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
Ghosteken/agent-harness/skills/ui-review Skill
1★ repoReview UI code for StyleSeed design-system compliance, accessibility, mobile ergonomics, spacing discipline, and implementation quality.
The same file is in 3 other repositories
Verification before completion
Ghosteken/agent-harness/skills/verification-before-completion Skill
1★ repoClaiming work is complete without verification is dishonesty, not efficiency. Use when ANY variation of success/completion claims, ANY expression of satisfaction, or ANY positive statement about work state.
The same file is in 4 other repositories
hu553in/skills/staged-code-review Skill
no license1★ repoPerform an exhaustive iterative code review of all staged Git changes, fix every actionable issue found, and leave all new fixes unstaged. Use when the user asks for full review of staged changes, pre-commit review, release-prep review of staged changes, or similar staged-review requests covering correctness, tests, architecture, consistency, performance, invariants, user experience, documentation, and cleanup while preserving the staged index.
AlexStormwood/agentic-skills/conventional-commit-summary Skill
1★ repoGenerate concise one-line Conventional Commit summaries for work completed by an AI agent. Use when Codex needs to summarise code changes, file edits, documentation updates, tests, refactors, fixes, generated assets, breaking changes, or other repository work as a brief git commit message with type, optional scope, optional breaking-change marker, and no extended description.
batur/ts-baseline-docs/.agents/skills/cicd-git Skill
1★ repoEnforces CI/CD and Git workflow standards for TypeScript projects. Use when creating or reviewing branches, commits, pull requests, GitHub Actions, deployment pipelines, release/versioning, CODEOWNERS, hooks, secret scanning, OpenAPI checks, migrations, raw SQL gates, or day-one deployability.
batur/ts-baseline-docs/.agents/skills/config-environment Skill
1★ repoEnforce TypeScript config and environment rules. Use when adding or reviewing env variables, process.env usage, Zod env validation, server/client config separation, secrets, public env exposure, feature flags, provider config, .env.example, or adapter initialization.
batur/ts-baseline-docs/.agents/skills/eslint Skill
1★ repoEnforce and review the TypeScript ESLint baseline for this project. Use when creating or reviewing ESLint flat config, lint rules, imports, exports, naming, file names, side-effect imports, environment access, component boundaries, or provider/SDK dependency restrictions in TypeScript code.
batur/ts-baseline-docs/.agents/skills/validation Skill
1★ repoApply the project's Zod runtime validation standard for TypeScript APIs, forms, env/config, webhooks, third-party responses, and AI outputs. Use when creating or reviewing schemas, DTO inputs, request body/query/path parsing, PATCH validation, Zod error mapping, or boundary validation.
VoldemortGin/AI-Coding-Skill-Bible/java-project-standard Skill
1★ repoEnforce a strict, model-agnostic, AI-navigable Java project standard: the Java compiler plus `-Werror` + `-Xlint:all` as the baseline, **Error Prone** (bug-pattern checks as errors, the clippy/detekt analog) and **NullAway** (JSpecify `@Nullable`, null-safety at compile time — the Kotlin null-safety / Swift optional analog) as the static guarantee, **Spotless** with google-java-format as the format gate, sealed error hierarchies + exhaustive `switch` (no silent failures), **TDD with a JaCoCo coverage floor in the gate**, Jackson at boundaries with lightweight record compact-constructor validation, a Gradle multi-module module-per-domain structure, a zero-SDK zero-framework `:domain` module behind provider interface seams with a default `MockProvider`, a manual composition root (no DI framework), a version catalog pinning every version, a CLAUDE.md in every module, and scaffold/conformance scripts. Use whenever starting or scaffolding a Java project; setting up Gradle / settings.gradle.kts / libs.versions.toml / Error Prone / NullAway / Spotless / JaCoCo / CI; deciding module structure; adding an LLM / embedding / vector-store dependency; wiring providers or adapters; or checking that an existing Java project conforms. Apply it even when the user only says "start a Java project", "set up the structure", "add an LLM", or "wire up CI" without naming the standard. This skill governs the Java host's internals; it is complementary to polyglot-core-standard, which governs the cross-language seam (a Rust core + a JNI/JNA/Panama-FFM bridge — Java has no official UniFFI support).
VoldemortGin/AI-Coding-Skill-Bible/python-project-standard Skill
1★ repoEnforce a strict, type-safe, model-agnostic, AI-navigable Python project standard: mypy --strict + beartype runtime type-checking + pydantic at boundaries + provider Protocol seams (zero-SDK core) + src layout with a real package name + domain-first deep structure + centralized config/logging/prompts + a one-command zero-warning gate + drift guards. Use this whenever starting or scaffolding a new Python project, service, or package; setting up pyproject/ruff/mypy/pytest; deciding where code, config, or prompts belong; adding type checking, runtime validation, or an LLM/embedding/vector-store dependency; organizing or deepening package structure; wiring providers; setting up CI or pre-commit; or checking that an existing Python project conforms. Apply it even when the user only says "start a Python project", "set up the repo", "add types", "wire up an LLM", or "structure this", without naming the standard.
monikazapisek/design-engineering-playbook/skills/socratic-dialogue Skill
1★ repoReasoning rigor and anti-sycophancy guard for high-stakes decisions. Refuses to answer until the question is anchored to operational definitions, cross-examined against prior commitments, and validated by an internal faithfulness check. For high-stakes, ambiguous, or strategically loaded reasoning.
Da-loong/agent-skill-os/skills/code-reviewer Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete code reviewer work with a reliable workflow.
Da-loong/agent-skill-os/skills/performance-reviewer Skill
1★ repoA reusable Agent Skill OS skill that helps AI coding agents complete performance reviewer work with a reliable workflow.
yiyaw-lab/agent-armor/commit-mine Skill
1★ repoCommit ONLY this session's work out of a shared dirty tree where parallel agent sessions have uncommitted edits in the same files. Positive hunk selection, staged-snapshot test (checkout-index + suite), and a foreign-symbol check before every commit. Use whenever git status shows modifications you didn't all make.
yiyaw-lab/agent-armor/tidy Skill
1★ repoThe judgment layer for workspace hygiene — resolves the loose ends the hygiene hook SURFACES with the reasoning a bash reconciler cannot do: branch-supersession triage (merged-equivalent-via-squash vs real-unmerged vs stale-divergent vs sibling-superseded), push/PR decisions, worktree-removal calls, and PR-state awareness. The on-demand judgment sibling of the always-on workspace-reconcile hook (which auto-cleans only the provably-safe and surfaces the rest). Verify-before-delete; reversible-only; propose-on-approval; never deletes unmerged work or a peer's worktree. Modes: <repo> (triage + propose + act on approval) | audit (read-only report) | apply.
yiyaw-lab/agent-armor/until Skill
1★ repoGoal-pursuit engine — attempt, verify, adjust until a pinned objective is verifiably done. Negative-control verification, a hypothesis ledger that forbids re-testing refuted ideas, git checkpoints, and a forced escalation ladder (switch layers → fresh-context subagent → attack the goal itself). Survives session death via a state file. (For time-based recurrence, use the built-in /loop instead.)
AdrianParedez/capability-fabric/skills/verifying-reasoning Skill
1★ repoA fast, on-demand check that catches wrong answers before they ship, surface assumptions, seek disconfirming evidence, and validate the result against the question. Use before committing to a high-stakes conclusion, an irreversible action, or a final answer. Invoked as a quality gate by decomposing-tasks, progressive-research, guarding-code-quality, and the meta-skills.
vasu-devs/Forge/skills/review Skill
1★ repoReview code changes for correctness and quality before merging. Use after implementing a meaningful chunk or feature, between plan tasks, or before opening a PR — to catch issues while they're cheap.
vasu-devs/Forge/skills/verify Skill
1★ repoProve that work is actually complete, fixed, or passing before saying so. Use right before claiming success, marking a task done, committing, or opening a PR — any moment you're about to assert that something works.
Cloudflare domain registration
nachoal/my-skills/plugins/codex/my-skills/skills/cloudflare-domain-registration Skill
1★ repoCheck availability and register domains through Cloudflare Registrar. Use when asked to buy, purchase, register, check, price, or verify a domain on Cloudflare Registrar with CLOUDFLARE_REGISTRAR_TOKEN.
Cloudflare domain registration
nachoal/my-skills/skills/cloudflare-domain-registration Skill
1★ repoCheck availability and register domains through Cloudflare Registrar. Use when asked to buy, purchase, register, check, price, or verify a domain on Cloudflare Registrar with CLOUDFLARE_REGISTRAR_TOKEN.
Razaib-khan/ForgeWeave/src/forgeweave/templates/claude/.claude/skills/quick-research Skill
1★ repoLightweight single-pass search for fast answers when context is missing. Use this skill whenever the agent needs to: look up an API signature, verify a library version, check a CLI flag, find a code example, research an error message, or confirm a configuration option. Triggers automatically when you are about to write code with an unfamiliar library or encounter a gap in context. NOT for comprehensive research — use deep-research for that.
Razaib-khan/ForgeWeave/src/forgeweave/templates/claude/.claude/skills/validation-engine Skill
1★ repoChecks outputs from other skills for consistency, correctness, and adherence to AGENTS.md rules
Razaib-khan/ForgeWeave/src/forgeweave/templates/gemini/.gemini/skills/quick-research Skill
1★ repoLightweight single-pass search for fast answers when context is missing. Use this skill whenever the agent needs to: look up an API signature, verify a library version, check a CLI flag, find a code example, research an error message, or confirm a configuration option. Triggers automatically when you are about to write code with an unfamiliar library or encounter a gap in context. NOT for comprehensive research — use deep-research for that.
Razaib-khan/ForgeWeave/src/forgeweave/templates/gemini/.gemini/skills/validation-engine Skill
1★ repoChecks outputs from other skills for consistency, correctness, and adherence to AGENTS.md rules
Razaib-khan/ForgeWeave/src/forgeweave/templates/qwen/.qwen/skills/quick-research Skill
1★ repoLightweight single-pass search for fast answers when context is missing. Use this skill whenever the agent needs to: look up an API signature, verify a library version, check a CLI flag, find a code example, research an error message, or confirm a configuration option. Triggers automatically when you are about to write code with an unfamiliar library or encounter a gap in context. NOT for comprehensive research — use deep-research for that.
Razaib-khan/ForgeWeave/src/forgeweave/templates/qwen/.qwen/skills/validation-engine Skill
1★ repoChecks outputs from other skills for consistency, correctness, and adherence to AGENTS.md rules
nyechiel/ai-augmented-workflow/skills/review Skill
1★ repoEnd-of-day or end-of-week review covering work output, wins/risks/opportunities. Weekly output is sharable with your manager.
vladcheck/skills/git-sequential Skill
1★ repoUse when a pile of uncommitted changes (or one big commit/diff) should become a clean sequence of logical commits — incremental commits, splitting a big change, building a readable history as if the work were done step by step, staging hunks selectively before a PR.
gjbex/scientific-computing-skills/skills/scientific-numerics-review Skill
1★ repoReview scientific-computing and HPC code for numerical stability, conditioning, convergence logic, tolerance choices, invariants, and scientifically meaningful correctness risks that ordinary software review may miss.
gjbex/scientific-computing-skills/skills/scientific-review Skill
1★ repoReview scientific-computing repositories, pull requests, or code changes for correctness, validation, reproducibility, maintainability, documentation, and performance risks beyond ordinary software review.
srahnama/Sina/skills/sina Skill
1★ repoApply rigorous scientific method as Dr. Atlas: frame precise questions, rank falsifiable hypotheses, classify evidence strength, retrieve and verify claims, design controlled experiments, analyze data, critique methods, improve academic writing, and report uncertainty. Use when the user says "sina", "Dr. Atlas", "scientific method", "evidence-based", "hypothesis", "verify", "reproduce", "root cause", "systematic analysis", asks for proof, validation, literature reasoning, experimental design, SOTA scientific AI workflows, statistical interpretation, or reproducible research.
JCreatesGH/claude-skills/unity-headless-validation Skill
1★ repoValidate Unity C# changes from the command line — fast compile checks WITHOUT launching Unity, plus PlayMode/EditMode tests and editor automation (-executeMethod scene bakes) run in -batchmode on a lock-free clone so they work WHILE the editor is open on the project. Use WHENEVER you edit a Unity project's C# and want to know it compiles/passes without clicking into the editor or waiting on a domain reload — triggers include "does this Unity code compile", "run the Unity tests headless", "validate my Unity change", "check this without opening Unity", "rebake the scene from the CLI", "set up Unity CI", or any edit→verify loop on a project whose editor is already open. Uses Unity's own bundled Roslyn + .NET; no extra installs.
JCreatesGH/claude-skills/unity-visual-self-qa Skill
1★ repoLet an agent SEE its own Unity game — render every scene and UI popup to exact-resolution PNGs headlessly (in -batchmode via a PlayMode test), including the screen-space HUD, then review the shots by reading them and cropping/colour-probing the fiddly regions. Use WHENEVER you want to verify how a Unity game actually LOOKS without a human screenshotting — triggers include "screenshot every scene", "does the HUD look right", "capture the game headlessly", "visual QA / visual regression for my Unity game", "review my game's UI", "audit the menus/popups", or checking art/layout after a change. Pairs with headless-validation to capture freshly-baked scenes while the editor stays open. Needs the GPU render path (run batchmode WITHOUT -nographics).
Lightbridge-KS/agent-skills/plugins/coding/skills/commit-push-pr Skill
1★ repoGit workflow: commit, push, and create/update a draft PR. If a PR exists for the current branch, update its body. Trigger: 'commit push pr', 'ship it', 'send a PR', or /commit-push-pr.
fengsihao23-eng/shen-hua/skills/self-reviewer Skill
1★ repoShen-Hua self-review workflow before finishing a task. Use before final responses, commits, PRs, handoffs, or readiness claims to inspect requirements coverage, diffs, risks, tests, missed edge cases, destructive changes, and unresolved work.
fengsihao23-eng/shen-hua/skills/verification-loop Skill
1★ repoShen-Hua verification and repair loop for modified projects. Use after code/config/docs changes that need quality gates, before final readiness claims, when tests/build/lint/typecheck fail, before a PR/commit, or when the user asks Codex to check, verify, test, fix failures, or prove the current work is safe.
Colacn/agent-pipeline/skills/review Skill
1★ repoUse this skill when evaluating analyze/plan outputs before implementation, especially for feasibility, risk, security, performance, compatibility, and testability gates. It produces evidence-based pass, conditional pass, or fail conclusions.
HorizonBrute/Standardized_AI_Looping_Language-SAILL/skills/dirtree-check Skill
1★ repoWalk every tested_implementation directory that has a testing_nonce.md, collect each directory's agents.md inheritance chain and nonce via parallel haiku agents, render a directory tree showing context depth at every node, write it to documentation/lastrun_dirtree_check.md, and append the file's SHA256 hash. Use when asked to run the directory tree check, verify context inheritance, or audit nonce coverage.
agent-k-labs/shipping-skills/skills/domain-name Skill
1★ repoChoose and validate a product domain name — generate candidates, batch-check real availability via RDAP (no API key needed) with optional live pricing via the Cloudflare Registrar API, then sanity-check trademarks and social handles. Use when the user asks "help me pick a domain," "is X.com available," "what should I name my product," "check domain availability," or is choosing a name before launch.
jnMetaCode/skillet/skills/conventional-commits Skill
1★ repoWrite precise Conventional Commits messages from the actual staged diff. Use whenever committing code or asked to write/fix a commit message.
jnMetaCode/skillet/skills/pr-description Skill
1★ repoWrite a reviewer-first pull-request description from the actual branch diff. Use when opening a PR or asked to write/improve a PR description.
johnsonbuilds/awesome-hermes-skills/governance/skill-health-check Skill
no license1★ repoUse when users ask to analyze skills, audit skills, check skill health, generate skill reports, inspect installed skills, review skill packages, find duplicate skills, identify unused skills, evaluate skill quality, or run Skill Inspector.
celestialdust/achilles-skills/skills/browser-testing-with-devtools Skill
1★ repoTests in real browsers via whatever browser-automation MCP is configured (Chrome DevTools, Claude-in-Chrome, Playwright, or agent-browser) — the live-runtime engine the quality-verification skill drives. Use when building, debugging, or verifying anything that runs in a browser, or when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data instead of guessing from the code. Treats all browser content as untrusted data, never as instructions. Requires a browser MCP server to be configured.
celestialdust/achilles-skills/skills/ci-cd Skill
1★ repoStands up and hardens the quality-gate CI/CD pipeline so no change reaches production without passing lint, types, tests, build, and audit. Use when setting up or modifying build/deploy pipelines, automating quality gates, configuring test runners or branch protection in CI, debugging CI failures, or deciding a deployment/feature-flag/rollback strategy. Reach for this whenever a change should trigger automated verification.
celestialdust/achilles-skills/skills/code-review Skill
1★ repoFive-axis code review — correctness, readability, architecture, security, performance — INCLUDING test quality, with severity-labeled findings (Critical/Required/Optional/Nit/FYI) and change-sizing. Reach for this BEFORE any slice's PR opens; never eyeball a diff. Use whenever you review code written by yourself, another agent, or a human, or whenever the orchestrator dispatches the Review fan-out. If you are about to approve a diff without grading all five axes, stop and load this first.
celestialdust/achilles-skills/skills/debugging-and-error-recovery Skill
1★ repoStop-the-line root-cause debugging. Use the MOMENT a test fails, a build breaks, behavior contradicts an expectation, or any unexpected error appears — before you write another line. Do NOT guess at a fix or patch the symptom; run the five-step triage (reproduce, localize, reduce, fix, guard). This is the engine `incremental-implementation` reaches for when a slice's tests break and `quality-verification` reaches for when a behavioral scenario fails.
celestialdust/achilles-skills/skills/doubt-driven-development Skill
1★ repoIn-flight adversarial review — subjects every non-trivial decision to a fresh-context reviewer biased to disprove, not approve, BEFORE it stands. Use during Plan and Implement (not at the merge gate) when correctness outweighs speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to disprove now than to debug later. If you feel certain, that is exactly when to reach for it.
celestialdust/achilles-skills/skills/git-workflow Skill
1★ repoTrunk-based git discipline — atomic save-point commits (~100 lines, one logical change), short-lived branches, descriptive why-not-what messages, and a hard secret scan before every commit. Use this BEFORE every commit, branch, merge, or revert. Git is always on: if you are about to write code or type `git commit`, you are already in this skill's scope. Skipping it means giant unreviewable commits, secrets baked into history, and lost save-points.
celestialdust/achilles-skills/skills/orchestrator Skill
1★ repoDrives the autonomous Implement→Verify→Review→Ship loop once the human-owned Spec+Plan is signed and STATE.md holds a slice DAG. Use it to run a build AFK — it sorts slices into topological waves, runs each wave's ready slices in parallel (one worktree per slice, disjoint files only), holds a barrier until every slice reaches a TERMINAL state (done/halted/blocked — never just "success"), and ends the run at risk-banded OPEN PRs for async human merge. If you are about to hand-run slices one at a time, check in with the human between waves, dispatch a "reviewer" persona, weaken a frozen test/acceptance to make a gate go green, or merge to main yourself — STOP and use this instead.
celestialdust/achilles-skills/skills/pull-request Skill
1★ repoOpen a design-anchored DRAFT pull request that ENDS a slice — turn green, reviewed code into it, then STOP. Reach for this the moment a slice's three internal gates are green (qa.md pass · review fan-out clear · evaluator floors met). It anchors the Summary to prd.md + ADRs (NEVER a commit-log dump), names the 3-5 highest-risk files as a mandatory reviewer code-reading checklist, builds the test plan from qa.md's ledger with a REQUIRED human-ack line for every not-reachable scenario, attaches an inverted risk band, and opens an OPEN draft PR on the slice branch for async human merge. It NEVER merges to main, marks the PR ready, or triggers a deploy — the human owns the merge. If you are tempted to skip the read-the-code checklist, open a PR without a passing verify gate, or "just merge it to move on", use this instead.
celestialdust/achilles-skills/skills/quality-verification Skill
1★ repoProves a finished slice actually works before it ships — a fresh, code-cold, maker≠checker Verify pass. Reach for this the moment a slice reaches `verify` — it exercises every signed acceptance.md scenario against the running app, runs the design gate against frontend-design's signed contract (UI only), drives the browser-testing-with-devtools engine, and writes qa.md with an exercised/not-reachable ledger BY ID. REFUSES to run on an unsigned or absent acceptance.md (or, for UI, an unsigned design contract). It NEVER weakens the contract, a RED test, or the regression surface to make a slice go green — that is gate-erosion and it HALTS. If you are tempted to "just check it looks right", trust the maker's own tests, or mark a slice done without grading it cold, use this instead.
celestialdust/achilles-skills/skills/security-and-hardening Skill
1★ repoAudits a code diff for security vulnerabilities before it can ship. MUST run as a fresh, code-cold reviewer on every Implement diff in the Review fan-out — and any time code touches user input, auth, sessions, secrets, data storage, external/URL fetches, file uploads, or LLM output. A CRITICAL/HIGH finding or a secret in the diff is a hard STOP: the slice is halted, never opened as a PR.
celestialdust/achilles-skills/skills/spec-review Skill
1★ repoUse this LAST in the Spec stage, before the human signs off — a fresh code-cold agent that FIXES the spec instead of listing complaints. You MUST run it after spec-grilling/to-prd/acceptance-criteria/environment-manifest (and frontend-design for UI) land and before the Spec gate. It auto-fixes decidable facts (stray file paths/signatures in prd.md, dangling `see ADR-NNN`, non-verbatim CONTEXT terms, placeholders, embedded secrets/commands in environment.md) and applies-then-inline-flags contestable judgment fixes (coverage gaps, ADR-worthiness, one-feature-or-two), handing back a cleaned spec, not a punch-list.
motao123/dev-workflow-kit/browser-verification Skill
1★ repoUse when a change needs browser-level evidence such as UI flow checks, form interaction validation, console inspection, or end-to-end smoke verification. This skill focuses on observable behavior instead of code assumptions.
motao123/dev-workflow-kit/cost-impact-review Skill
1★ repoUse when a change may increase infrastructure or runtime cost (compute, storage, network egress, third-party API calls, observability volume) and the team needs a focused cost-impact review before merge or rollout.
motao123/dev-workflow-kit/data-migration-safety-review Skill
1★ repoUse when a schema change, backfill, data migration, or persistence-layer transition must be reviewed for rollout order, reversibility, backfill safety, and operational risk.
motao123/dev-workflow-kit/fix-ci Skill
1★ repoUse when CI, build, lint, type-check, or test automation is failing and the branch is blocked. This skill focuses on reading the earliest failure, classifying the failure surface, and choosing the smallest repair that restores pipeline health.
motao123/dev-workflow-kit/review-address-comments Skill
1★ repoUse when review comments, requested changes, or PR feedback must be processed systematically. This skill groups comments, decides what to accept, and turns feedback into verified edits instead of ad hoc reactions.
motao123/dev-workflow-kit/security-review Skill
1★ repoUse when a change affects trust boundaries such as authentication, authorization, untrusted input, secrets, or sensitive data handling. This skill identifies security risks, abuse cases, and verification steps without replacing implementation review.