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
jacob-balslev/skills/skills/quality-assurance/integration-test-design Skill
2★ repoUse when designing tests that verify the interaction between two or more units of a system — modules, services, layers, processes: the scope-and-boundary primitives that distinguish integration from unit and e2e tests, the test-pyramid (Cohn 2009) and test-trophy (Dodds) frameworks for how much integration testing belongs in the suite, the real-vs-faked-collaborator decision per dependency, the test-data lifecycle (per-test setup, transaction rollback, container reset), the difference between sociable-unit tests, integration tests, and contract tests, and the failure modes (over-broad scope that mimics e2e, over-narrow scope that mimics unit, shared mutable state that produces flakes). Do NOT use for testing one unit in isolation (use testing-strategy + test-doubles-design), full user-journey testing (use e2e-test-design), consumer-driven contract verification (use contract-testing), or test-suite quality measurement (use mutation-testing).
jacob-balslev/skills/skills/quality-assurance/lint-overlay Skill
2★ repoUse when adding or enforcing lint rules as part of a test or verification plan. Extends testing-strategy with lint-specific guidance: rule selection, gate placement, failure triage, and migration planning when introducing rules to an existing codebase. Do NOT use standalone — load the base testing-strategy skill alongside it — and do NOT use for chasing a specific lint failure in one file (that is debugging).
jacob-balslev/skills/skills/quality-assurance/test-doubles-design Skill
2★ repoUse when designing or reviewing test doubles — the stand-in objects that replace real collaborators in a test: the five-kind taxonomy (dummy, stub, spy, fake, mock) from Meszaros's xUnit Test Patterns, the difference between state verification (Detroit-school, classicist) and interaction verification (London-school, mockist) and how it determines which doubles fit, the cost of doubles (fragility, false confidence, divergence from real behavior), the role of fakes as the under-used middle ground, the verify_with relationship to test-driven-development, and the heuristics for when to use a real collaborator instead of any double. Do NOT use for choosing test levels or what to test (use testing-strategy), the design discipline of writing tests first (use test-driven-development), specific mocking-library API choice (library docs), or general production stubs and feature flags (use feature-gating or domain-specific skills).
jacob-balslev/skills/skills/software-engineering-method/canonical-repo-structure Skill
2★ repoUse when organizing or cleaning a project/repository so every script, command, prompt, doc, generated artifact, compatibility shim, and legacy path has one canonical home under version control. Covers owner selection, repo-boundary verification, generated-vs-authored separation, duplicate implementation cleanup, compatibility-shim registration, delete-to-git-history discipline, timestamped changelog explanations, and path-limited commits in the owning repo. Do NOT use for ordinary branching/rebase/tag strategy alone (use `version-control`), behavior-preserving code restructuring alone (use `refactor`), documentation-sync routing alone (use `doc-updater`), or controlled category taxonomy design alone (use `taxonomy-design`).
jacob-balslev/skills/skills/software-engineering-method/ci-cd-pipelines Skill
2★ repoDesigning continuous integration and continuous delivery pipelines that turn every commit into a verified, releasable artifact and move it safely toward production. Covers the CI/CD distinction (integration vs delivery vs deployment), the pipeline as a staged graph of fast-to-slow gates, trunk-based integration and short-lived branches, build-once/promote-the-same-artifact discipline, hermetic and reproducible builds, dependency and layer caching for fast feedback, the test pyramid mapped onto pipeline stages, required status checks and branch protection, quality and security gates (lint, type-check, SAST, dependency/SCA scanning, license checks) as blocking vs advisory, artifact and container registries with immutable versioning and provenance, environment promotion (build → test → stage → prod), deployment strategies the pipeline triggers (blue-green, canary, rolling, feature-flag-gated), pipeline secrets and least-privilege CI credentials (OIDC over long-lived tokens), DORA delivery metrics (deployment frequency, lead time, change-failure rate, MTTR), flaky-test quarantine, pipeline observability, and rollback/auto-revert on failed gates. Stack-agnostic across GitHub Actions, GitLab CI, Jenkins, CircleCI, and equivalents.
jacob-balslev/skills/skills/software-engineering-method/doc-updater Skill
2★ repoEnforces the documentation-sync discipline: every code or behavior change ships its documentation in the SAME commit, never after. Provides the five-step workflow — diff the change, route each changed file to the doc that OWNS that behavior (document by ownership, not convenience), update each owning doc, verify the update actually landed, and report what was changed — plus the doc-type-purity and stale-reference gates that keep a docs corpus from drifting as code moves. Use at the pre-commit step of any task that changes code, when a change touches several docs, when renaming or deleting something that is referenced elsewhere, or whenever you are unsure which doc owns a change. Do NOT use for how to WRITE good documentation prose or pick a doc's Diátaxis type (that is a documentation-authoring skill), for choosing clear names (use `naming-conventions`), or for the broad cross-domain quality catalog (use `best-practice`).
jacob-balslev/skills/skills/software-engineering-method/version-control Skill
2★ repoUse when designing or maintaining the shape of a repository's git history — choosing a branching model, deciding rebase vs merge, sizing commits, linking commits to tracker tickets, tagging releases, running parallel work across worktrees, and resolving the merge conflicts that arise from any of the above. Covers trunk-based development, short-lived feature branches, atomic commit discipline, linear-history conventions (rebase + squash), release tagging with annotated tags and SemVer, hotfix flows from tags, and worktree lifecycle for parallel agents or contributors. Do NOT use for the words inside the commit message (Conventional Commits format, identifier naming — use `naming-conventions`), for chasing a release-pipeline failure (use `debugging`), or for reviewing a PR's content (use `code-review`).
Superpowers using git worktrees
host452b/polish/skills/superpowers-using-git-worktrees Skill
no license2★ 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
Superpowers verification before completion
host452b/polish/skills/superpowers-verification-before-completion Skill
no license2★ 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
latent-variable/agentscope/skills/pull-requests Skill
2★ repoHow to write pull requests and commits, terse style, structure, and attribution. Load when opening a PR, writing a commit, or summarizing a branch.
latent-variable/agentscope/skills/review-cycle Skill
2★ repoA standing workflow for EVERY project: branch off main, validate + test, open a PR, run it through automated review, merge once it passes clean. This is the user-scope source of truth, projects keep only their own commands (test/build/deploy), not this contract. Load whenever you're about to commit, open/respond to a PR, or merge in any repo. (Optional: enabled during onboarding.)
lhh1301506137/CoTend/skills/grill-me Skill
2★ 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, mentions "grill me", or wants one-question-at-a-time clarification where replying `1` accepts the recommended default answer.
ballisarium/aiogram-bot-skills/skills/telegram-docs-check Skill
2★ repouse when current or version-specific telegram, aiogram, or related library documentation materially affects a change; документация, limits, signatures, webhooks, payments, Mini Apps, versions.
liftli-ai/skills/skills/hot-take-risk-check Skill
2★ repoUse when the user has a spicy or risky draft and wants a second opinion before publishing — returns a verdict (SHIP IT / SHIP WITH EDITS / RETHINK), the most uncharitable plausible reading, ranked risks, and minimal edits that keep the edge.
liftli-ai/skills/skills/linkedin-text-formatter Skill
2★ repoUse when the user wants bold, italic, or monospace text for LinkedIn (or any plain-text field) — converts words to Unicode Mathematical Alphanumeric characters that survive paste, with honest guidance on accessibility costs and when not to use it.
matvej-melikhov/karpathy-llm-wiki/.claude/skills/lint Skill
2★ repoРевьюер Obsidian wiki-vault. Запускает статические проверки + script auto-fixes, затем агентские проверки (Layer 2) и LLM-fix'ы, в конце ведёт диалог с пользователем по оставшимся ask-issues. Единственный owner всего post-detection пайплайна — вызывается напрямую (`/lint`) или из ingest в конце synthesis-цикла. Триггеры: /lint, "lint", "проверка здоровья", "очисти wiki", "проверь wiki", "найди сирот", "wiki audit".
JacobStephens2/skills/review Skill
2★ repoWrite an adversarial review.
ryanbaumann/fieldwork/.agents/skills/portfolio-review Skill
2★ repoAudit publishable portfolio copy, content completeness, claims, links, canonicals, redirects, images, social metadata, accessibility, and rendered presentation. Use for every public content addition or meaningful edit before it is considered ready for review or publication.
makigjuro/cloudstack-ai-plugins/plugins/cloud-infra/skills/complete-infra Skill
2★ repoComplete infrastructure task — lint, validate, review, and submit PR. Use when an infrastructure-only branch is ready for submission — runs Terraform/Helm validation and creates the PR, skipping application/frontend checks.
makigjuro/cloudstack-ai-plugins/plugins/cloud-infra/skills/infra-lint Skill
2★ repoLint Terraform, Terragrunt, and Helm charts only — skips application and frontend checks. Use for infrastructure-only changes when /lint would be overkill.
makigjuro/cloudstack-ai-plugins/plugins/cloud-infra/skills/trivy-scan Skill
2★ repoScan Terraform and Helm charts for security misconfigurations using trivy. Use for a fast IaC security check — catches issues that `/infra-lint` doesn't (secrets, public-access defaults, missing encryption, weak TLS, over-broad IAM). Invoked automatically by `/infra-lint` and `/complete-infra`.
makigjuro/cloudstack-ai-plugins/plugins/dev-workflow/skills/code-review Skill
2★ repoReview code changes for security, architecture, and quality issues. Use for deep PR-level review -- checks OWASP vulnerabilities, hexagonal architecture violations, code smells, and test gaps. For a quick architecture-only check, use /check-architecture instead.
makigjuro/cloudstack-ai-plugins/plugins/dev-workflow/skills/complete-task Skill
2★ repoComplete current task with all quality gates, code review, QA check, and submit PR. Use when implementation is done and you want to run the full verification pipeline (build, lint, tests, review, QA) and create the pull request.
makigjuro/cloudstack-ai-plugins/plugins/dev-workflow/skills/lint Skill
2★ repoRun all linters and formatters -- dotnet format, ESLint, helm lint, and terraform validate. Use to verify formatting before a PR. Note that hooks auto-fix on save/commit; this skill is for explicit verification across the full codebase. For infrastructure-only changes, use /infra-lint instead.
makigjuro/cloudstack-ai-plugins/plugins/dev-workflow/skills/run-tests Skill
2★ repoRun .NET tests with smart change detection -- auto-detects changed files via git diff and runs only affected test projects. Use whenever the user wants to run tests, verify changes, check if tests pass, run unit tests, integration tests, or test a specific service.
makigjuro/cloudstack-ai-plugins/plugins/dev-workflow/skills/task-check Skill
2★ repoQA check to verify implementation matches GitHub issue requirements. Use to validate that all acceptance criteria from the linked issue are met before creating a PR.
makigjuro/cloudstack-ai-plugins/plugins/dotnet-architect/skills/check-architecture Skill
2★ repoVerify hexagonal architecture layer rules, Result pattern usage, and coding conventions. Use as a quick local check during development -- fast and focused on architecture rules only. For full security + quality review, use /code-review instead.
makigjuro/cloudstack-ai-plugins/plugins/react-developer/skills/verify-feature Skill
2★ repoAuto-detect changed frontend routes, navigate them with Playwright, take screenshots, and check for console/network errors. Use after implementing a frontend feature to verify it works visually — auto-detects routes from git changes or accepts a route argument. Supports --responsive for mobile testing and --interactive for click testing.
Sequenzy/skills/skills/emaildesignskill Skill
2★ repoUse when Codex, Hermes, OpenClaw, Claude Code, Cowork, or another AI agent needs to plan, review, implement, audit, or improve email work focused on responsive email design, component systems, dark-mode behavior, and accessibility checks. Triggers include requests about template critique, module system planning, dark-mode QA, layout fixes, accessibility reviews, and design-to-email handoff.
The same file is in 2 other repositories
yu-iskw/skill-inspector/.claude/skills/lint-and-fix Skill
2★ repoRun linters and fix violations, formatting errors, or style mismatches using Trunk. Use when code quality checks fail, before submitting PRs, or to repair "broken" linting states.
Verification before completion
bryanwhl/skill-graph/.agents/skills/verification-before-completion Skill
2★ 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
5dive-ai/skills/code-review Skill
2★ repoReview a diff or pull request for correctness and quality — logic bugs, edge cases, error handling, race conditions, missing tests, API misuse, performance, and readability. Use when reviewing a PR, auditing a change before merge, giving feedback on someone's code, or self-reviewing your own diff. Keywords code review, PR review, pull request, diff review, review my changes, approve, request changes.
5dive-ai/skills/loops Skill
2★ repoThe full lifecycle for agentic loops — recurring, scheduled AI agents packaged as a portable LOOP.md (the agenticloops.dev standard: a trigger + skills + a prompt in one file any harness can install and run on a schedule). Use this whenever the user wants to FIND, INSTALL, RUN, or BUILD a loop: "find a loop for X", "is there a loop that…", "install a recurring agent that does X", "run this loop", as well as "create a loop", "make an agentic loop", "write a LOOP.md", "turn this into a recurring agent", "schedule an agent", "set up a cron job for an agent", or any description of a repeating job they want an agent to do on a timer (a daily digest, a competitor watcher, a triage sweep, a report pipeline, "email me X every morning", "check Y every hour") — even if they never say the word "loop". Always search the directory first and install an existing loop when one fits; author a new LOOP.md only when nothing does. This is the loop-level analogue of skill-creator + find-skills combined. For an ad-hoc in-session multi-agent run (spawn, verify, panel, fan-out) use the `loops` skill instead; for authoring a reusable SKILL.md use skill-creator.
allanbian1017/skills/skills/development/git-master Skill
2★ repoMUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). STRONGLY RECOMMENDED: Use with task(category='quick', load_skills=['git-master'], ...) to save context. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.
allanbian1017/skills/skills/development/review-work Skill
2★ repoReviews uncommitted code changes using a dynamic pipeline that scales from a single reviewer to parallel specialized reviewers (Bug Hunter, Rules Auditor) based on diff size.
allanbian1017/skills/skills/personal/review-suggestions Skill
2★ repoReview pending AI suggestions from processed reports. Presents unreviewed suggestions as an artifact, collects Accept/Reject feedback, and updates the user preference profile. Use when the user says 'review my suggestions', '幫我看建議', 'check my suggestions', 'review AI suggestions', or any request to review AI analysis recommendations.
allanbian1017/skills/skills/productivity/grill-me Skill
2★ 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 3 other repositories
Vix0007/vixero-skills/skills/goal-criteria Skill
2★ repoTransform a vague task into verifiable success criteria with a checkable plan. Use when the user says "define success", "what should I check", "how do I know it works", "how do I test this", or hands over a loose imperative like "fix the auth system", "make it faster", or "clean this up". Returns a plan where each step pairs with a verification method, plus a rollback criterion.
Vix0007/vixero-skills/skills/token-budget-check Skill
2★ repoPre-flight check a prompt, message, or instruction for token cost and waste before it is sent. Use when the user asks to check, estimate, pre-flight, size-up, or budget a prompt before sending. Returns an estimated token count, a waste breakdown, and a ranked list of cuts with a proposed lean rewrite.
tommylower/cortex/agent-workflows/codex-review Skill
2★ repoSet up Codex plugin for cross-model code review and task delegation inside Claude Code
tommylower/cortex/design/review/agentation-self-driving Skill
2★ repoAgentation self-driving design review. Use when the user asks to critique a page, add design annotations, auto-annotate, or run a visible browser-based UI review through the Agentation toolbar. Requires Agentation and agent-browser.
tommylower/cortex/design/review/preflight Skill
2★ repoPreflight design review before shipping. Use for static UI/a11y checks, visual consistency, AI-slop detection, or a final component/page ship check. Triggers: preflight, design review, accessibility audit, WCAG, UI polish, design critique, AI slop check.
tommylower/cortex/engineering/grill-me Skill
2★ 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".
tommylower/cortex/engineering/grill-with-docs Skill
2★ 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, or is starting to build something new and the design is not yet pinned down. In-session skill; the async hand-off counterpart is improve.
tommylower/cortex/engineering/prototype Skill
2★ 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".
a-novel-kit/stack/.agents/skills/git-conventions Skill
2★ repoGit workspace hygiene (clean-tree pre-flight, pruning a scratch stack), branch naming, commit message format, and workflow conventions for Agora backend services. Use it whenever starting or finishing work in a checkout, creating a branch, writing a commit message, or grouping changes. Referenced by implement-feature and any other skill that touches git. Pair with attribute-ai-commits whenever an AI agent materially contributed to a commit.
a-novel-kit/stack/.agents/skills/manage-versions Skill
2★ repoCross-repo version management for a-novel / a-novel-kit. Load it whenever a change spans repos that must stay version-compatible to merge — an unreleased `golib` or `pkg/go` dependency, a proto or REST contract change, a breaking change to a published symbol. Covers git-tag semver, exact `go.mod` pins, commit-SHA pseudo-versions, the dependency-releases-FIRST merge order (the consumer re-pins to the released tag), and staged rollouts. Pairs with `git-conventions`, `implement-feature`, `open-pull-request`, `write-*`.
a-novel-kit/stack/.agents/skills/monitor-ci Skill
2★ repoMonitor GitHub Actions CI runs on a pushed branch or open PR, classify failures, and fix them where safe. Use whenever waiting on CI, investigating a failing check, judging a failure real or flaky, or iterating a branch to green. Covers the Agora CI job map and the retry/fix loop. Pairs with open-pull-request (the post-push handoff) and git-conventions.
a-novel-kit/stack/.agents/skills/open-pull-request Skill
2★ repoPush a branch and open a GitHub pull request for Agora backend services. Use whenever shipping work — features, fixes, refactors, chores. Covers pre-flight checks, base branch, PR title and body, draft mode, and updating an existing PR instead of re-creating it. Pairs with git-conventions (commit/branch format) and monitor-ci (post-push CI).
a-novel-kit/stack/.agents/skills/resolve-pr-feedback Skill
2★ repoSurvey a pull request's state (CI, review threads, reviewer status) and work through reviewer feedback on any repo in the a-novel / a-novel-kit orgs. Use it when checking on an open PR, reading Copilot or human review comments, replying on or resolving a thread, re-requesting review, or answering comments under an issue. Pairs with plan-feature, which owns the issue body.
morning-start/agent-skills/process/agents-writer/skills/4-gate-check Skill
no license2★ repo21 项质量门禁验收 — 逐条检查 AGENTS.md 是否符合战略、行为、格式三层质量标准,输出结构化验收报告
morning-start/agent-skills/process/doc-orchestrator/skills/doc-phase-quality/completeness-checker Skill
no license2★ repoUse when the user needs to check whether a document has all required sections, examples, and supporting material.
morning-start/agent-skills/process/doc-orchestrator/skills/doc-phase-quality/consistency-checker Skill
no license2★ repoUse when the user needs terminology, traceability, or formatting consistency checks across documents.
morning-start/agent-skills/process/tutorial-writer/skills/tutorial-writer-review Skill
no license2★ repoUse when checking, reviewing, scoring finished tutorial content, or running quality gates before delivery
morning-start/agent-skills/tool/git Skill
no license2★ repoGit版本控制技能,掌握仓库管理、提交操作、分支协作、远程同步等核心能力,提供安全的操作指导和故障排除
Maples7/Apple-Dev-AI-Skills/skills/pre-commit-review Skill
2★ repoReview uncommitted Apple-platform changes across seven lenses — performance, user experience, test coverage, architecture, code style, security & privacy, and documentation — and produce a structured report with severity-graded findings before the user runs git commit. Use when the user asks to review a diff before committing, audit pending Swift / SwiftUI / Apple-platform changes for regressions, layering or style drift, security or privacy issues, missing tests, or stale docs.
quickcall-dev/skills/skills/worktree-fleet Skill
2★ repoIndependence-validated parallel fleet that runs each worker (claude -p, codex exec, or pi -p) in its own git worktree. Use when tasks touch non-overlapping files and you need merge-safe isolation (each worker on its own branch). For DAG-ordered one-shot workers with budgets, use dag-fleet. For headless iteration with a reviewer loop, use iterative-fleet.
The same file is in 1 other repository
nevitonsantana/adaptive-skills/skills/architecture-review Skill
no license2★ repoReview boundaries, coupling, complexity, and maintenance cost before consolidating a structural decision.
nevitonsantana/adaptive-skills/skills/checkpoint-review Skill
no license2★ repoInsert a short review pause between rounds so work can continue, stop, or hand off with better discipline.
nevitonsantana/adaptive-skills/skills/observability-review Skill
no license2★ repoDesign or review metrics, events, alerts, and diagnostics so they support real decisions and expose real failure.