Review & quality
19,000 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
knownasnaffy/prompthound/dataset/case_05736 Skill
no license0★ repoCheck SSL certificates and expiry dates
knownasnaffy/prompthound/dataset/case_05752 Skill
no license0★ repoCheck SSL certificates and expiry dates
forchain/skills/git-period-report Skill
no license0★ repoGenerate git-based period reports from repository history: weekly reports by default, monthly reports, custom date-range summaries, commit-history reports, and squashed-diff/final-state reports. Use when the user asks for a weekly report, monthly report, work report, changelog-like status report, or asks to summarize commits or changes over a time window.
forchain/skills/repair-git-history Skill
no license0★ repoRepair Git history across repositories. Use for incorrect commit identities, non-English commit messages, evidence-backed tags or Releases, wrong GitHub accounts, and repository professionalism audits.
jwoo0122/harness/.agents/skills/grill-with-docs Skill
0★ repoRelentlessly refine a plan or design through one-question-at-a-time interviewing, while maintaining a project glossary and recording durable architectural decisions as ADRs.
goonobu-dot/dev-skills-library/skills/project-conventions Skill
0★ repoProject scaffolding conventions from elsewhencode/project-guidelines: directory layout, env var and config management, README/CONTRIBUTING essentials, Git branch and commit conventions. Use when starting a new project/repository, restructuring project layout, setting up .env/.gitignore, or when the user says プロジェクト構成, 雛形, 新規リポジトリ, ディレクトリ構成. Not for writing the commit message itself (use commit-and-pr) or for CI/CD workflow design (use ci-cd-hardening).
goonobu-dot/dev-skills-library/skills/refactoring-discipline Skill
0★ repoDisciplined refactoring workflow combining Kent Beck's Tidy First, Fowler's refactoring catalog, and Google's small-CL principle. Use when restructuring or cleaning up existing code, when a diff is growing beyond one concern, or when the user says リファクタリング, 整理して, きれいにして. Keeps structural changes strictly separate from behavior changes. Not for designing new module interfaces (use deep-module-design) or commit message writing (use commit-and-pr).
MasashiFukuzawa/agent-toolbox/plugins/toolbox/skills/claude-review Skill
0★ repoReusable engineering skills for Claude Code and Codex
MasashiFukuzawa/agent-toolbox/plugins/toolbox/skills/codex-review Skill
0★ repoReusable engineering skills for Claude Code and Codex
MasashiFukuzawa/agent-toolbox/plugins/toolbox/skills/e2e-capability-verification Skill
0★ repostaging や test 環境で認証付き E2E と機能可否を安全に検証する。破壊的操作や storageState が関わる検証に使う。アドホックなブラウザ操作には browser-operations を使う。「stagingで可能か確認」「認証付きE2Eを検証」を正のトリガーとし、日常的なサイト閲覧やログイン引き継ぎには使わない。
MasashiFukuzawa/agent-toolbox/plugins/toolbox/skills/git-worktrees Skill
0★ repoReusable engineering skills for Claude Code and Codex
MasashiFukuzawa/agent-toolbox/plugins/toolbox/skills/verification-loop Skill
0★ repo実装中に型チェック、lint、テストを短い間隔で繰り返す。変更途中の継続検証に使う。完了時の最終品質ゲートには done を使う。「変更ごとに検証して」「lintとtestを回し続けて」を正のトリガーとし、出荷可否を確定する完了時の署名には使わない。
jikkujoyce/agent-skills/skills/pr-triage Skill
0★ repoCool skills for me, you and everyone.
Kofiloski/ios-release-quality-toolkit/plugins/ios-release-quality-toolkit/skills/ios-ui-testability-contract Skill
0★ repoFix XCUITest, AXe, and ios-ai-ui-check failures where a SwiftUI or UIKit element is reported as not found, resolves as the wrong XCUIElement type, inherits a container accessibilityIdentifier, or cannot be reached deterministically. Use to diagnose UI automation artifacts and patch app-side accessibility identifiers, element exposure, stable row IDs, launch routes, seeded state, scenario files, or planner context, then verify the exact path with a focused replay.
The same file is in 1 other repository
arniesaha/ctxops/skills/decision-review Skill
0★ repoWHEN about to commit to a direction and want a sharp adversarial pass. Triggers: 'should we do X?', 'is this worth it?', 'pressure-test this plan/principle/vision', 'pick between A and B', 're-check the call we made two weeks ago', 'play devil's advocate'. Direct, not balanced. OUTPUT: verdict (do/delay/narrow/compare/kill), strongest case for and against, cheapest test. PAIR BEFORE: ticket-scoping (file the chosen path). Use post-hoc mode for older calls.
kaustin923/agent-fitness-coach/.claude/skills/weekly-review Skill
0★ repoCompute and write the weekly training and nutrition review for the last completed Monday–Sunday week, with grounded numbers, a per-run grade table, the weight trend, and up to three plan-adjustment suggestions. Use when it's Monday, the athlete asks "how did my week go", or a full week of data has just been synced.
sandev/engineering-os/skills/design-and-architecture/system-design-review Skill
0★ repoRun a structured review of a system or service design across scalability, reliability, security, cost, and operability. Use when the user shares an architecture, asks to review a system design, evaluate a proposed service, or pressure-test a design before build.
chuaitry-edu/try-skills/hermes/try-review Skill
no license0★ repo当用户说「学完就忘了」「怎么复习」「怎么复盘」「怎么回忆学过的内容」「间隔多久复习一次」时使用。 Use when someone learns something but forgets—needs review, recall, spaced repetition, or reflection strategies. Trigger: /try-review, /复习, /回忆, /复盘, "how to review", "I keep forgetting", "spaced repetition"
gio-del/skills/skills/engineering/grill-with-docs Skill
0★ repoA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
The same file is in 19 other repositories
gio-del/skills/skills/productivity/grill-me Skill
0★ repoA relentless interview to sharpen a plan or design.
The same file is in 19 other repositories
frankxai/creator-skills/skills/reviews/production-review Skill
0★ repoUse when the user asks to review or pressure-test a video / content plan BEFORE generating it — triggers include "review my video plan", "is this worth generating", "pre-flight my shoot", "grill my content idea", "will this convert", "should I spend credits on this". Grills the brief for hook, destination-fit, identity-consistency, and cost, then hands a go / rework verdict to the video-gen router.
zhoy0409-debug/scholarflow-skills/skills/scholarflow-citation-review Skill
0★ repoUse when a researcher needs citations or a reference list audited for source verification, metadata consistency, journal style, or evidence-to-claim alignment.
zhoy0409-debug/scholarflow-skills/skills/scholarflow-review-response Skill
0★ repoUse when a researcher needs reviewer responses, rebuttals, revision plans, or response tables drafted and audited with evidence-backed replies and clear manuscript-change mapping.
robcsaszar/ai-forge/skills/ai-forge-review Skill
0★ repoCritically reviews and stress-tests agent, skill, and AI workflow definitions before they ship. Use whenever someone creates, modifies, or proposes an agent config, skill file, system prompt, or AI-powered workflow — including 'review this agent', 'check this skill', 'is this agent safe', or any request for feedback on an AI/LLM integration. Also trigger when someone mentions creating a new agent or skill, even before it is written — help them think before they build. Don't use for rubric scoring — that's ai-forge-judge.
kaskilling/agent-coordination-skills/skills/second-round Skill
0★ repoRuns an adversarial second-round review loop for any task by asking a fresh reviewer surface to independently review the current work, research comparable patterns, find gaps, and recommend fixes. Use when the user asks for a second round, critical review, independent review, adversarial review, another agent's view, or a review/improve/re-review loop.
meo9805/mininglamp-oss-octo-spec/templates/octospec-init/.claude/skills/octospec-workflow Skill
0★ repoUse when implementing a feature, fixing a bug, or making any non-trivial code change in this repository. Drives the octospec 4-phase engineering flow (Plan, Implement, Verify, Finish) so the change follows this repo's rules in .octospec/ and ships a PR with a linked spec. Triggers on requests like "add ...", "implement ...", "fix ...", "refactor ...", "change the ... API", 写功能, 修 bug, 加接口, 改逻辑. Skip for trivial edits (typo, docs, lint, pure config) — those do not need the flow.
DrOlu/agent-skills/skills/dbcli/skills/dbcli-compare Skill
no license0★ repoCompare results of two SQL queries to verify if they produce identical data. Checks structure, record count, and data content using MINUS/EXCEPT operations. Use when user needs to validate query equivalence, compare view logic, verify refactoring, or check data consistency.
DrOlu/agent-skills/skills/hyperframes-cli Skill
no license0★ repoHyperFrames CLI dev loop — `npx hyperframes` for scaffolding (init), validation (lint, inspect), preview, render, and environment troubleshooting (doctor, browser, info, upgrade). Use when running any of these commands or troubleshooting the HyperFrames build/render environment. For asset preprocessing commands (`tts`, `transcribe`, `remove-background`), invoke the `hyperframes-media` skill instead.
The same file is in 1 other repository
DrOlu/agent-skills/skills/interminai Skill
no license0★ repoControl interactive terminal applications like vim, git rebase -i, git add -i, git add -p, apt, rclone config, sudo, w3m, and TUI apps. Can also supervise another CLI LLM (cursor-agent, codex, etc.) - approve or reject its actions by pressing y/n at confirmation prompts. Use when you need to interact with applications that require keyboard input, show prompts, menus, or have full-screen interfaces. Also use when commands fail or hang with errors like "Input is not a terminal" or "Output is not a terminal". Better than application specific hacks such as GIT_SEQUENCE_EDITOR or bypassing interactivity through file use.
aoli0919/learn-anything-skills/skills/hallucination-checker Skill
0★ repoCheck AI-generated learning material for unsupported claims, missing sources, contradictions, and safer wording.
aoli0919/learn-anything-skills/skills/literature-review Skill
0★ repoHelp a beginner build a small literature review map with clusters, claims, evidence, contradictions, and reading order.
aoli0919/learn-anything-skills/skills/project-lab Skill
0★ repoUse when a beginner needs a 2-hour, 1-day, or 1-week project with steps, definition of done, fallback path, check question, and reflection.
aoli0919/learn-anything-skills/skills/spaced-review-planner Skill
0★ repoSchedule spaced reviews for concepts, papers, projects, and mistakes without overloading the learner.
aoli0919/learn-anything-skills/skills/startup-idea-validator Skill
0★ repoHelp beginners validate ideas with user problem, assumptions, tests, evidence, and no-code experiments.
aoli0919/learn-anything-skills/skills/statistics-checker Skill
0★ repoHelp learners check statistical claims, sample sizes, uncertainty, correlations, p-values, and practical interpretation.
aoli0919/learn-anything-skills/skills/weekly-review Skill
0★ repoReview a week of learning, identify compounding progress, weak spots, and next week adjustments.
K95M65/AI_ONBOARD/skills/automated-security-review Skill
0★ repoWire automated security scanning into CI so every pull request is scanned for vulnerable dependencies, committed secrets, and code weaknesses. Use when setting up or improving a project's security gates in GitHub Actions.
K95M65/AI_ONBOARD/skills/changelog Skill
0★ repoAssemble release notes / a CHANGELOG entry from Conventional Commits since the last tag. Use when cutting a release or updating CHANGELOG.md. Pairs with the conventional-commit skill.
K95M65/AI_ONBOARD/skills/check-ai-onboard-updates Skill
0★ repoChecks a managed AI_ONBOARD installation for package updates, fixes, and security releases, reports drift separately from available releases, and offers a safe preview before applying an upgrade. Use when the user asks whether AI_ONBOARD is current, invokes the update-check workflow, or wants to review and apply an available bundle update.
K95M65/AI_ONBOARD/skills/conventional-commit Skill
0★ repoWrites a Conventional Commits message from the currently staged git changes. Use when the user asks to commit, wants a commit message drafted, or asks you to figure out the right commit type/scope for staged work.
K95M65/AI_ONBOARD/skills/gh-pr Skill
0★ repoCreate or update a GitHub pull request with the gh CLI. Use when opening a PR from the current branch or updating an existing one. Pairs with the pr-description skill for the body.
K95M65/AI_ONBOARD/skills/pr-description Skill
0★ repoWrite a clear pull-request description from the branch's commits and diff. Use when opening a PR or when asked to summarize a branch's changes for review.
K95M65/AI_ONBOARD/skills/workflow-foundations/grill-requirements Skill
0★ repoRuns an explicit, repository-informed interview that pressure-tests a request, plan, or design one consequential decision at a time before implementation. Use only when the user asks to be grilled, interviewed, challenged, or wants assumptions and requirements stress-tested; do not invoke implicitly for routine ambiguity or ordinary clarifying questions.
nick3/vibe-design-skills/skills/design-system-review Skill
0★ repoIndependently review a Vibe Design foundation document set and decide whether it is ready for team use. Use this skill after creating, reconstructing, or updating PRODUCT.md, DOMAIN.md, DESIGN.md, CRAFT.md, COMPONENTS.md, PATTERNS.md, TEMPLATES.md, AGENTIC-INTERFACE.md, or EVAL.md; when validating Google DESIGN.md compatibility; or when checking cross-document contradictions, unsupported assumptions, traceability, representative previews, and migration regressions. This skill reviews foundation readiness, not a single feature artifact, and must not silently rewrite approved standards.
aoli0919/learning-os-productivity-skills/skills/spaced-review Skill
0★ repoSchedule spaced review cards without overwhelming the learner.
aoli0919/learning-os-productivity-skills/skills/weekly-review Skill
0★ repoReview a learning week, identify weak spots, and adjust next week with evidence.
Story-Engine-Inc/worldos-agent-skills/skills/worldos-simulation-review Skill
0★ repoReview an owned WorldOS Simulation save and its turn history through the WorldOS MCP without modifying it. Use when a user wants to evaluate opening quality, state persistence, character behavior, pacing, app consistency, or regressions in an existing Simulation run.
tejask0/agent-skills/food-check Skill
0★ repoAnalyse a dish, meal, or ingredient combination across five dimensions: digestion compatibility, nutrient absorption, Ayurvedic food combining rules, micronutrient and protein content, and overall pros/cons with actionable suggestions. ALWAYS use this skill when the user mentions eating a dish or a mix of ingredients and asks whether it is good, healthy, safe, or okay — even with casual phrasing like "I'm eating X and Y together, is this fine?", "does this combo work?", "what do you think of this meal?", "check this", "is this good?", "analyse this food", or when the user describes their diet, meals, or post-workout food. Trigger any time food items are listed together and some form of health or suitability check is implied.
tejask0/agent-skills/vps-health-check Skill
0★ repoUse when asked for a health check, status check, or "is everything up/healthy" on this VPS — checks system resources plus every running service (n8n, WAHA, code-server, Ollama, OpenClaw, Tailscale, Docker, Syncthing notes sync, VNC/XFCE4 desktop) and configured site liveness, and reports findings. Designed to run locally on the VPS (installed under its own `~/.claude/skills/`), not over SSH from another machine.
hashorva/purrfect-harness/.agents/skills/skillify Skill
no license0★ repoGraduate a battle-tested procedure into a new SKILL.md in .agents/skills/. MUST be used at mission end (after the last feature passes), whenever the code-reviewer's flywheel notes flag the same failure class or procedure twice, or when the user says "skillify this", "make this a skill", or "we keep doing this". Orchestrator-only. Produces skills from EVIDENCE (PROGRESS.md, review findings, git log) — never from speculation.
JoaoAlavarse/cursor-config/skills/performance-review Skill
0★ repoEvaluates code, architecture and runtime behavior to identify performance bottlenecks and recommend improvements based on measurable impact. Use when reviewing performance, latency, throughput, or resource usage.
JoaoAlavarse/cursor-config/skills/security-review Skill
0★ repoEvaluates code, configuration and system design to identify security risks and recommend practical mitigations. Use when reviewing security, auth flows, input handling, or secrets management.
slalomboy/talking-head-video-suite/skills/short-video-operations-pack/skills/short-video-content-review Skill
0★ repoUse when a short-video script, shot plan, or cut needs fact, evidence, rights, disclosure, privacy, clarity, platform, or conversion review before release.
Short video performance review
slalomboy/talking-head-video-suite/skills/short-video-operations-pack/skills/short-video-performance-review Skill
0★ repoUse when comparable short-video samples need diagnosis across content, audience, conversion, and delivery metrics or a bounded next experiment.
aoli0919/visual-thinking-skills/skills/visual-explanation-review Skill
0★ repoReview visual explanations for clarity, misleading layout, and missing context.
Finishing a development branch
trugurpala/divan/plugins/core-pack/skills/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 135 other repositories
trugurpala/divan/plugins/core-pack/skills/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 141 other repositories
trugurpala/divan/plugins/core-pack/skills/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 144 other repositories
trugurpala/divan/plugins/core-pack/skills/using-git-worktrees Skill
0★ 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 140 other repositories
Verification before completion
trugurpala/divan/plugins/core-pack/skills/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 361 other repositories