Review & quality
19,178 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
Verification before completion
autohandai/community-skills/verification-before-completion Skill
10★ 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
nonlinear-xyz/factory-kit/skills/factory-ci Skill
9★ repoCI and pull-request review conventions. One canonical `.github/workflows/ci.yml` is the merge gate (typecheck, lint, test, build, claude-review); branch protection's required-checks list matches the job list 1:1; `anthropics/claude-code-action@v1` reviews every PR against the `factory-pitfalls.md` checklist as a required check, not advisory. Deploy workflows live separately and never gate merge. Read at project kickoff and whenever wiring CI on a new repo.
nonlinear-xyz/factory-kit/skills/factory-code-reviewer Skill
9★ repoUse to review a PR, diff, or recently-written code against the factory's conventions. Read-only — outputs structured review, not diffs. Carries the full factory-pitfalls digest as a PR checklist plus the conventions from every other factory-*.md skill. Flags anti-patterns, missing conventions, security risks, and inconsistencies with prior builds. Invoke after writing nontrivial code, before merge, or when on-boarding a contractor.
nonlinear-xyz/factory-kit/skills/factory-commits Skill
9★ repoCommit message and branch convention — Conventional Commits format with a Linear issue reference required in subject or body. Includes the canonical commitlint.config.cjs, Husky hook snippet, and opencommit configuration. Read whenever setting up a new project or wiring AI-assisted commits.
nonlinear-xyz/factory-kit/skills/factory-db-migration-engineer Skill
9★ repoUse when planning or executing a destructive change against a production database — schema migrations with backfills, periodic data imports, one-shot RPCs, drop-constraint operations, anything that mutates prod tables and cannot be trivially undone. Sister agent to `db-schema-architect` (schemas) and `data-pipeline-engineer` (ingestion); this agent owns the *runbook discipline* — preflight / mutate / verify / rollback, idempotency by natural key, layered backup independence (Layer C of `factory-security.md`), bidirectional update semantics, validation-at-parse-not-at-constraint, human-gated execution. Outputs a runbook + gating criteria, not raw SQL. Refuses to auto-run any DB command.
nonlinear-xyz/factory-kit/skills/factory-db-migration Skill
9★ repoThe operational discipline for running a destructive change against a production database — schema migrations, data backfills, one-shot RPCs, historical seed imports. Adjacent to `factory-data-layer.md` (schema design) and `factory-deployment.md` (where migrations execute in CI) — this skill is about the runbook around the act of mutating prod. Covers the three-stage write contract (preflight → mutate → verify → rollback), idempotency by natural key, layered backup independence (Layer C from `factory-security.md` / KAI-126 doctrine), human-gated execution, bidirectional update semantics, validation-at-parse-not-at-constraint, and the failure modes a senior DB engineer pattern-matches before opening a migration PR.
nonlinear-xyz/factory-kit/skills/factory-verification-engineer Skill
9★ repoUse to design the verification strategy for a change — what would prove it correct, given its blast radius, and what is currently unverifiable. Read-only — outputs a verification plan and a gap list, not a review and not code. Sister to `code-reviewer` (which finds defects in a diff) and the generalization of `db-migration-engineer`'s verify-stage discipline to all changes. Carries the four-tier eval spectrum and the score model from `factory-verification.md`. Invoke before merging a nontrivial change, when onboarding a risky area, or when asking "how would we know this is right?"
nonlinear-xyz/factory-kit/skills/factory-verification Skill
9★ repoHow we know the software the factory produces is correct, and how we know the kit's own conventions are followed. Defines the four-tier eval spectrum (CLI rule / test / agent / human gate), the rule that evals graduate downward to their cheapest home, the banded coverage score with severity-aware disclosure, and the delta-gated GitHub Action that guards the PR boundary without disrupting the inner loop. The recipe locks to `factory-kit-check` + GitHub Actions; the principles are stack-agnostic. Read at project kickoff, when wiring the conformance gate, and whenever asking "how do we know the agent did this right?"
huzaifa525/claude-code-optimizer/templates/.claude/skills/dep-check Skill
9★ repoUse when the user wants to check dependencies, find outdated packages, or audit for vulnerabilities.
huzaifa525/claude-code-optimizer/templates/.claude/skills/perf-check Skill
9★ repoUse when the user wants to check performance, find slow code, identify bottlenecks, or audit efficiency.
huzaifa525/claude-code-optimizer/templates/.claude/skills/review Skill
9★ repoUse when the user wants a code review, quality check, or asks to review their changes.
huzaifa525/claude-code-optimizer/templates/.claude/skills/token-check Skill
9★ repoUse when the user asks about token usage, session cost, or wants to check optimization effectiveness.
yamanidev/claude-code-configuration/skills/review-code Skill
9★ repoRead-only workflow for code review, PR review, or feedback on a diff, branch, or specific files. Produces structured, prioritized feedback with blockers, should-fix items, nits, questions, and notable strengths — does not modify code. NOT for making changes (use /ship for that).
yamanidev/claude-code-configuration/skills/ship Skill
9★ repoWorkflow for extending, fixing, or evolving existing production code — bugs, features, refactors, or shipping changes that touch APIs, data models, integrations, business logic, or user-facing behavior. NOT for greenfield prototypes or throwaway scripts, NOT for read-only investigation of how existing code works or why it fails (use /investigate), and NOT for code review (use /review-code).
yamanidev/claude-code-configuration/skills/test Skill
9★ repoWorkflow for writing tests against requirements — verifying that a feature, endpoint, or function behaves correctly according to its specification, not according to its current implementation. Reads the spec/requirement and the surface being tested (signatures, contracts, observable behavior); deliberately avoids mirroring implementation logic into the tests. Suitable for adding coverage after the fact in a codebase without strong test culture. Does not modify production code (use /ship) and does not review existing tests as part of a code review (use /review-code).
itaywol/adeptability/examples/skills/pr-review Skill
9★ repoCross-harness AI skill portability CLI. Author an agent skill once, sync it into Claude Code, Cursor, Copilot, Codex, OpenCode & 45+ AI coding agents. Safety scanner, content-hash drift detection. A package manager / dotfiles for AI coding agent skills.
vanara-agents/skills/skills/conventional-commits Skill
9★ repoWrite Conventional Commits — the type(scope)!: subject + body + footer spec — so history is readable and changelogs and SemVer bumps can be derived automatically. Use when committing, configuring commitlint, designing release tooling, or deciding feat vs fix vs breaking change.
vanara-agents/skills/skills/git-collaboration-workflows Skill
9★ repoRun git collaboration that scales — trunk-based vs git-flow decided by deploy cadence, branch protection and required checks, PR sizing and review etiquette, monorepo vs polyrepo trade-offs, release branches and hotfixes, and history hygiene with disciplined merges.
Verification before completion
endorphin-ai/hasbrains-agent-kit/agent-engineering/skills/verification-before-completion Skill
9★ repoThe battle-tested Claude Code kit behind HasBrainsAI — agent skills, subagents & slash commands for production multi-agent systems. Install in one command.
ellmos-ai/skills/skills/dev/rotation-check Skill
9★ repoPortable SKILL.md library for Claude Code, Codex-compatible agents, BACH, and local-first LLM workflows
ellmos-ai/skills/skills/game-dev/using-blender Skill
9★ repoGeneral Blender workflow skill for AI agents working with .blend, .fbx, .obj, .glb, glTF, materials, scene inspection, bpy automation, headless Blender batch runs, export/reimport validation, previews, and optional Blender MCP control. Use when a task asks to open, inspect, create, automate, convert, optimize, render, or verify Blender or 3D asset files in a user-agnostic way.
ellmos-ai/skills/skills/utilities/law-checker Skill
9★ repoPoints to the standalone module law-checker ("Legal Department"): source-grounded AI first-look legal assessments for German law with a statute registry and a statute-embodiment agent. Use this skill when a situation, contract, official notice, or legal question under German law should be checked with exact citations (article/section, paragraph, sentence) -- with a clear boundary: AI-assisted first orientation, not a substitute for a lawyer.
muratmirgun/gophers/skills/go-linting Skill
9★ repoUse when setting up linting for a Go project, configuring golangci-lint, picking a linter set, suppressing findings with //nolint, or wiring lint checks into CI. Apply proactively whenever a project lacks .golangci.yml, when lint output is unclear, or when a new package needs the project's quality bar. Does not cover code review process (see go-code-review).
isvlasov/rageatc-oss/plugins/rageatc-code-oss/skills/verifying-work Skill
9★ repoGates completion claims with mandatory evidence — no "should work" or "probably passes" without fresh verification output. Use when verifying test results, confirming builds pass, checking linter output, or validating acceptance criteria.
isvlasov/rageatc-oss/plugins/rageatc-core-oss/skills/finalise-session Skill
9★ repoRun /handover then commit and push changes to git
jiatastic/open-python-skills/skills/ruff-linter Skill
9★ repoPython linting with Ruff - an extremely fast linter written in Rust. Use when: (1) Standardizing code quality, (2) Fixing style warnings, (3) Enforcing rules in CI, (4) Replacing flake8/isort/pyupgrade/autoflake, (5) Configuring lint rules and suppressions.
gaelic-ghost/socket/plugins/android-dev-skills/skills/build-kotlin-android Skill
9★ repoImplement Kotlin-first Android app or library changes, including activities, fragments, services, receivers, Compose UI, XML/AppCompat UI, AndroidX, lifecycle-aware coroutines, state, persistence touchpoints, resources, accessibility labels, navigation touchpoints, tests, lint, and validation while preserving repo conventions.
gaelic-ghost/socket/plugins/android-dev-skills/skills/choose-project-shape Skill
9★ repoChoose the right Android project, app, library, module, language, UI, build, test, lint, signing, release, or dependency-maintenance shape before implementation. Use when Android work needs routing across Kotlin, Java, Gradle, Android Gradle Plugin, Compose, XML views, emulator-aware validation, release readiness, or server-side JVM handoffs.
gaelic-ghost/socket/plugins/android-dev-skills/skills/testing-lint-workflow Skill
9★ repoPlan, run, filter, and triage Android tests and lint, including local unit tests, instrumentation and Compose UI test handoffs, Gradle variant tasks, lint configuration, lint baselines, failure explanations, emulator-aware validation routing, and readable next checks.
Devicecheck app attest workflow
gaelic-ghost/socket/plugins/apple-dev-skills/skills/devicecheck-app-attest-workflow Skill
9★ repoGuide DeviceCheck and App Attest adoption in Apple-platform apps using DCDevice, DCAppAttestService, app IDs, entitlements, server challenges, attestation objects, assertions, receipts, fraud-risk metrics, sandbox/production environments, rollout planning, and explicit client/server handoffs. Use when implementing or diagnosing DeviceCheck per-device two-bit state, App Attest app-instance integrity, Apple server API validation, App Attest environment setup, macOS App Attest verification, App Clip key-sharing, supported extension contexts, or fraud-risk integration that must be checked against current Apple documentation.
gaelic-ghost/socket/plugins/cybersecurity-skills/skills/check-artifact-reputation Skill
9★ repoCheck local and external reputation for a suspicious artifact, signer, hash, URL, domain, certificate, package, or vendor. Use when provenance and threat-intelligence context could inform triage, while sample-upload privacy, stale intelligence, hash-only misses, false positives, and reputation-versus-behavior limits must remain explicit.
Scope authorized security test
gaelic-ghost/socket/plugins/cybersecurity-skills/skills/scope-authorized-security-test Skill
9★ repoDefine and verify authorization, targets, rules of engagement, data handling, safety controls, and stop conditions before active security testing. Use for penetration tests, vulnerability scans, exploit validation, web/API tests, network probing, red-team-like exercises, bug bounty work, or agent-driven testing where ownership and allowed techniques must be explicit.
gaelic-ghost/socket/plugins/productivity-skills/skills/maintain-github-repository Skill
9★ repoAudit or align a GitHub repository's server-side settings, including repository features, merge methods, branch protection or rulesets, Dependabot, secret scanning, push protection, private vulnerability reporting, DCO web sign-off, and related defaults. Use when the user asks to configure a new GitHub repo, apply normal repository settings, inspect settings drift, audit branch protection or security settings, or change specific GitHub repository policy. Do not use for ordinary local Git commits, branches, pushes, pull-request prose, code review replies, or release choreography.
gaelic-ghost/socket/plugins/productivity-skills/skills/maintain-project-repo Skill
9★ repoInstall or refresh the profile-aware local-first maintain-project-repo toolkit, or execute its protected-main release workflow. Use when the user asks to install or refresh repo-owned validate, sync, and release scripts; release or publish a version; bump and tag a release; create the GitHub release; prepare or merge a protected-main release; or complete release cleanup and branch accounting. Do not use for ordinary edits, local Git work, documentation maintenance, or GitHub repository-settings audits.
gaelic-ghost/socket/plugins/python-skills/skills/bootstrap-python-mcp-service Skill
9★ repoBootstrap Python MCP server projects and workspaces on macOS using uv and FastMCP with consistent defaults. Use when creating a new MCP server from scratch, scaffolding a single uv MCP project, scaffolding a uv workspace with package/service members, customizing scaffold defaults through layered YAML profiles, initializing pytest+ruff+mypy defaults, creating README.md, initializing git, running initial validation checks, or starting from OpenAPI/FastAPI with MCP mapping guidance.
gaelic-ghost/socket/plugins/python-skills/skills/bootstrap-python-service Skill
9★ repoBootstrap Python FastAPI services on macOS using uv with consistent project and workspace scaffolds. Use when creating a new backend/API service from scratch, scaffolding a single uv service project, scaffolding a uv workspace with package/service members, customizing scaffold defaults through layered YAML profiles, initializing pytest+ruff+mypy defaults, creating README.md, initializing git, and running initial validation commands.
gaelic-ghost/socket/plugins/python-skills/skills/bootstrap-uv-python-workspace Skill
9★ repoBootstrap new Python projects and multi-package workspaces with uv on macOS using deterministic scripts and consistent defaults. Use when creating a new uv Python project, scaffolding a uv monorepo/workspace, setting up package or service profiles, customizing scaffold defaults through layered YAML profiles, initializing dev tooling (pytest, ruff, mypy), creating README scaffolds, or initializing git with an optional first commit.
gaelic-ghost/socket/plugins/python-skills/skills/build-python-project Skill
9★ repoBuild or modify idiomatic Python projects using uv, explicit package layout, typed configuration, focused tests, Ruff, mypy, and repo-local validation without overriding established conventions.
gaelic-ghost/socket/plugins/reverse-engineering-skills/skills/review-decompiler-output Skill
9★ repoReview generated pseudocode or disassembly without presenting it as original source. Use when Codex must interpret, compare, annotate, validate, or summarize output from Cutter, Rizin, Malimite, Ghidra, Hopper, ILSpy, or another decompiler or disassembler; assess recovered types and control flow; track analyst renames; or reconcile disagreements between generated output and binary or runtime evidence.
gaelic-ghost/socket/plugins/rust-skills/skills/tooling-style-workflow Skill
9★ repoAlign Rust formatting, linting, toolchain, and CI behavior with repository policy, including cargo fmt, rustfmt style edition, cargo clippy, rust-toolchain.toml, MSRV checks, warnings-as-errors decisions, and validation command selection. Use when configuring or fixing Rust style, lint, toolchain, or CI workflows.
gaelic-ghost/socket/plugins/swift-lang/skills/swift-format-style-workflow Skill
9★ repoAlign SwiftFormat, SwiftLint, formatter and linter responsibility, checked-in style config, Git hooks, and CI formatting policy for Swift repositories. Use for shared Swift style and formatting before source-organization or modernization passes.
gaelic-ghost/socket/skills/check-artifact-reputation Skill
9★ repoCheck reputation for a suspicious artifact, signer, hash, URL, domain, certificate, package, or vendor. Use when threat intelligence informs triage while privacy, stale data, false positives, and behavior limits stay explicit.
Scope authorized security test
gaelic-ghost/socket/skills/scope-authorized-security-test Skill
9★ repoDefine and verify authorization, targets, rules of engagement, data handling, safety controls, and stop conditions before active security testing. Use for penetration tests, vulnerability scans, exploit validation, web/API tests, network probing, red-team-like exercises, bug bounty work, or agent-driven testing where ownership and allowed techniques must be explicit.
duthaho/skillhub/.claude/skills/done Skill
9★ repoEnd-of-session shipping gate — "prove it works, then ship it." Runs an evidence checklist (full test suite, lint/typecheck, build, and actually running the change — output quoted, never asserted), then a fresh-context two-stage review by a sub-agent that sees only the diff and the spec: spec-compliance first, correctness second, style never — joined by a cross-model second opinion when a codex/gemini CLI is installed. Flags fake-green tripwires (edited or deleted tests, new TODOs or skips, hardcoded expectations) and ends with a verdict — SHIP, FIX FIRST, or NEEDS HUMAN — before drafting the commit/PR for the user's approval. Use at the end of any coding session or when the user asks "is this done", "ready to ship?", "/done", "wrap this up", "review and commit this". It is the closing step of both feature and bugfix, but works standalone on any uncommitted or branch diff.
duthaho/skillhub/.claude/skills/factcheck Skill
9★ repoAdversarial citation and claim audit for any document — "do these sources actually say what the text claims?" Takes a markdown file, URL, or pasted draft (including this repo's own pulse/verdict briefs), extracts every checkable claim, then fans out verifier sub-agents instructed to refute, not confirm: does the cited link resolve AND assert the claim as stated, is the source primary or a laundered secondary write-up, has the claim gone stale. Emits a graded audit table — VERIFIED / MISATTRIBUTED / UNSUPPORTED / STALE / UNCHECKABLE — with a quoted passage as evidence for every grade, saved to out/factcheck/. Advisory: it grades, the human edits. Use when the user wants to check citations, verify sources, or audit a report, post, or brief — e.g. "/factcheck <doc>", "verify the sources in this", "are these citations real?", "is this actually true?". For researching a fresh topic use pulse; for judging code changes use done.
sherifabdlnaby/skills/skills/git Skill
no license9★ repoLoad when planning or about to git commit, branch, push, rebase, resolve a merge conflict, open PR, stack PR, or write/update the description of a Pull Request (PR / stacked diff), respond to review comments, review a PR, or watch/babysit a PR's CI. Carries the user's git conventions and style you are expected to match. Load as early as possible, the moment git or GitHub work is anywhere in the chat's future.
sherifabdlnaby/skills/skills/grill Skill
no license9★ repoA relentless interview that asks every frontier question at once, round by round. (Sherif's version).
sherifabdlnaby/skills/skills/review Skill
no license9★ repoGate the work behind a local reviewer panel.
iotron/gsap-cookbook/skills/gsap-test Skill
no license9★ repoProduction recipes for testing, debugging, and verification of GSAP animations. No API overlap — unique to this plugin. Triggers: test animation, animation cleanup test, Playwright animation, animation debug, animation markers, memory leak animation, animation screenshot, visual QA animation, animation verification, pre-launch animation check. Non-triggers: Not for building animations (use gsap-animate). Not for performance optimisation (use gsap-optimise). Use this skill for verification and QA. Outcome: Produces test infrastructure — Vitest cleanup tests, Playwright hooks, debugging patterns, and pre-launch checklists.
widnyana/eyay-toolkits/plugins/evm-decimal-validation/skills/evm-decimal-validation Skill
9★ repoValidate and configure token decimals for EVM-compatible blockchain deployments. Use when working with ERC20 tokens, multi-chain deployments, token amount conversions, or when decimals might vary across chains.
widnyana/eyay-toolkits/plugins/solana-onchain/skills/solana-setup Skill
9★ repoInstall, update, or verify the solana-onchain-mcp binary. Use when user runs /solana-setup, asks to "install solana binary", "update solana-onchain-mcp", "check solana setup", "set up solana plugin", or when the binary is missing from PATH.
widnyana/eyay-toolkits/plugins/ts-backend-dev/skills/ts-review Skill
9★ repoReview TypeScript code for quality, security, and correctness. Use this skill when the user asks for a code review, wants feedback on a PR or diff, or says "review this". Covers architecture, security, error handling, database patterns, type safety, and code quality. Produces categorized findings: critical issues, improvements, suggestions, and positive notes. Also triggers on phrases like "check this code", "what do you think of this", or "any issues with".
TonyCasey/lisa/src/project/.lisa/skills/review Skill
9★ repoPersistent memory for Claude Code - powered by Graphiti knowledge graphs
Notysoty/openagentskills/skills/code-review-checklist Skill
9★ repoRuns a systematic checklist review on any code diff or file, covering correctness, security, performance, and readability.
Notysoty/openagentskills/skills/database-schema-reviewer Skill
9★ repoReviews database schemas for normalization issues, missing indexes, naming inconsistencies, and scalability risks.
Notysoty/openagentskills/skills/git-commit-writer Skill
9★ repoGenerates conventional commit messages from staged changes or a diff.
Notysoty/openagentskills/skills/hallucination-risk-reviewer Skill
9★ repoReviews an AI-generated response or LLM application output for factual risks, hallucination patterns, and confidence calibration issues.
Notysoty/openagentskills/skills/pr-description-writer Skill
9★ repoWrites clear, thorough pull request descriptions from a diff or list of changes.
Notysoty/openagentskills/skills/react-code-reviewer Skill
9★ repoAnalyzes React components for performance, accessibility, and modern hook usage.
Notysoty/openagentskills/skills/responsive-layout-reviewer Skill
9★ repoReviews HTML/CSS or component code for responsive design issues across mobile, tablet, and desktop breakpoints.