings bundle against a fixed schema, verifies every finding against real code, and rejects speculative/broad/unrealistic findings.
1natsu-vacation/agent-skills/skills/1natsu-auto-resolve-conflicts Skill
0★ repoGitのコンフリクト解消をAI単独で完全自動化する自走スキル。merge / rebase / cherry-pick / stash pop で衝突した時、履歴と変更意図を読み、両側の機能を壊さず統合し、検証を自動実行して --continue まで完了する。すでに衝突している場合に加え、stale な PR(mergeable:false)で未コンフリクトの状態からでも base 追従で衝突を発生させて解消する。merge は解消履歴を追えるよう2段コミットで残す。「自動でコンフリクト解消」「コンフリクト解消お任せ」「auto resolve conflicts」「stale な PR を base 追従して解消」「mergeable false を直して」等、AI主導の自動化・自走を示唆した時に使う。デグレ防止が最優先で、安全に解消できなければ `1natsu-pair-resolve-conflicts` へ引き継ぐ。**1ファイルずつ承認しながら解消したい場合は本スキルでなく `1natsu-pair-resolve-conflicts` を使う。**
The same file is in 1 other repository
1natsu-vacation/agent-skills/skills/1natsu-commit Skill
0★ repogitコミットの作成、コミットメッセージの記述、変更のステージング時に使用する。Conventional Commitsやアトミックコミット、明確なコミットメッセージのベストプラクティスを提供する。
The same file is in 1 other repository
1natsu-vacation/agent-skills/skills/1natsu-conventional-commits Skill
0★ repoConventional Commitsのフォーマット、タイプ、スコープ、破壊的変更、本文・フッターの書き方が必要なときに自動的に参照される内部リファレンス。コミットメッセージやPRタイトルの作成時に他のスキルから利用される。
The same file is in 1 other repository
1natsu-vacation/agent-skills/skills/1natsu-git-analysis Skill
0★ repogitリポジトリの変更、ブランチの差分、コミット履歴を分析する。ブランチ分析、変更比較、コミット履歴の確認、PR作成の準備、コード変更のレビュー時に使用する。
The same file is in 1 other repository
1natsu-vacation/agent-skills/skills/1natsu-pair-resolve-conflicts Skill
0★ repoGitのコンフリクト解消を人間とペアで行う協調スキル。merge / rebase / cherry-pick / stash pop で衝突した時、コミット履歴と変更の経緯を分析し、「なぜこう変わったか」を解説しながら1つずつ人間の承認を得て解消する。マーカーを消すだけでなく、両側が実装した機能を壊さない統合を前提に解消案を出す。すでに衝突している場合だけでなく、stale な PR(mergeable:false)で未コンフリクトの状態からでも、承認のうえ base 追従でコンフリクトを発生させて始められる。ユーザーが「コンフリクト解消しよう」「一緒にコンフリクト直そう」「conflict resolve」「stale な PR を base 追従して一緒に解消」等、またはAIがコンフリクト検知時に使う。自動で一括解消してコミットせず、必ず人間と対話しながら進めること。
The same file is in 1 other repository
1natsu-vacation/agent-skills/skills/1natsu-pr-review-handler Skill
0★ repoGitHubのPRレビューコメントを自律的に読んで判断・コード修正・返信・サマリー投稿を行う。「レビューを対応して」「PRの指摘を直して」「レビューコメントを処理して」など、PRレビュー対応のタスクで使用する。人間レビュワーとAIレビューツール(Devin, Copilot, CodeRabbit, Gemini等)を区別せず処理する。
The same file is in 1 other repository
gdm257/cc-plugins/plugins/cc-sdd-skills/skills/kiro-review Skill
no license0★ repoReview a task implementation against approved specs, task boundaries, and verification evidence. Use after an implementer finishes a task, after remediation, or before accepting a task as complete.
The same file is in 1 other repository
gdm257/cc-plugins/plugins/cc-sdd-skills/skills/kiro-verify-completion Skill
no license0★ repoVerify completion and success claims with fresh evidence. Use before claiming a task is complete, a fix works, tests pass, or a feature is ready for GO.
The same file is in 1 other repository
gdm257/cc-plugins/plugins/code-review-graph/skills/review-changes Skill
no license0★ repoPerform a structured code review using change detection and impact
gdm257/cc-plugins/plugins/openspec-claude-skills/skills/openspec-verify-change Skill
no license0★ repoVerify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
gdm257/cc-plugins/plugins/openspec-opencode-skills/skills/openspec-verify-change Skill
no license0★ repoVerify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
gdm257/cc-plugins/plugins/trellis/skills/trellis-check Skill
no license0★ repoComprehensive quality verification: spec compliance, lint, type-check, tests, cross-layer data flow, code reuse, and consistency checks. Use when code is written and needs quality verification, before committing changes, or to catch context drift during long sessions.
gdm257/cc-plugins/plugins/trellis/skills/trellis-finish-work Skill
no license0★ repoWrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session.
badrusiddique/enggenie-skill/skills/dev-commit Skill
0★ repoUse when creating commit messages - analyzes git diffs, proposes conventional commit messages with appropriate type, and waits for user approval before committing
badrusiddique/enggenie-skill/skills/qa-verify Skill
0★ repoUse before claiming any work is complete - evidence-based verification that tests pass, builds succeed, and requirements are met
badrusiddique/enggenie-skill/skills/review-code Skill
0★ repoUse when requesting or receiving code review - dispatches reviewer subagent or processes human PR feedback with technical evaluation
badrusiddique/enggenie-skill/skills/review-design Skill
0★ repoUse when reviewing frontend implementation against design specs - design system compliance, responsive behavior, accessibility audit
jmlrt/skills/plan-with-review Skill
0★ repoRuns a two-pass planning workflow (draft → Plan QA → final plan + QA notes). Use when the user asks to create a plan, is in plan mode, requests an implementation plan, asks to "review this plan" for issues/missing parts/improvements/clarifications, or mentions planning, missing parts, or clarifications.
jmlrt/skills/pull-request Skill
0★ repoCreate and update pull requests as an author. Use when you're ready to propose changes: creates PRs with comprehensive file validation, tests, commit messages, and PR descriptions. Also guides addressing reviewer feedback through iterative fixes and comment resolution.
jmlrt/skills/python-development Skill
0★ repoGuide Python development with greenfield defaults and brownfield flexibility. Apply when writing, maintaining, or reviewing Python code to ensure consistency with modern tooling (uv, ruff, ty, pytest, pre-commit) and patterns (CLI separation, type safety, error handling).
jmlrt/skills/review-claude-config Skill
0★ repoAudit the ecosystem of Claude config files — global CLAUDE.md, per-repo CLAUDE.md and CLAUDE.local.md, memory files, and skills — for redundancy, inconsistency, outdated facts, and misplaced content. Use when asked to "review CLAUDE.md", "audit claude config", "clean up claude files", or "check what should be global vs local".
jmlrt/skills/review-claude-settings Skill
0★ repoAudit Claude Code settings.json files — global (~/.claude/settings.json) and per-repo (.claude/settings.json, .claude/settings.local.json) — for permission consolidation, redundancy, and security risks. Use when asked to "review settings.json", "audit claude settings", "clean up permissions", "check what should be global vs repo", or "security review of settings".
jmlrt/skills/review-pull-request Skill
0★ repoReview pull requests as a reviewer. Use when validating a PR before merge: performs independent code review, runs tests, validates manual testing. Handles single PRs with detailed analysis or multiple PRs in parallel batch mode with summary triage table.
coderbaba0/ai_agents_skills/git-guardrails-claude-code Skill
0★ repoSet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
The same file is in 18 other repositories
coderbaba0/ai_agents_skills/grill-me Skill
0★ 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 1 other repository
coderbaba0/ai_agents_skills/setup-pre-commit Skill
0★ repoSet up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
The same file is in 19 other repositories
Finishing a development branch
bensonmaxai/minis-coding-success-skills/skills/finishing-a-development-branch Skill
no license0★ repoUse when implementation or debugging work is mostly done and you need to safely finish the branch. Optimized for Minis on iOS: verify tests, inspect diffs, remove debug residue, check scope creep, summarize changes, and prepare a clean commit or handoff. Helps raise coding success rate by preventing rushed, messy, or incomplete finishes.
bensonmaxai/minis-coding-success-skills/skills/release-readiness Skill
no license0★ repoUse when implementation is mostly complete and you need to decide whether a branch, build, tool, or small app is actually ready to release, ship, or hand off. Optimized for Minis on iOS: verify scope, validation coverage, versioning/release notes, dependency/config surprises, known risks, and final go/no-go criteria before release.
bensonmaxai/minis-coding-success-skills/skills/using-git-worktrees Skill
no license0★ repoUse when working on multiple bugs, features, or experiments in the same repository and you want clean task isolation. Optimized for Minis on iOS: create isolated git worktrees safely, avoid branch contamination, keep experiments separate, and reduce messy context switching between tasks.
jovd83/Cypress-skill/coverage_plan/review Skill
0★ repoCoverage-plan review skill for Cypress work. Use when Codex needs to present a proposed coverage plan, surface assumptions and tradeoffs, collect user feedback, and secure explicit approval before large implementation or documentation work.
auralshin/agent-skills/skills/defi-transaction-builder Skill
0★ repoUse this skill to build and sanity-check unsigned DeFi transaction payloads (to/data/value/chain) for swaps, lending, staking, and bridging.
rulebased-io/claude-plugin/packages/second-brain/skills/reference-check Skill
0★ repoScan all markdown files for broken wikilinks and path references, suggest and execute fixes. Use after file moves, renames, or deletions.
rulebased-io/claude-plugin/packages/second-brain/skills/review Skill
0★ repoResurface and review old notes using spaced repetition or random selection. Use when the user wants to revisit their knowledge, process inbox items, or maintain note quality.
kpatryk/skills/skills/git-cliff Skill
0★ repoExpert guide for git-cliff, a highly customizable changelog generator from git history. Invoke this skill whenever the user wants to generate, update, or customize a CHANGELOG.md file; auto-bump semantic versions; configure cliff.toml; write Tera templates for changelogs; work with conventional commits for changelog purposes; set up git-cliff in CI/CD pipelines; filter commits by path for monorepos; integrate GitHub/GitLab remote metadata into changelogs; debug changelog output; or run any git-cliff CLI command. Use even when the user just says "generate changelog", "update my CHANGELOG", "prep release notes", or "bump my version" — any changelog or release-notes workflow likely benefits from this skill.
kpatryk/skills/skills/pyrefly Skill
0★ repoExpert guidance for Pyrefly — the fast Python type checker and language server by Meta, written in Rust. Use this skill whenever the user mentions pyrefly, wants to type-check Python code, asks about setting up a type checker, wants to configure type checking in pyproject.toml or pyrefly.toml, needs to suppress type errors, wants to migrate from mypy or pyright to a modern alternative, wants to integrate type checking into CI/GitHub Actions, or needs editor/IDE type-checking setup. Also trigger when users ask about Python type annotations, flow types, gradual typing adoption, type inference, or Python LSP setup — pyrefly is the fast modern recommendation worth knowing about.
kpatryk/skills/skills/ruff Skill
0★ repoExpert guidance for ruff — the extremely fast Python linter and formatter written in Rust. Use this skill whenever the user mentions ruff, wants to lint or format Python code, asks about pyproject.toml linting config, wants to migrate from flake8/black/isort/pylint to a single tool, wants to set up pre-commit hooks for Python quality, asks about fixing unused imports or style violations, or needs to configure or debug ruff rules. Also trigger when the user asks about Python code quality tooling in general, since ruff is almost always the right recommendation.
kpatryk/skills/skills/trufflehog Skill
0★ repoComprehensive guide for using TruffleHog (open-source) to detect, classify, and verify leaked secrets and credentials. Use this skill whenever the user wants to scan for secrets, credentials, API keys, tokens, or passwords in git repos, GitHub/GitLab orgs, Docker images, S3/GCS buckets, filesystems, CI systems, or any other data source. Also invoke this skill when the user asks about setting up pre-commit hooks for secret detection, integrating secret scanning into CI/CD pipelines (GitHub Actions, GitLab CI, etc.), reducing false positives from secret scanners, writing custom regex detectors, understanding TruffleHog's verification model, or auditing repositories for credential leaks. Trigger on any mention of: trufflehog, secret scanning, credential detection, leaked keys, API key detection, pre-commit secret hooks, or scanning git history for secrets.
kpatryk/skills/skills/ty Skill
0★ repoExpert guidance for ty — the extremely fast Python type checker written in Rust by Astral (makers of ruff and uv). Currently in beta. Use this skill whenever the user mentions ty, wants to type-check Python code, asks about Python type checking, wants to migrate from mypy or Pyright, needs to configure type checking rules, wants to integrate a type checker into their project, asks about type checking performance, or needs help with type checking errors and diagnostics. Also trigger when the user asks about fast Python tooling or Astral's tools in general.
kpatryk/skills/skills/worktrunk Skill
0★ repoExpert guide for Worktrunk (the `wt` CLI), a git worktree manager designed for running AI agents in parallel. Invoke this skill whenever a user mentions worktrunk or wt commands (wt switch, wt list, wt merge, wt remove, wt hook, wt step, wt config), asks about git worktrees for AI agents or parallel development, wants to configure LLM commit messages, set up worktree lifecycle hooks, run multiple Claude or Codex agents simultaneously, use wt list CI status, configure the interactive picker, copy build caches between worktrees, or troubleshoot shell integration. Also use for questions about .config/wt.toml, ~/.config/worktrunk/config.toml, hash_port, sanitize filters, wt merge squash/rebase workflow, wt step copy-ignored, wt step prune, agent handoffs, dev servers per worktree, bare repository layouts, or any other worktrunk topic.