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
honerlaw/agent-marketplace/plugins/minerva/skills/grill-plan Skill
0★ repoUse when a plan has just been drafted in conversation and needs stress-testing before approval — invoked by `minerva:propose` after approach selection and by `minerva:replan` after the new-plan brainstorm, also usable standalone on any drafted plan. Interviews the user relentlessly about the drafted plan, one question at a time, with the LLM's recommended answer leading each question, until shared understanding is reached.
honerlaw/agent-marketplace/plugins/minerva/skills/lint-fix Skill
0★ repoA personal plugin marketplace for AI coding agents. Each plugin provides skills and automation scripts.
honerlaw/agent-marketplace/plugins/minerva/skills/lint Skill
0★ repoA personal plugin marketplace for AI coding agents. Each plugin provides skills and automation scripts.
honerlaw/agent-marketplace/plugins/minerva/skills/migrate Skill
0★ repoA personal plugin marketplace for AI coding agents. Each plugin provides skills and automation scripts.
honerlaw/agent-marketplace/plugins/minerva/skills/propose-ship-balanced Skill
0★ repoA personal plugin marketplace for AI coding agents. Each plugin provides skills and automation scripts.
honerlaw/agent-marketplace/plugins/minerva/skills/propose-ship-quick Skill
0★ repoA personal plugin marketplace for AI coding agents. Each plugin provides skills and automation scripts.
honerlaw/agent-marketplace/plugins/minerva/skills/propose Skill
0★ repoA personal plugin marketplace for AI coding agents. Each plugin provides skills and automation scripts.
honerlaw/agent-marketplace/plugins/minerva/skills/review Skill
0★ repoReviews a changeset against both the minerva spec/knowledge lenses and code quality. With a work unit in context it runs a spec/knowledge audit alongside the code quality review, presenting both result sets before unified triage; if a GitHub PR exists for the branch it delegates code quality to `code-review:code-review`, otherwise it performs a check via a fresh-context subagent in the same finding format. Triage state persists to the scratchpad so re-runs pre-fill prior dispositions. Use when implementation on a work unit has just finished and the diff is unreviewed, when the user asks to review or audit a changeset or to verify shipped code matches what was designed, or when they invoke `minerva:review`.
honerlaw/agent-marketplace/plugins/minerva/skills/ship Skill
0★ repoA personal plugin marketplace for AI coding agents. Each plugin provides skills and automation scripts.
JimmyBlanquet/project-forge/skills/speckit/archi-review Skill
0★ repoRun an architecture audit on the current project to detect drift, layer violations, ADR non-compliance, and technical debt. Inspired by ATAM (utility tree, scenarios), DCAR (decision-centric), and ISO 25010 (quality attributes). Use this skill when the user wants to audit architecture, check architectural coherence, review ADR compliance, detect layer violations, find architecture drift, verify the project still respects its constitution and design decisions, or assess technical health. Also use when the user says "is the architecture still coherent", "check architecture", "audit the project", "are we drifting", "review architecture", "check ADR compliance", or "architecture health check". This is a read-only reporting skill — it does NOT fix issues, only reports them.
JimmyBlanquet/project-forge/skills/speckit/e2e Skill
0★ repoRun comprehensive end-to-end tests on the application using agent-browser (accessibility-tree-based browser testing). Use this skill when the user wants to run E2E tests, perform automated browser testing, verify the app works end-to-end, test user journeys in a real browser, check for UI bugs or regressions, do responsive testing across viewports, hunt for security issues via browser interaction, or validate that a feature works from the user's perspective. Also triggers on "speckit e2e", "speckit-e2e", "test the app in the browser", "run browser tests", "check if the UI works", "test user flows", "verify the feature end to end", or "automated acceptance testing". This skill launches 3 parallel research sub-agents (app structure, data flows, bug hunting), starts the dev server, creates a combined test plan, executes tests with agent-browser snapshots and screenshots, and fixes bugs as they are found. It generates an e2e-report.md with results and evidence screenshots. This does NOT generate a recette/UAT checklist without running tests (use speckit-recette), write unit tests or integration tests in code (those are part of speckit-tasks), or run tests via Playwright/Cypress — it uses agent-browser for exploration. For deterministic regression tests in CI, use Playwright (`pnpm test:e2e`).
JimmyBlanquet/project-forge/skills/speckit/recette Skill
0★ repoGenerate a recette (acceptance testing checklist) from the feature specification to validate that a feature meets all acceptance scenarios. Use this skill when the user wants to create a recette, build a UAT checklist, generate acceptance test scenarios, prepare for manual or automated feature validation, create a QA checklist, or verify a feature against its spec. Also triggers on "speckit recette", "speckit-recette", "create recette", "acceptance testing", "QA checklist", "generate test checklist from spec", "validate the feature", "UAT scenarios", "recette checklist", or "verification checklist". This skill reads spec.md, extracts all acceptance scenarios (AS1.1, AS1.2, etc.), and generates a structured recette.md with pre-conditions, manual test steps, expected outcomes, non-functional checks (performance, security, accessibility), and a systematic debugging protocol for failures. It can optionally run automated verification using agent-browser if installed. This does NOT run full E2E test suites with parallel research agents (use speckit-e2e for that), write the feature specification (use speckit-specify), or generate implementation tasks (use speckit-tasks). The recette is a validation artifact, not a planning artifact.
anandan-digital-marketer/seo-agent-skills/skills/6g-review-aggregator Skill
no license0★ repoPulls G2 and Capterra ratings and recent reviews on demand. Aggregates review sentiment, identifies most-cited strengths and weaknesses, tracks rating trends, and surfaces review content useful for VS pages (6C) and trust signals on landing pages. Also flags competitor review trends.
specdd/plugin-copilot/skills/specdd-review Skill
0★ repoUse when GitHub Copilot needs to review changes against active SpecDD specs.
webdevtodayjason/dev-kit/plugins/dev-kit/skills/grill-me Skill
no license0★ 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 440 other repositories
webdevtodayjason/dev-kit/plugins/dev-kit/skills/grill-with-docs Skill
no license0★ repoGrilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
The same file is in 137 other repositories
giostriquer/agent-workshop/.codex/skills/push Skill
0★ repoUse when committing and pushing changes in the project repository; detect the current branch, pull origin for that branch before committing, prefer the newest meaningful update in docs/change-log.md as the commit message source when available, otherwise derive the message from the primary diff, then stage all changes, commit, and push to the same current branch.
giostriquer/agent-workshop/plugins/toolkit/skills/claim-check Skill
0★ repoUse when you have a premise to verify before acting on it — most often a tracker ticket, but also a hunch you are carrying or a bare question — and you want a deep, unbiased, evidence-grounded investigation rather than a guess. Treats each claim as a hypothesis checked against the current repo and the provenance of its own evidence; a confident verdict requires direct evidence the session examined itself, so "needs more information" is a legitimate honest outcome rather than a forced answer. Scans for work that already addressed it, and returns a concise verdict-first report — the validity verdict with how it was verified, the prior/parallel work that bears on it, and the readiness dossier (or what is missing). Builds a repro to prove or break a code claim, but does not implement the fix.
giostriquer/agent-workshop/plugins/toolkit/skills/code-quality-review Skill
0★ repoRun an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a strict code quality review, deep code quality audit, or especially harsh maintainability review.
giostriquer/agent-workshop/plugins/toolkit/skills/handoff-pr Skill
0★ repoUse when a branch is ready for a PR but the current session is not authorized to open one. Produces a structured PR handoff artifact (title, body, ticket links, validation and review status) for a separately-authorized session or agent to open. Derives the PR body from the repo's own PR template when one exists. Auto-detects the ClickUp / Linear / Jira ticket and asks to confirm. Writes the artifact to a `tmp/` scratch file by default; `inline` prints it in-session instead and writes no file. Never opens the PR itself.
giostriquer/agent-workshop/plugins/toolkit/skills/handoff-review Skill
0★ repoUse when work on a branch needs a fresh, unbiased pair of eyes — a pre-PR review, or a clean restart when this session's context has gone bad and a new session should independently verify what was already done and continue it. Produces a self-contained brief (task-vs-code, rules conformance, information leak, correctness) that re-derives the task from ticket + diff, never trusting the prior session. Default spawns a fresh reviewer (verify-only); `handoff`/`session` writes the brief to a scratch file for a new session (verify-only); `continue`/`resume` writes a verify-then-continue brief carrying current state, remaining work, and operating rules, pointing to handoff-goal for substantial forward work.
giostriquer/agent-workshop/plugins/toolkit/skills/qa-sweep Skill
0★ repoUse when running a broad QA / verification pass over a release, branch, feature, or app surface that splits into independent slices, and you want team-scale coverage without trading away rigor. Fans out a QA team over the slices — each driving the real running artifact — then treats every returned finding as a lead and reproduces the verdict-moving ones firsthand before they count, drops claims that do not reproduce, separates regressions from pre-existing bugs against a baseline, and synthesizes a verdict-first report with each finding tagged by how it was verified. The decomposition gate and the firsthand-corroboration loop are the rigid core; how you slice, harness, and size the team is yours to adapt. NOT for a single code change (that is empirical-proof) or a single premise / ticket / hunch (that is claim-check) — this is the corroborated, team-scale sweep.
patdhlk/skills/skills/grill-me Skill
0★ repoInterview the user relentlessly about a plan or design until reaching shared understanding, walking every branch of the decision tree and resolving dependencies between decisions one by one. Use when the user wants to stress-test a plan, get grilled on a design, or says "grill me" / "poke holes in this".
The same file is in 1 other repository
patdhlk/skills/skills/grill-with-docs Skill
0★ repoGrilling session that challenges a plan against the project's recorded domain model - existing decisions, requirements, and glossary terms from the sphinx-needs spec - and updates term and decision directives inline as the discussion crystallises. Use when the user wants to stress-test a plan against their project's documented language and decisions, or says "grill me with docs" / "check this plan against our decisions".
The same file is in 1 other repository
patdhlk/skills/skills/prototype Skill
0★ repoBuild a throwaway prototype to answer a specific design question before committing to an approach - a runnable terminal app for state/data-model/algorithm questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this" / "let me play with it".
The same file is in 1 other repository
patdhlk/skills/skills/review Skill
0★ repoReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes in parallel - Standards (does the code follow this repo's documented rules?) and Spec (does it deliver what the originating issue and its linked requirements asked for?). Use when the user wants to review a branch, a PR, or work-in-progress changes, or says "review since X" / "review this before I merge".
The same file is in 1 other repository
fxjim/agent-commerce-guard/plugins/agent-commerce-guard/skills/agent-commerce-action-review Skill
no license0★ repoReview proposed AI-agent actions locally before execution. Use for deployments, external publishing, financial actions, marketplace jobs, social actions, destructive commands, billing changes, elevated permissions, or credential-dependent work. Produce an allow, review, or deny decision with reasons and required evidence. Never request or reproduce secrets, customer data, credentials, or private wallet material.
fxjim/agent-commerce-guard/skills/buy-agent-commerce-guard Skill
no license0★ repoInspect and buy the Agent Commerce Guard 1 USDC Base launch pass through an authorized Base MCP wallet, x402 client, or browser wallet. Use when a user wants to evaluate the offer, confirm payment details, purchase the package, verify a Base transaction, or unlock the paid download. Require explicit approval before any payment and never request wallet secrets.
fxjim/agent-commerce-guard/skills/try-agent-commerce-guard Skill
no license0★ repoEvaluate non-sensitive AI-agent commerce action manifests with the free Agent Commerce Guard hosted policy endpoint. Use when a user wants to preflight wallet spend, paid API calls, deployments, token launches, marketplace jobs, social actions, destructive commands, billing changes, or credential access before execution. Never send secrets, private source, customer data, or credentials to the hosted demo.
ULudo/codex-science-skills/skills/scientific-referee-reviewer Skill
no license0★ repoFundamentally and rigorously review scientific manuscripts as an independent scientific assessor. Use when Codex must assess novelty, technical soundness, methodology, evidence quality, literature positioning, reproducibility artifacts, ethics, clarity, and produce a structured scientific assessment ending in a binary Accept or Reject decision without asking authors questions or writing editor-only comments.
ULudo/codex-science-skills/skills/scientific-structure-reviewer Skill
no license0★ repoReview a scientific manuscript outline or draft for peer-review-ready structure, scientific story, contribution framing, section order, paper-type fit, motivation, gap, and narrative coherence. Use before detailed technical or prose review. Do not use for citation verification or line editing.
ULudo/codex-science-skills/skills/technical-reviewer Skill
no license0★ repoReview a scientific manuscript, method, experiment plan, results, or rebuttal for technical correctness, claim-evidence support, methodology, baselines, metrics, statistics, assumptions, interpretation, reproducibility, and reviewer-critical rigor issues. Do not use for grammar-only editing or bibliography metadata checks.
ULudo/codex-science-skills/skills/writing-reviewer Skill
no license0★ repoReview or rewrite scientific manuscript prose for peer-review-ready clarity, concision, paragraph flow, terminology consistency, grammar, tone, and professional wording while preserving technical meaning. Use after structure and technical claims are stable. Do not strengthen unsupported claims.
aidehua08/codex-obsdian/plugins/codex-obsdian/skills/wiki-lint Skill
0★ repoHealth check the Obsidian wiki vault. Finds orphan pages, dead wikilinks, stale claims, missing cross-references, frontmatter gaps, and empty sections. Creates or updates Dataview dashboards. Generates canvas maps. Triggers on: "lint", "health check", "clean up wiki", "check the wiki", "wiki maintenance", "find orphans", "wiki audit".
The same file is in 1 other repository
aidehua08/codex-obsdian/skills/wiki-lint Skill
0★ repoHealth check the Obsidian wiki vault. Finds orphan pages, dead wikilinks, stale claims, missing cross-references, frontmatter gaps, and empty sections. Creates or updates Dataview dashboards. Generates canvas maps. Triggers on: "lint", "health check", "clean up wiki", "check the wiki", "wiki maintenance", "find orphans", "wiki audit".
The same file is in 1 other repository
Sf onboarding compliance review
SahirVhora/sf-agent-skills/skills/sf-onboarding-compliance-review Skill
0★ repoUse when you need to validate forms, tasks, document flows, and local compliance before new hires start.
Sf people analytics quality review
SahirVhora/sf-agent-skills/skills/sf-people-analytics-quality-review Skill
0★ repoUse when you need to check whether reports are trusted, performant, governed, and safe to use for decisions.
SahirVhora/sf-agent-skills/skills/sf-position-integrity-review Skill
0★ repoUse when you need to validate position management data integrity -- find orphans, broken hierarchies, cyclical chains, and missing incumbents before they cause payroll errors.
schmoenraad/godot-gamestudio/plugins/godot-gamestudio/skills/godot-code-reviewer Skill
0★ repoIndependently review Godot GDScript, C#, scenes, Resources, and gameplay changes for correctness, regressions, architecture risks, engine misuse, save compatibility, and missing tests. Use as the opposing reviewer for gameplay-engineering deliverables.
schmoenraad/godot-gamestudio/plugins/godot-gamestudio/skills/godot-level-design-reviewer Skill
0★ repoIndependently review Godot maps and levels for flow, readability, traversal, navigation, collision, encounters, camera behavior, exits, soft locks, and environmental storytelling. Use as the opposing reviewer for world-building deliverables.
schmoenraad/godot-gamestudio/plugins/godot-gamestudio/skills/godot-narrative-editor Skill
0★ repoIndependently review Godot story, dialogue, quests, character voice, branching logic, continuity, localization readiness, and engine integration. Use as the opposing reviewer for narrative deliverables.
schmoenraad/godot-gamestudio/plugins/godot-gamestudio/skills/godot-performance-reviewer Skill
0★ repoIndependently review Godot rendering, shaders, particles, imports, memory, scene complexity, frame cost, and asset budgets using measured evidence. Use as the opposing reviewer for technical-art and optimization deliverables.
schmoenraad/godot-gamestudio/plugins/godot-gamestudio/skills/godot-systems-critic Skill
0★ repoIndependently review Godot mechanics, progression, balance, economies, audio behavior, exploits, scope, and player feedback. Use as the opposing reviewer for game-design or audio-system deliverables.
Godot ui accessibility reviewer
schmoenraad/godot-gamestudio/plugins/godot-gamestudio/skills/godot-ui-accessibility-reviewer Skill
0★ repoIndependently review Godot UI for information hierarchy, focus navigation, controller and keyboard use, scaling, safe areas, readability, contrast, motion, error handling, and accessibility. Use as the opposing reviewer for UI and UX deliverables.
schmoenraad/godot-gamestudio/skills/godot-animation-reviewer Skill
0★ repoIndependently review Godot sprite sheets and animations for timing, anchors, scale, silhouettes, loops, transitions, event timing, state coverage, and runtime playback. Use as the opposing reviewer for animated visual deliverables.
Godot art consistency reviewer
schmoenraad/godot-gamestudio/skills/godot-art-consistency-reviewer Skill
0★ repoIndependently review Godot visual assets for style, palette, perspective, scale, lighting, outlines, silhouettes, readability, import quality, and cohesion with established art direction. Use as the opposing reviewer for sprite and static-art deliverables.
schmoenraad/godot-gamestudio/skills/godot-code-reviewer Skill
0★ repoIndependently review Godot GDScript, C#, scenes, Resources, and gameplay changes for correctness, regressions, architecture risks, engine misuse, save compatibility, and missing tests. Use as the opposing reviewer for gameplay-engineering deliverables.
schmoenraad/godot-gamestudio/skills/godot-level-design-reviewer Skill
0★ repoIndependently review Godot maps and levels for flow, readability, traversal, navigation, collision, encounters, camera behavior, exits, soft locks, and environmental storytelling. Use as the opposing reviewer for world-building deliverables.
schmoenraad/godot-gamestudio/skills/godot-narrative-editor Skill
0★ repoIndependently review Godot story, dialogue, quests, character voice, branching logic, continuity, localization readiness, and engine integration. Use as the opposing reviewer for narrative deliverables.
schmoenraad/godot-gamestudio/skills/godot-performance-reviewer Skill
0★ repoIndependently review Godot rendering, shaders, particles, imports, memory, scene complexity, frame cost, and asset budgets using measured evidence. Use as the opposing reviewer for technical-art and optimization deliverables.
schmoenraad/godot-gamestudio/skills/godot-systems-critic Skill
0★ repoIndependently review Godot mechanics, progression, balance, economies, audio behavior, exploits, scope, and player feedback. Use as the opposing reviewer for game-design or audio-system deliverables.
Godot ui accessibility reviewer
schmoenraad/godot-gamestudio/skills/godot-ui-accessibility-reviewer Skill
0★ repoIndependently review Godot UI for information hierarchy, focus navigation, controller and keyboard use, scaling, safe areas, readability, contrast, motion, error handling, and accessibility. Use as the opposing reviewer for UI and UX deliverables.
evertonfernandes3321-wq/mythos-skills/flutter-overflow-guard Skill
0★ repoPrevine, diagnostica e prova ausencia de overflow de layout em Flutter/Dart - barras listradas de RenderFlex e seus primos (unbounded constraints, form empurrado pelo teclado, texto que nao cabe). Use ao construir, revisar ou debugar UI Flutter com Row, Column, ListView/GridView, Form, dialog ou layout responsivo, e sempre que mencionarem overflow, estourou ou estourando o layout, RenderFlex, pixels overflowed, bottom/right overflowed, layout quebrando, tela cortada, unbounded height/width, texto cortado ou teclado cobrindo o botao. Cobre Expanded/Flexible/Wrap/SingleChildScrollView/FittedBox, tabela sintoma-correcao, scanner heuristico de risco e harness de widget-test multi-device, com checklist sub-atomico (multi-size, textScaler, RTL, dark mode, SafeArea, teclado) e principios cross-stack (CSS, React Native, SwiftUI, Compose).
evertonfernandes3321-wq/mythos-skills/git-workflow-standards Skill
0★ repoPadroes de fluxo de trabalho Git para qualquer time/host (GitHub/GitLab/Bitbucket/Azure DevOps) — convencao de nomes de branch (feature/fix/hotfix/chore), Conventional Commits no formato tipo(escopo) descricao, e babysitting de PR (monitorar CI, corrigir lint/test com fixup, nunca amend em commit publicado), com gates de workflow (nao avancar sem CI verde) e modo de auditoria de conformidade do historico. Use para padronizar commits, branches e operacoes de PR/MR em qualquer stack.
lensetek/Startup-Agent-Skills-Hub/skills/developer-qa-reviewer Skill
0★ repoThe Developer QA Reviewer evaluates generated code, runs testing diagnostics, scans code repositories for credential leaks, and issues code quality verdicts.
lensetek/Startup-Agent-Skills-Hub/skills/devops-git-guard Skill
0★ repoThe DevOps Git Guard acts as a pre-push gatekeeper and documentation auditor. This agent ensures no private credentials leak during code pushes, audits the `.gitignore` setup, and updates the repository's documentation (`README.md`) before any branch merges.
SoftwareOneHN/dev-kit/references/code-review Skill
0★ repoReview code quality with adversarial rigor. Supports input modes: pending changes, PR number, commit hash, codebase scan. Always-on red-team analysis finds security holes, false assumptions, and failure modes.
tjrice42/design-judgment-skills/portfolio-critique Skill
no license0★ repoRun a structured, multi-lens critique of a design portfolio, case study, or portfolio prototype — evaluating storytelling, content choices, confidentiality risk, hiring-manager appeal, design depth, impact evidence, target-company fit, and application readiness. Use this skill whenever the user shares portfolio work and asks for feedback, critique, review, audit, or "is this good enough" / "am I ready to apply" — or mentions hiring managers, recruiters, case studies, or tailoring work for a specific company. Also trigger when reviewing a portfolio site's code or a landing page meant to showcase design work.
tjrice42/design-judgment-skills/portfolio-edit-pass Skill
no license0★ repoA screen-by-screen editorial pass over a design portfolio, case study, or portfolio prototype that flags unneeded screens and sections, recommends cuts and merges, and proposes specific visual, layout, and copy improvements. Use this skill whenever the user wants to trim, tighten, curate, declutter, or improve their portfolio before review — or asks "what should I cut," "is this screen needed," "how can this look better," or wants an edit pass before running a critique. Run this BEFORE portfolio-critique when both are in play.
muqian2026-rgb/qian-public/skills/prd-review-gate Skill
no license0★ repoPRD completeness gate before dev: boundary → module breakdown → 95% review checklist. Triggers on "PRD review", "review this PRD", "PRD gate", "acceptance criteria check".