Review & quality
19,178 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
dolutech/dolu-agents-skills/skills/requesting-code-review Skill
6★ repoUse when completing tasks, implementing major features, or before merging to verify work meets requirements
The same file is in 11 other repositories
Verification before completion
dolutech/dolu-agents-skills/skills/verification-before-completion Skill
6★ 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
mikeng-io/agent-skills/skills/deep-review Skill
no license6★ repoMulti-agent quality improvement review with constructive feedback. Provides suggestions for best practices, code quality, alternatives, and performance optimization.
mikeng-io/agent-skills/skills/deep-verify Skill
no license6★ repoGeneric multi-agent verification framework with balanced expert analysis. Model-agnostic and domain-agnostic - verify any work through expert analysis.
chipfighter/coding-discipline/plugins/coding-discipline/skills/git-flow Skill
6★ repoUse when creating a branch, using worktrees for parallel work, committing, or wrapping up. Covers branch naming, conventional commits, short-lived branches, worktree isolation, and final merge/cleanup.
chipfighter/coding-discipline/plugins/coding-discipline/skills/verify-before-done Skill
6★ repoUse before claiming "done", "fixed", "tested", or "it runs", and before committing or opening a PR or MR—no task is exempt. Accept only evidence gathered after the last relevant change and just sufficient to prove the claim; do not over-verify small changes.
Finishing a development branch
pengzhangzhi/superpowers-ml/skills/finishing-a-development-branch Skill
6★ 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 10 other repositories
pengzhangzhi/superpowers-ml/skills/ml-result-review Skill
6★ repoUse when concluding an ML experiment - produce a sober conclusion that separates confirmed results from exploratory observations and states the highest verified rung.
pengzhangzhi/superpowers-ml/skills/receiving-code-review Skill
6★ 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
pengzhangzhi/superpowers-ml/skills/requesting-code-review Skill
6★ repoUse when completing tasks, implementing major features, or before merging to verify work meets requirements
The same file is in 11 other repositories
pengzhangzhi/superpowers-ml/skills/using-git-worktrees Skill
6★ repoUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
The same file is in 13 other repositories
Verification before completion
pengzhangzhi/superpowers-ml/skills/verification-before-completion Skill
6★ 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
martgueritainaccurate875/skills/skills/minimax-docx Skill
6★ repoProfessional DOCX document creation, editing, and formatting using OpenXML SDK (.NET). Three pipelines: (A) create new documents from scratch, (B) fill/edit content in existing documents, (C) apply template formatting with XSD validation gate-check. MUST use this skill whenever the user wants to produce, modify, or format a Word document — including when they say "write a report", "draft a proposal", "make a contract", "fill in this form", "reformat to match this template", or any task whose final output is a .docx file. Even if the user doesn't mention "docx" explicitly, if the task implies a printable/formal document, use this skill.
The same file is in 7 other repositories
martgueritainaccurate875/skills/skills/vision-analysis Skill
6★ repoAnalyze, describe, and extract information from images using the MiniMax vision MCP tool. Use when: user shares an image file path or URL (any message containing .jpg, .jpeg, .png, .gif, .webp, .bmp, or .svg file extension) or uses any of these words/phrases near an image: "analyze", "analyse", "describe", "explain", "understand", "look at", "review", "extract text", "OCR", "what is in", "what's in", "read this image", "see this image", "tell me about", "explain this", "interpret this", in connection with an image, screenshot, diagram, chart, mockup, wireframe, or photo. Also triggers for: UI mockup review, wireframe analysis, design critique, data extraction from charts, object detection, person/animal/activity identification. Triggers: any message with an image file extension (jpg, jpeg, png, gif, webp, bmp, svg), or any request to analyze/describ/understand/review/extract text from an image, screenshot, diagram, chart, photo, mockup, or wireframe.
The same file is in 3 other repositories
Finishing a development branch
smallocean43658/codex-superpowers/skills/finishing-a-development-branch Skill
6★ repoUse when implementation is complete, tests pass, or work is ready for merge, PR, cleanup, handoff, or branch integration
smallocean43658/codex-superpowers/skills/receiving-code-review Skill
6★ repoUse when receiving, evaluating, or responding to code review feedback, reviewer comments, requested changes, or technical criticism
smallocean43658/codex-superpowers/skills/requesting-code-review Skill
6★ repoUse when completing tasks, implementing major features, or before merging to verify work meets requirements
smallocean43658/codex-superpowers/skills/using-git-worktrees Skill
6★ repoUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
Verification before completion
smallocean43658/codex-superpowers/skills/verification-before-completion Skill
6★ repoUse when about to claim work is complete, fixed, passing, verified, ready for commit, ready for PR, or safe to ship
nijanthan-dev/taxmate-australia/runtime/skills/finance-review Skill
no license6★ repoUse when full-runtime TaxMate Australia finance review, GST candidate triage, or evidence-gap classification is needed.
Taxmate australia finance review
nijanthan-dev/taxmate-australia/wrappers/taxmate-australia-finance-review Skill
no license6★ repoUse when a local helper must route TaxMate Australia finance review into the full runtime.
Higangssh/yocto-agent-skills/skills/yocto-layer-review Skill
6★ repoReview Yocto/OpenEmbedded layer structure, layer.conf, BBFILE collections and patterns, LAYERSERIES_COMPAT, LAYERDEPENDS, BBFILE_PRIORITY, BBFILES_DYNAMIC, bbappend matching, overlayed recipes, provider selection, and layer compatibility. Use for layer creation, layer migration, layer review, or when a bbappend/recipe is not being applied.
Higangssh/yocto-agent-skills/skills/yocto-recipe-review Skill
6★ repoReview and improve Yocto/OpenEmbedded recipes, bbappends, bbclasses, package splits, dependencies, licensing, source fetching, patch handling, install logic, systemd/init integration, PACKAGECONFIG, and modern BitBake override syntax. Use for .bb, .bbappend, .bbclass, recipe diffs, recipe modernization, packaging errors, or metadata code review.
ahgraber/skills/skills/changelog Skill
6★ repoUse when writing, updating, or generating a CHANGELOG.md — for a new release, an unreleased section update, or drafting from git history or diff. Triggers: "update the changelog", "write release notes", "what changed since X", "generate changelog for v1.2.0", "add this to the changelog", "draft unreleased section". Not for commit messages (use commit-message skill) or internal deployment runbooks.
ahgraber/skills/skills/code-review Skill
6★ repoUse when reviewing code changes before committing or merging — staged diffs, branch diffs, or PR readiness checks. Triggers: 'review my code', 'check these changes', 'review this branch', 'give feedback on my diff', 'is this PR ready?'. Not for implementing features, running test suites, or formatting-only passes.
ahgraber/skills/skills/commit-message Skill
6★ repoUse whenever a Conventional Commit message is being drafted — whether the user asks ("write commit message", "draft commit from staged changes", "generate conventional commit", "split this into commits") or you are about to propose one proactively after finishing work (e.g. completing tasks, wrapping up a feature, or summarizing staged changes). Invoke before writing the message inline. Not for creating commits, amending history, or full code review.
ahgraber/skills/skills/editorial-review Skill
6★ repoUse when the user wants rigorous, non-sycophantic editorial feedback on a draft, essay, blog post, or argument through back-and-forth dialogue — pressure-testing thesis, structure, argument, clarity, tone, and evidence. Triggers: "be my sparring partner", "pressure-test this draft", "poke holes in my argument", "is this ready to publish", "sharpen this post", "where is this weak". Not for one-shot copyediting, proofreading, or ghostwriting.
ahgraber/skills/skills/explain-diff Skill
6★ repoUse when the user wants a rich, interactive explanation of a code change — a diff, branch, commit, staged changes, or PR — as a standalone artifact rather than a quick answer in chat. Produces a dated, self-contained HTML (default) or Markdown artifact the reader can revisit and quiz themselves against, so understanding sticks instead of evaporating after one read. Triggers: "explain this diff/PR/branch", "walk me through this change", "make an interactive explanation of this commit", "help me/my team understand this PR", "onboarding doc for this change", "teach me what changed". Not for: a quick one-line summary of a diff (just answer), writing a commit message (use commit-message), or reviewing code for defects (use code-review).
ahgraber/skills/skills/sdd-verify Skill
6★ repoUse when verifying that an implementation matches a change's SDD artifacts. Triggers: "verify", "check implementation", "did I implement everything", "verify the change", "is implementation complete", "check conformance".
ahgraber/skills/skills/security-fix-finding Skill
6★ repoUse when the user explicitly asks to fix and verify a validated or plausible security finding. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.
ahgraber/skills/skills/security-scan Skill
6★ repoUse when the user asks for a security scan or review of a repository, a scoped path (package, folder, or submodule), or a Git-backed change set (pull request, commit, branch diff, or working-tree patch). Point it at the target; it runs the full threat-model, discovery, validation, and attack-path pipeline and writes a report. Do not use to triage externally supplied findings or to fix a single finding.
ahgraber/skills/skills/subagent-patterns Skill
6★ repoUse when dispatching development work to one or more subagents and deciding how to shape each dispatch. Triggers: "use subagents", "orchestrate subagents", "delegate to a cheaper/stronger model", "big:little" / "little:big", "verifier / adversary / explorer / oracle subagent", "run this with subagents", "get an independent second opinion". Not for: the parallel code-review path (use `code-review`), or driving a separate agent CLI non-interactively.
dbc-oduffy/coordinator-claude/skills/code-health Skill
no license5★ repoAn opinionated Claude operating system for PM-led engineering. Planning, enrichment, delegated execution, staged review, ship decisions, durable handoffs.
dbc-oduffy/coordinator-claude/skills/codex-review-gate Skill
no license5★ repoRun a Codex code review as a second-opinion gate. Returns structured result with findings or graceful skip. Used by /bug-sweep --codex-verify and /workweek-complete Step 7.4.
dbc-oduffy/coordinator-claude/skills/consolidate-git Skill
no license5★ repoAn opinionated Claude operating system for PM-led engineering. Planning, enrichment, delegated execution, staged review, ship decisions, durable handoffs.
dbc-oduffy/coordinator-claude/skills/enrich-and-review Skill
no license5★ repoAn opinionated Claude operating system for PM-led engineering. Planning, enrichment, delegated execution, staged review, ship decisions, durable handoffs.
Finishing a development branch
dbc-oduffy/coordinator-claude/skills/finishing-a-development-branch Skill
no license5★ repoAn opinionated Claude operating system for PM-led engineering. Planning, enrichment, delegated execution, staged review, ship decisions, durable handoffs.
dbc-oduffy/coordinator-claude/skills/parallel-code-review Skill
no license5★ repoAn opinionated Claude operating system for PM-led engineering. Planning, enrichment, delegated execution, staged review, ship decisions, durable handoffs.
dbc-oduffy/coordinator-claude/skills/review-code Skill
no license5★ repoUse when a code change / diff / PR is ready for review or code-review findings have landed.
dbc-oduffy/coordinator-claude/skills/review Skill
no license5★ repoAn opinionated Claude operating system for PM-led engineering. Planning, enrichment, delegated execution, staged review, ship decisions, durable handoffs.
teambrilliant/dev-skills/skills/qa-test Skill
no license5★ repoBrowser-based QA verification after any implementation. Use when someone says "QA this", "test this in browser", "verify the feature", "qa test", "browser test", or after completing an /implement-change to verify acceptance criteria in a real browser. Opens Chrome via MCP, exercises each acceptance criterion, verifies via DOM snapshots, and reports pass/fail. The "closer" for every implementation — proof it works, not just that tests pass.
teambrilliant/dev-skills/skills/strategic-thinker Skill
no license5★ repoUse for cross-domain strategic reasoning, approach selection, and systems-level analysis. Trigger when the user wants to: think through how to approach a problem, evaluate tradeoffs between architectural or technical approaches, sanity-check a plan or direction, understand second-order effects of a decision, get a holistic view across code/org/time dimensions, or pressure-test assumptions. The core signal is the user asking "what's the right approach?", "think about this", "what am I not seeing?", "sanity check", "tradeoffs", "how should we tackle this?", or any request for multi-level reasoning that spans product, architecture, and organization. Also use when the user needs help deciding which workflow skill to invoke next. NOT for: product/user/business decisions (→ product-thinker), work definition (→ shaping-work), file-level technical planning (→ implementation-planning), writing code, test authoring, or PR review.
tercel/code-forge/skills/review Skill
no license5★ repoUse when reviewing code, handling review feedback, or posting a review to a GitHub PR — 15-dimension quality analysis PLUS an Acceptance Gate (runs the test suite fresh and reconciles every P0/P1 acceptance criterion against a named passing test, hard-blocking merge on any uncovered P0 or failing test) for features or entire projects (generate mode), structured evaluation and response to incoming review comments (feedback mode via --feedback flag), or automated PR review posted as a GitHub comment (--github-pr flag).
tercel/code-forge/skills/verify Skill
no license5★ repoUse before claiming work is done, fixed, or passing — requires running verification commands and confirming output before any success claim. Prevents false completion claims, unverified assertions, and "should work" statements.
panjose/Co-Scientist/skills/hypothesis-deep-verification Skill
5★ repoRun the assumption decomposition and deep verification review for a hypothesis.
panjose/Co-Scientist/skills/hypothesis-full-review Skill
5★ repoRun the full literature-grounded review for a hypothesis.
panjose/Co-Scientist/skills/hypothesis-initial-review Skill
5★ repoRun the initial review gate for a hypothesis.
panjose/Co-Scientist/skills/hypothesis-observation-review Skill
5★ repoEvaluate a hypothesis against prior observations.
panjose/Co-Scientist/skills/hypothesis-review-pipeline Skill
5★ repoRun the decomposed review pipeline for a single hypothesis and persist each review stage as a structured artifact.
panjose/Co-Scientist/skills/hypothesis-review-summary Skill
5★ repoSummarize the completed reviews for a hypothesis.
panjose/Co-Scientist/skills/hypothesis-simulation-review Skill
5★ repoSimulate the hypothesis mechanism and identify failure scenarios.
panjose/Co-Scientist/skills/insights-from-reviews Skill
5★ repoExtract recurring critique patterns from the completed review of a hypothesis.
augchan42/inkstone/skills/plan-review-loop Skill
5★ repoRun a review loop on an implementation plan — author or locate the plan, get an independent multi-lane review (zero-context executability, grounding against the repo and source spec, task structure), then address findings with judgment. Use when a plan is written and needs adversarial review before execution, or when asked to "review the plan", "check this plan", or "plan review loop". Supports superpowers plans (docs/superpowers/plans/), planning-with-files task_plan.md, and any other plan format; the source spec is reviewed transitively via the traceability lane. For code review loops, see the review-loop plugin.
photostructure/coding-skills/plugins/coding/skills/review-staged Skill
5★ repoOpinionated Claude Code and Codex workflow skills: iterative planning, proof-based review, and clean Conventional Commits.
photostructure/coding-skills/plugins/coding/skills/review Skill
5★ repoOpinionated Claude Code and Codex workflow skills: iterative planning, proof-based review, and clean Conventional Commits.
photostructure/coding-skills/plugins/cpp/skills/resource-review Skill
5★ repoTop-level memory- and resource-safety code review for modern C/C++ (C++17), including Node.js native addons (node-addon-api / Node-API). Use when the user asks to "review C++/C for memory safety", "find a memory leak", "why does this segfault", "check for use-after-free / double-free / buffer overflow / data race", "resource/handle/fd leak", "review this native addon", "N-API / node-addon-api review", or to check native code with AddressSanitizer/UBSan/TSan/Valgrind. Reports only defects backed by a sanitizer trace, reproducer, or fully traced lifetime. Do not restart the full workflow for a delegated leaf validation task.
photostructure/coding-skills/plugins/security/skills/web-security-hardening Skill
5★ repoSecurity best-practices and hardening review for JavaScript/TypeScript web and Electron desktop applications. Use when asked to harden an app, review security posture or secure defaults, assess OWASP ASVS or Electron security-checklist alignment, improve HTTP headers or CSP, review forms/input validation/sanitization/uploads, strengthen authentication/passwords/sessions/secrets, secure Electron windows/preloads/IPC/navigation/permissions/protocols/updates/packaging, or evaluate deployment/operations controls. Produces an applicability-aware baseline gap analysis (Met / Gap / Not applicable / Needs verification), not exploit severity findings.
photostructure/coding-skills/plugins/security/skills/web-security-review Skill
5★ repoOpinionated Claude Code and Codex workflow skills: iterative planning, proof-based review, and clean Conventional Commits.
bg-szy/TOP-SKILLS/skills/Claude-meta-skill/local-diff-review Skill
no license5★ repo基于本地 git diff 的代码审查技能。用于在提交 PR 前先做自检评审,严格复用 pr-review 的三维度标准(代码质量标准、FastGPT 风格规范、常见问题清单),支持审查未暂存改动、已暂存改动、某次提交、或当前分支相对基线分支的全部改动。
bg-szy/TOP-SKILLS/skills/agent-skills/code-quality Skill
no license5★ repotwo-stage review (spec compliance first, then code quality), refactoring, and quality improvement. Use when reviewing code, eliminating code smells, reducing technical debt, refactoring methods, running self-critique loops, or improving maintainability and readability.