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
philpalmieri/engineering-manager-skills/skills/metrics/review-cycles Skill
1★ repoTrack PR review rounds (feedback cycles) before merge per person and over time. Surfaces who consistently needs many iterations vs ships cleanly, and whether individuals are improving. Uses enrichment data for accurate round counts. Use when asked about review quality, iteration patterns, or PR friction.
philpalmieri/engineering-manager-skills/skills/metrics/review-network Skill
1★ repoAnalyze the team's code review network: who reviews whom, reciprocity ratios, network density, and time-series comparison. Surfaces siloed review patterns and shows improvement toward distributed collaboration. Use when asked about review dynamics, collaboration patterns, or team connectivity.
philpalmieri/engineering-manager-skills/skills/orchestration/context-check Skill
1★ repoValidate and rebuild session context awareness. Checks that key paths, skills, data structures, and configurations are accessible and properly indexed. Use when behavior seems off, after long breaks, or proactively before complex tasks to ensure full environment awareness.
endalk200/skills/skills/conventional-commit Skill
no license1★ repoCreate git commits using Conventional Commits. Use when the user asks to commit code, prepare a commit, write a commit message, or standardize commit history with conventional commit types, scopes, breaking-change markers, and safe git workflow checks.
endalk200/skills/skills/grill-me Skill
no license1★ repoA relentless interview to sharpen a plan or design.
The same file is in 2 other repositories
endalk200/skills/skills/grill-with-docs Skill
no license1★ repoGrill the user relentlessly to sharpen a plan or design while maintaining ADRs and domain glossary documentation. Use when the user asks to "grill with docs" or wants decisions documented during a design interview.
The same file is in 3 other repositories
endalk200/skills/skills/prototype Skill
no license1★ repoCollection of agent skills I use in day to day work spanning engineering and none engineering work.
The same file is in 1 other repository
All-The-Vibes/ATV-PaperBoard/adapters/claude-code/_dist/skills/validate-artifact Skill
1★ repoRun ENFORCE checks on a rendered artifact slug: Google design.md lint + HTML-side color-token trace. Reports ACCEPT or FAIL with fail_class. Invokes `paperboard validate`.
All-The-Vibes/ATV-PaperBoard/adapters/copilot-cli/_dist/skills/validate-artifact Skill
1★ repoRun ENFORCE checks on a rendered artifact slug: Google design.md lint + HTML-side color-token trace. Reports ACCEPT or FAIL with fail_class. Invokes `paperboard validate`.
All-The-Vibes/ATV-PaperBoard/skills/validate-artifact Skill
1★ repoRun ENFORCE checks on a rendered artifact slug: Google design.md lint + HTML-side color-token trace. Reports ACCEPT or FAIL with fail_class. Invokes `paperboard validate`.
ravihammond/skills/skills/implement-issue Skill
1★ repoImplement one GitHub issue in the current checkout using the issue, comments, linked PRD, existing branch work, TDD, repo validation rules, and a local commit. User-invoked only; require an explicit issue number.
ravihammond/skills/skills/review-issue Skill
1★ repoReview and repair one GitHub issue implementation in the current checkout.
almasumdev/awesome-mobile-release-agent-skills/.github/skills/versioning/semantic-versioning-mobile Skill
no license1★ repoApply SemVer to mobile apps — versionName, versionCode, CFBundleShortVersionString, CFBundleVersion, and release branching. Use this when bumping versions or designing branch strategy.
davidvictor/adlc-skills/skills/adlc/adlc-commit Skill
1★ repoPrepare conventional commits from verified staged work and ADLC commit plans.
davidvictor/adlc-skills/skills/adlc/adlc-review Skill
1★ repoReview staged or working-tree changes with ADLC context and read-only gate output.
davidvictor/adlc-skills/skills/adlc/adlc-rules-check Skill
1★ repoRun a read-only ADLC rules compliance gate for plans, diffs, or release candidates.
davidvictor/adlc-skills/skills/adlc/adlc-verify Skill
1★ repoVerify implementation completeness against ADLC plans, rules, and repo behavior.
liuqi1024/matrix-boot/skills/implementation-verification Skill
1★ repoVerify generated or modified application code with reproducible build, test, runtime, browser, API, console, and network checks. Use after code generation or bug fixes, especially for web UI login flows, forms, dashboards, frontend/backend integration, local dev servers, and claims that implementation is complete or tested.
vmvenkatesh78/engineering-skills/skills/generator-reviewer-loop Skill
1★ repoTwo-pass code delivery discipline. Use for EVERY code task — writing, reviewing, debugging, refactoring, implementing features, fixing bugs, producing snippets, creating components, patching, or any code artifact, including prototypes, demos, and quick fixes. Enforces a Generator (Staff Engineer) pass that writes code correctly the first time against the full standards bar, followed by a Reviewer (Principal Engineer) pass that adversarially tears it apart at file, function, snippet, line, and variable granularities. Structured findings with Critical/High/Medium/Low severity. 10/10 confidence gate blocks delivery until zero Critical, zero High, zero Medium findings remain and final verdict is Ready to Merge. No exceptions for task size.
vmvenkatesh78/engineering-skills/skills/runtime-behavior-review Skill
1★ repoRuntime behavior analysis layer for every infrastructure, observability, monitoring, middleware, rate-limiting, health-check, readiness-probe, metrics-collection, caching, queueing, or system-lifecycle PR. Catches what static code review misses — self-measurement contamination, cumulative-vs-windowed metric confusion, boundary math at small sample sizes, shutdown/drain race conditions, config flags that are semantic no-ops, middleware ordering that changes what gets measured, probe interference with business metrics, and metric exposure without auth. Composes with generator-reviewer-loop and triple-pass-review-loop as an additional mandatory checklist that runs AFTER Stage 2 (Reviewer) and BEFORE Stage 3 (Reviewer-of-Reviewer). Operates at the "2 AM prod is down" level — the question is never "does this compile" but "what happens to this code when 400 instances are draining, GC is spiking, the load balancer is probing every 5 seconds, and the on-call engineer is reading the dashboard this code powers."
vmvenkatesh78/engineering-skills/skills/triple-pass-review-loop Skill
1★ repoThree-pass code delivery discipline — Generator, Reviewer, Reviewer-of-Reviewer. Use for EVERY code task — writing, reviewing, debugging, refactoring, implementing features, fixing bugs, producing snippets, creating components, patching, or any code artifact, including prototypes, demos, and quick fixes. Generator (Staff Engineer) writes against the full standards bar. Reviewer (Principal Engineer) tears it apart adversarially at six granularities. Reviewer-of-Reviewer (Founding Architect) audits the Reviewer's work — catches missed findings, severity errors, rationalizations, and process violations. 10/10 confidence gate blocks delivery until zero Critical, zero High, zero Medium findings remain AND all proposed fixes are verified. No exceptions for task size.
dillonschultz93/quieto-skills/design-token-contrast Skill
1★ repoCheck WCAG contrast ratios between color pairs or across your token system semantic foreground/background pairings. Use when the user wants to verify accessibility compliance for specific colors or their entire token palette.
zhjai/grill-all/plugins/grill-all/skills/grill-all Skill
1★ repoUse when stress-testing a coding plan or design and the right answers may come from the human, project docs, codebase, or the web.
agentjido/jido-skills/.agents/skills/pr-review Skill
1★ repoReview a Pull Request for code quality, tests, merge conflicts, and readiness to merge. Use when asked to review a PR, check if a PR is ready to merge, or analyze PR code quality.
agentjido/jido-skills/.cursor/skills/pr-review Skill
1★ repoReview a Pull Request for code quality, tests, merge conflicts, and readiness to merge. Use when asked to review a PR, check if a PR is ready to merge, or analyze PR code quality.
agentjido/jido-skills/.gemini/skills/pr-review Skill
1★ repoReview a Pull Request for code quality, tests, merge conflicts, and readiness to merge. Use when asked to review a PR, check if a PR is ready to merge, or analyze PR code quality.
agentjido/jido-skills/source/skills/pr-harden Skill
1★ repoHarden a pull request by fixing blocking review findings, strengthening regression tests, validating locally, pushing to the PR branch, and updating AgentJido review-state labels. Use only when explicitly asked to fix a PR.
agentjido/jido-skills/source/skills/pr-review Skill
1★ repoReview pull requests for correctness, tests, merge readiness, CI status, conflicts, and AgentJido review-state labels. Use when asked to review a PR, check if it is ready to merge, or provide PR feedback without editing code.
pjankiewicz/skills/skills/ux-review Skill
1★ repoUse when auditing or reviewing the UX/interaction quality of a mobile (iOS/Android) or web app — checking whether screens have distinct pressed/focus/disabled states, proper empty/loading/error states, accessible touch targets, platform-native conventions (Apple HIG / Material 3), WCAG 2.2 AA contrast, honest system status feedback, and clear copy. Provides a per-screen PASS/FAIL heuristic rubric (~55 criteria across 9 sections) grounded in Nielsen's 10 heuristics, Apple Human Interface Guidelines, Material Design 3, and WCAG 2.2. Triggers on "UX review", "design review", "audit the UI", "heuristic evaluation", "does this screen feel right", "accessibility pass", "review my app's UX", "why does this feel janky". Skip for pure visual/brand image generation (use a design-generation skill) or backend/logic review.
GerardoRdz96/aios-starter-kit/.claude/skills/grill-me Skill
1★ repoUse PROACTIVELY whenever the user is working something OUT OF THEIR HEAD rather than asking a quick question — mulling or scoping a plan/design/decision, describing how they do something, or floating a half-formed idea to capture. Natural signals: "I've been thinking about…", "I have an idea for…", "I want to build/plan/figure out…", "let me think this through", "help me scope this", "here's how I do X". Also the explicit "grill me", "interrogate me", "stress-test this", "/grill-me". One-question-at-a-time extraction into a durable doc. SAFETY: unless they explicitly asked to be grilled, OFFER first and wait for yes — never silently launch a long interview on a quick question.
GerardoRdz96/aios-starter-kit/.claude/skills/multi-brain Skill
1★ repoMulti-LLM auto-router. Your main assistant orchestrates and routes a sub-task to a different model ONLY when that model fits the job better; the user talks to one assistant the whole time. The roster is yours to fill in. Fires automatically when a routing rule matches. NO-SELF-REVIEW LAW: when the user asks you to "check / review / verify / sanity-check / second-opinion" ANY work YOU just produced, route the review to a model from a DIFFERENT lineage if one is on the roster. Triggers: "check your work" · "review what you just did" · "is this right?" · "second opinion" · "sanity check" · "double-check" · "make sure this works".
fbarrento/laravel-agent-kit/.agents/skills/grill-me Skill
no license1★ 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 23 other repositories
fbarrento/laravel-agent-kit/.agents/skills/grill-with-docs Skill
no license1★ 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 11 other repositories
fbarrento/laravel-agent-kit/.agents/skills/prototype Skill
no license1★ repoBuild a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic 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", "try a few designs".
The same file is in 11 other repositories
fbarrento/laravel-agent-kit/archive/product-pipeline/idea-grill Skill
no license1★ repoPressure-tests a half-formed product or feature idea on desirability, strategy, and user experience — never on feasibility or implementation — until it is sharp enough to scope. Use when an idea is vague and needs interrogating before it enters the pipeline. Produces a transient readied-idea stub that change-scope consumes. Optional front door; a well-formed idea can go straight to change-scope.
fbarrento/laravel-agent-kit/archive/product-pipeline/vision-grill Skill
no license1★ repoPressure-tests a product on strategy, positioning, market, and reason to exist — never on feasibility or implementation — until it is sharp enough to set a vision from. Use when a product idea is vague and needs interrogating before product-vision runs. Produces a transient readied-idea stub that product-vision consumes. Optional front door; a clear product idea can go straight to product-vision.
fbarrento/laravel-agent-kit/skills/git-conventions Skill
no license1★ repoCanonical naming + message rules for commits, pull request titles, and branch names using Conventional Commits. Defines the shared type vocabulary (feat, fix, refactor, chore, docs, test, perf, build, ci, style, revert), subject grammar, body/footer format, co-author trailer, breaking-change marking, and issue references. Use when writing or reviewing a commit message, naming a PR, or naming a branch. Framework-agnostic — applies to any repo.
The same file is in 1 other repository
fbarrento/laravel-agent-kit/skills/new-task Skill
no license1★ repoCreates a fresh task branch from the latest remote main branch using conventional-commit branch naming. Use when starting any new coding task, bug fix, refactor, feature, chore, documentation change, or user request that will modify repository files.
The same file is in 1 other repository
jasontang-ai/acp/skills/protocol-implementer-review Skill
1★ repoUse this skill to review whether an external implementation or adapter follows ACP protocol semantics and discovery expectations.
nianbaizy/grad-agent-kit/skills/reviewer-simulator Skill
1★ repoReusable AI agent skills for research writing, experiment analysis, academic presentation, reviewer simulation, and project delivery.
coreline-ai/codex-devflow-plugin/skills/plan-eng-review Skill
1★ repoEngineering-manager style implementation plan review. Use when asked to review architecture, lock in an execution plan, assess data flow, edge cases, test coverage, performance, rollout risk, or perform an engineering review before coding.
andrey-learning-machines/swe-harness/plugins/swe-harness/skills/unicorn-javascript Skill
1★ repoGuides JavaScript and TypeScript development with modern tooling and patterns. ALWAYS trigger on "typescript", "javascript", "tsconfig", "eslint", "prettier", "vitest", "jest", "react", "node.js", "express", "npm", "package.json", "type error", "ts error", "js project setup", "frontend testing", "react hooks", "discriminated union", "type guard". Use when configuring TS/JS tooling, writing tests, structuring React or Node apps, or debugging type issues. Different from testing skill which covers general strategy; this covers JS/TS-specific test patterns and framework configs.
andrey-learning-machines/swe-harness/plugins/swe-harness/skills/unicorn-python Skill
1★ repoGuides Python development with modern idioms, tooling, and project structure. ALWAYS trigger on "python project", "pyproject.toml", "ruff", "mypy", "pytest", "poetry", "python setup", "type hints", "pydantic", "dataclass", "async python", "asyncio", "python anti-pattern", "python best practices", "python tooling", "python lint". Use when setting up Python projects, configuring tooling, choosing data modeling approaches, or writing tests. Different from testing skill which covers general test strategy; this covers Python-specific pytest patterns and tooling configs.
andrey-learning-machines/swe-harness/plugins/swe-harness/skills/unicorn-self-verification Skill
1★ repoGuides the user through systematic pre-commit quality verification. ALWAYS trigger on "review my code", "check my work", "before commit", "self-review", "quality check", "am I ready to commit", "pre-commit review", "code quality", "verify my changes", "sanity check", "review before merge", "is this ready". Use before any commit, merge, or code review submission.
VdustR/skills/skills/vp-cspell Skill
1★ repoReusable Agent Skills by VdustR
VdustR/skills/skills/vp-git-cleanup Skill
1★ repoReusable Agent Skills by VdustR
VdustR/skills/skills/vp-pr-briefing Skill
1★ repoReusable Agent Skills by VdustR
VdustR/skills/skills/vp-pr-review-followup Skill
1★ repoReusable Agent Skills by VdustR
VdustR/skills/skills/vp-stacked-pr-rebase Skill
1★ repoReusable Agent Skills by VdustR
pavelsimo/skills/skills/create-cli Skill
no license1★ repoScaffolds production-ready CLI projects from language templates, supporting Go with Cobra, Makefile, golangci-lint, goreleaser, and GitHub Pages docs; and Python with Typer, uv, ruff+mypy, PyPI OIDC trusted publishing, and GitHub Pages docs. Use when the user wants to bootstrap a new command-line tool project from scratch.
pavelsimo/skills/skills/review Skill
no license1★ repoPerforms deep, evidence-first code review on local diffs, staged changes, branch comparisons, or GitHub PRs and issues, with severity-annotated findings. Use when the user wants to review code changes, audit a pull request, or investigate a GitHub issue.
Soham407/studio-kickstart/architecture/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
Soham407/studio-kickstart/architecture/grill-me Skill
1★ 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 23 other repositories
Soham407/studio-kickstart/architecture/grill-with-docs Skill
1★ 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 8 other repositories
Soham407/studio-kickstart/architecture/prototype Skill
1★ repoBuild a throwaway prototype to flush out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic 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", "try a few designs".
Soham407/studio-kickstart/architecture/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
mo-hawary/hawary-workflow-skills/skills/project-status-dashboard Skill
1★ repoBuild a read-only project health dashboard from git state, docs, CI hints, open work, branch drift, and likely next steps.
mo-hawary/hawary-workflow-skills/skills/pull-request-review-loop Skill
1★ repoReview pull requests with adversarial findings, fix validation, re-review loops, local artifacts, and source-backed proof before merge.
mo-hawary/hawary-workflow-skills/skills/repo-workflow-checker Skill
1★ repoCheck whether a repo has an agent workflow scaffold: instructions, work queues, specs, skills, verification commands, and archive conventions.
riz007/architect-os/skills/aos-generate Skill
1★ repoMulti-agent full-stack feature generator. Dispatches four specialised subagents — Architect, Backend Engineer, Frontend Engineer, Reviewer — to design, generate, and review a complete vertical slice in one pass. Use when user wants to generate a complete feature end-to-end, says "generate the full feature", or needs fullstack scaffolding beyond what /aos-feature provides.