Review & quality
19,040 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
Background-Craft/hydrant-skills/skills/preflight Skill
1★ repoRun the pre-PR quality gate on a Hydrant branch — lint, build, tests, coverage assessment, acceptance-criteria check, dependency-graph verification, production-safety review, and adversarial review. Use when the user asks for `/preflight`, says "preflight HYD-123", or wants final validation before shipping.
Background-Craft/hydrant-skills/skills/yeet Skill
1★ repoShip a Hydrant branch — detect where you are in the commit→push→PR→merge→cleanup pipeline and pick up from there. Use when the user asks for `/yeet`, says "ship this", "yeet HYD-123", or wants the current branch fully delivered and `main` cleaned up.
UniverLab/skills/texforge Skill
1★ repoCLI tool for compiling LaTeX documents to PDF without TeX Live, MiKTeX, or any external LaTeX distribution. Use this skill whenever the user wants to create a LaTeX project, compile .tex files to PDF, format or lint LaTeX documents, manage templates, or work with the texforge CLI. Activate when the user mentions "texforge new", "texforge build", "texforge fmt", "texforge check", "texforge init", "texforge template", creating a thesis or academic document, compiling LaTeX without installing TeX Live, using tectonic as a LaTeX engine, project.toml configuration, or any workflow involving .tex files and the texforge tool.
stevennitesh/programming-agent-skills/skills/.archive/pre-pr-review Skill
1★ repoUse when reviewing a branch, commit, working tree, or PR-ready diff before opening or updating a pull request; when asked for pre-PR review, PR readiness, bug finding, regression review, code review, review before merge, or review with Codex; and when the review should focus on actionable correctness, security/privacy, data, contract, test, dependency/config, performance, or migration issues introduced by the diff.
stevennitesh/programming-agent-skills/skills/.archive/verify-before-done Skill
1★ repoUse before claiming repo work is done, fixed, passing, reviewed, ready, resolved, clean, safe to merge, mergeable, or complete; calibrates claim strength to fresh evidence.
stevennitesh/programming-agent-skills/skills/.archive/workspace-safety Skill
1★ repoUse as a lightweight gate when overlapping dirty tracked paths, relevant untracked protected paths, or repo operations could overwrite, delete, publish, mix, stage, regenerate, or depend on unknown work: staging, commit, PR, push, merge, branch/worktree changes, installs, lockfiles, migrations, generators, broad formatters, generated cleanup, or destructive Git/filesystem commands.
stevennitesh/programming-agent-skills/skills/.archive/worktree-isolation Skill
1★ repoUse when approved parallel implementation across agents or sessions needs separate git branches/worktrees, when a user explicitly asks for isolated worktrees, or when `parallel-disjoint`/`parallel-overlap` execution needs branch, ownership, integration, or cleanup safety before editing.
stevennitesh/programming-agent-skills/skills/custom/convergent-pr-review Skill
1★ repoReview one immutable local PR, release candidate, or bounded high-risk diff read-only through direct fresh-context reviewers, root-verified finding admission, exact degraded-capacity fallbacks, and optional nonblocking advisories, then return one terminal release decision. Root-only. Route open-ended repository correctness, methodology, model-risk, leakage, validation, calibration, analytics, or performance baselines to $audit-codebase.
stevennitesh/programming-agent-skills/skills/custom/grill-with-docs Skill
1★ repoUse when a request combines grilling one repo-backed decision with keeping its domain language, invariants, or relationships current; exclude conversation-only grilling and settled-domain-only work.
stevennitesh/programming-agent-skills/skills/custom/resolving-merge-conflicts Skill
1★ repoReconcile an in-progress merge, rebase, cherry-pick, revert, or conflict-marked file when the user asks to resolve conflicts. For status, explanation, or review, perform only read-only State and Trace.
stevennitesh/programming-agent-skills/skills/custom/review Skill
1★ repoReview one ordinary branch, WIP, staged, or "review since X" diff read-only from a fixed snapshot. Judge Standards ("built right?") and Spec ("right thing?") separately, then return one terminal report. Hand off local PRs or high-risk local diffs once to $convergent-pr-review.
stevennitesh/programming-agent-skills/skills/extra/setup-pre-commit Skill
1★ 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
lgtm-hq/ai-skills/skills/branch Skill
1★ repoStart work on a new branch or worktree. Use when asked to start a new branch, new worktree, begin work on a feature/fix, or start fresh. Supports issue numbers and plain descriptions.
lgtm-hq/ai-skills/skills/commit Skill
1★ repoPre-commit workflow and commit guidelines. Use when asked to commit changes. Requires passing lint and tests, signed commits, semantic prefixes, imperative mood.
lgtm-hq/ai-skills/skills/lint Skill
1★ repoRun linting and formatting. Prefer `uv run lintro chk` for checks and `uv run lintro fmt` for formatting when lintro is available; fall back to native tools only when lintro is unavailable or another skill documents a follow-up pass (e.g. raycast).
lgtm-hq/ai-skills/skills/lintro-verify Skill
1★ repoVerify that a lintro tool implementation is complete and follows all project standards. Use after adding a new tool to lintro.
lgtm-hq/ai-skills/skills/rebase Skill
1★ repoRebase the current branch onto the latest main. Use when asked to rebase, sync with main, update branch, or pull latest changes. Fetches and rebases onto latest main; does not push automatically.
lgtm-hq/ai-skills/skills/turbo-verify Skill
1★ repoCanonical Agent Skills library for Claude Code, Cursor, Codex, and other agents.
simonkoehler/event-skills/event-reviewer Skill
1★ repoReview and validate outputs from other B2B event skills for cross-skill consistency, completeness, and quality. Checks that budget figures match timeline assumptions, sponsorship tiers align with venue capacity, email timing matches registration deadlines, and GDPR compliance is consistent across all outputs. Use this skill after generating outputs from multiple event skills to catch inconsistencies, before presenting a complete event plan to stakeholders, or when the user asks to review or validate their event planning outputs.
harrylabsj/hermes-skills/skills/token-cost-guard Skill
no license1★ repoMonitor agent token usage and model cost from the active ecosystem's own records, compare the current run with the previous snapshot, and send an alert report when cost growth exceeds a threshold. In OpenClaw it reads OpenClaw session logs; in Hermes agent it reads Hermes logs/state.db instead of OpenClaw. Use when users ask to track token spend, calculate realtime token cost, detect spending spikes, monitor DeepSeek/Kimi/GPT model usage, or set up cost alerts for OpenClaw or Hermes agents.
GustavoGutierrez/engineering-skills/skills/compliance-guard Skill
1★ repoValidate specs, APIs, data models, architectures, ADRs, and generated artifacts against organizational or architectural rules; use when checking compliance, enforcing governance, validating against rules, policy enforcement, or checking constraint violations.
GustavoGutierrez/engineering-skills/skills/reviewer Skill
1★ repoRigorous technical and quality reviewer that audits artifacts (PRDs, specs, architectures, user stories, APIs) for consistency, completeness, clarity, gaps, and standards compliance. Trigger: when the user asks for a review, quality audit, QA gate, technical validation, or to check an artifact before implementation.
GustavoGutierrez/engineering-skills/skills/validation-strategist Skill
1★ repoDesign layered validation and verification strategies for software artifacts. Trigger: when designing a validation plan, QA strategy, release gates, verification layers, test strategy, entry/exit criteria, or multi-layer quality assurance.
The same file is in 1 other repository
jsirish/workflow-skills/skills/local-ci Skill
no license1★ repoCross-project agent workflow skills — session onboarding, handoffs, PR review, and merge workflows
jsirish/workflow-skills/skills/pr-review Skill
no license1★ repoRequest and manage pull request reviews using pr-agent (local CLI) with optional Claude second-pass. Use when needing to review a PR, check review comments, address feedback, or iterate on fixes. Triggers on "review pr", "request review", "check review comments", "review this", or "re-review".
The same file is in 1 other repository
jsirish/workflow-skills/skills/ss-branch-strategy Skill
no license1★ repoEstablish consistent branch-naming and default-branch conventions across all module repos when executing a major framework or CMS version upgrade. Covers integer branch naming, default-branch promotion, previous-version preservation, and the fork-and-upstream workflow for third-party modules. Use when planning or executing a major version upgrade across a suite of repos.
jsirish/workflow-skills/skills/visual-regression-upgrade Skill
no license1★ repoVerify visual parity between two web environments (production vs upgraded/UAT) by capturing full-page screenshots of matching URLs and producing a pixel-diff HTML report. USE THIS SKILL whenever an agent needs to answer "does it look the same", "check the upgrade visually", "compare prod and UAT", "did the layout change", "screenshot diff", "visual regression", or verify a CMS major-version upgrade (SilverStripe 4→5, Drupal 9→10, WordPress major bumps) hasn't broken the front-end. Self-contained — bundles a Playwright capture script, URL crawler, and pixel-diff report generator.
The same file is in 1 other repository
sainzs/santiagosainz-skills/skills/core/requirements-review Skill
1★ repoReview requirements before implementation by turning fuzzy intent into decisions, constraints, risks, and a first executable step. Use when the user asks to clarify scope, review requirements, resolve ambiguity, identify constraints, or use align-change.
sainzs/santiagosainz-skills/skills/core/test-and-verify Skill
1★ repoTest and verify one behavior through a tight evidence loop: baseline, failing proof when useful, minimal edit, and final proof. Use for tests, verification, TDD, regression-proofing, smoke checks, readiness validation, or prove-change.
qmertesdorf/GameForge/.claude/skills/deepen Skill
1★ repoUse when growing an already-playable Godot game along a depth axis (systemic / content / run-meta) without regressing proven behavior. The first ITERATION skill in the GameForge loop — it EXTENDS the rules engine (the deliberate inverse of the asset re-skin's frozen-logic rule), TDD-ing each new sub-system against selftest.gd as a regression guard, records manifest.depth_pass, loops back through validator, and does NOT advance status.
qmertesdorf/GameForge/.claude/skills/validator Skill
1★ repoUse when confirming a generated Godot game opens, runs, and has a working core loop. Runs headless checks, records manifest.validation, and advances status to validated/playable or failed.
rmerk/crewai-headless-flow/.agents/skills/code-review Skill
1★ repoReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
The same file is in 12 other repositories
rmerk/crewai-headless-flow/.agents/skills/git-guardrails-claude-code Skill
1★ 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
rmerk/crewai-headless-flow/.agents/skills/grill-me Skill
1★ repoA relentless interview to sharpen a plan or design.
The same file is in 19 other repositories
rmerk/crewai-headless-flow/.agents/skills/grill-with-docs Skill
1★ 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
rmerk/crewai-headless-flow/.agents/skills/prototype Skill
1★ repoBuild a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
The same file is in 6 other repositories
rmerk/crewai-headless-flow/.agents/skills/resolving-merge-conflicts Skill
1★ repoUse when you need to resolve an in-progress git merge/rebase conflict.
The same file is in 11 other repositories
rmerk/crewai-headless-flow/.agents/skills/setup-pre-commit Skill
1★ 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
rmerk/crewai-headless-flow/vendor/agent-skills/skills/code-review-and-quality Skill
1★ repoConducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
The same file is in 9 other repositories
rmerk/crewai-headless-flow/vendor/agent-skills/skills/jira-ticket-plan Skill
1★ repoFetch a Jira issue from a ticket link or key in context, resolve the expected git branch for the ticket, and produce a Vue/TDD-grounded implementation plan saved locally to .agents/jira-plans/ (personal, never committed). For bugs, follow systematic-debugging investigation before fix steps. Optional plan-and-ship handoff to jira-ticket-implement. Jira is read-only (no comments or status changes). Use when the user passes a Jira URL, mentions a ticket key (e.g. AS-12345), or asks to plan or review work from Jira.
medzin/sre-runbook-agent-skills/skills/sre-runbook-reviewer Skill
1★ repoReview SRE runbooks from a clean-context perspective. Use when the user asks whether a runbook is clear, executable, safe, complete, on-call friendly, agent-executable, or missing assumptions, commands, dashboards, thresholds, rollback steps, escalation paths, or verification criteria.
ievo-ai/skills/plugins/ievo/skills/deep-review Skill
1★ repoiEvo — self-evolving plugin for Claude Code. Capture lessons, patch local agents and skills, replay logs on upstream updates.
ievo-ai/skills/plugins/ievo/skills/security-check Skill
1★ repoiEvo — self-evolving plugin for Claude Code. Capture lessons, patch local agents and skills, replay logs on upstream updates.
mlava/scholar-sidekick-skills/skills/scholar-sidekick-mcp Skill
1★ repoUse the connected scholar-sidekick-mcp MCP server when the user mentions a scholarly identifier (DOI, PMID, PMCID, ISBN, arXiv, ISSN, NASA ADS bibcode, WHO IRIS URL) and wants structured metadata, a formatted citation, a bibliography export file, a retraction check, an open-access check, verification that a claimed citation is real (not fabricated), or a whole-bibliography audit (batch fabrication + retraction check). Requires the MCP server connected — it works anonymously, no API key required; for a zero-install path use the scholar-sidekick-api skill instead.
frankxai/starlight-agent-skills/skills/cosmos/rights-check-nasa-esa Skill
1★ repoCheck usage rights for NASA/ESA/observatory space media and emit a correct attribution line. Use when reusing a space image/video, before publishing a short or atlas page, or when the user asks 'can I use this image' / 'what's the credit' for NASA, ESA, Hubble, Webb, or observatory media.
frankxai/starlight-agent-skills/skills/research/claim-verification Skill
1★ repoFact-check a claim against sources and return a verdict with evidence and confidence — supported, refuted, partially-supported, or unverifiable. Use when asked to 'verify', 'fact-check', 'is this true', or before publishing a statistic or scientific claim.
sarfaraz-munir/Claude-Code-Cyber-agents/.claude/skills/ciso-posture-review Skill
1★ repoFull enterprise security posture review using the CISO swarm (10 agents: queen + 9 specialists). Covers risk, compliance, threats, architecture, IR, vuln-mgmt, DevSecOps, awareness, and AI security. Use for comprehensive security assessments, board reporting, or pre-audit preparation.
anarefin/ai-agent-skills/resolve-open-questions Skill
no license1★ repoSecond-pass automation for an EARS specification file produced by /springboot-to-ears. Walks every `[NEEDS REVIEW]` item in the spec's `## Open Questions` section, executes the breadcrumb commands from the item's `*Hint for reviewer:*` footer, and either resolves the question (rewriting the entry and citing the resolution on every affected EARS statement) or leaves it open untouched. Trigger when the user types `/resolve-open-questions <path-to-EARS-file>`.
tdyzzsp47/claude-skills/skills/code-review Skill
1★ repoコードレビューを体系的に実施するスキル。PRレビュー依頼時・AI多視点レビューを並列実行したい時・レビュー観点の優先順位を整理したい時に使う。
tdyzzsp47/claude-skills/skills/git-workflow Skill
1★ repoブランチ戦略・コミット規約・PR運用を定めるGit運用スキル。新規リポジトリのルール策定時、開発フロー整備時、AIエージェント並列開発の調整時に使う。
unopim/agent-skills/skills/unopim-dev-cycle Skill
1★ repoDevelopment workflow for UnoPim. Activates when running tests, linting code, building assets, or debugging; or when the user mentions test, lint, pint, build, npm, pest, format, style, quality, coverage, or needs to verify code works.
unopim/agent-skills/skills/unopim-git Skill
1★ repoUse when creating an UnoPim branch, writing a commit message, or opening a pull request against the UnoPim repository. Trigger phrases include "branch", "commit", "commit message", "PR", "pull request", "changelog".
linyindong/platform-product-skills/skills/platform-prd-reviewer Skill
1★ repoReview PRDs, product requirement drafts, platform designs, prototypes, and requirement sections with PRD-quality-first judgment, document-specific findings, product-logic closure, and artifact-size calibration. Use when the user asks to check, review, validate, score, find gaps, help a PM improve the next PRD version, assess whether logic is closed-loop, compare small-feature vs 0-to-1 platform readiness, or decide whether a PRD is ready for product review, engineering review, RFC follow-up, or further scope clarification.
linyindong/platform-product-skills/skills/platform-scope-checker Skill
1★ repoAssess MVP scope, phase boundaries, build risk, change impact, and hidden complexity for product requirements. Use when the user asks whether to include something now, whether a request is actually big, how to split MVP vs future iteration, whether to validate before building, or when a feature may affect data objects, permissions, workflow, UI, APIs, operations, rollout, migration, ownership, or platform consistency.
WellDunDun/skills/skills/setup-build-verify-loop Skill
1★ repoSets up project-specific build, test, runtime, and evidence verification loops for AI agents. Use when onboarding a repo, documenting build/test commands, creating AGENTS.md instructions, preparing a project verification skill, or turning an ad hoc workflow into a repeatable build-and-verify loop.
roronoazoroshao369/vibe-coding-os/skills/agents/reviewer-agent Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/core/adversarial-code-review Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/core/checkpoint-validation Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/core/code-intelligence-review Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/core/critique-pass-protocol Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.