Review & quality
19,000 rows, by stacks then stars
1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid
vemodalen-x/VEMO_SKILLS/skills/research/reviewing-decisions Skill
0★ repoReliability ruleset for technical design decisions — a lightweight design-review discipline. Each key decision must carry 6 fields (options/evidence/trade-offs/assumptions/failure-modes/validation); a cross-model red-team pass critiques the doc before publish. Use when the research-solution agent finalizes the solution_document. Owned by Framework 1 (research). Generic; reviewer models/decisions are instance values.
codecraftersautomation/claude-code/plugins/ccp/skills/safety-check Skill
no license0★ repoCheck whether it's safe to hand off or take over by scanning the working tree for risky conditions. Use when the user asks "is it safe to switch/hand off", "any blockers", "check for secrets/conflicts before I switch profiles", or before/after /ccp:handoff and /ccp:takeover. Runs the git safety script and reports repo status, staged/unstaged/untracked/deleted files, merge conflicts, large files, likely secret files, and likely secrets in the diff. Writes .claude/ccp/handoff/SAFETY_CHECK.md.
codecraftersautomation/claude-code/plugins/ccp/skills/workstate Skill
no license0★ repoCapture a mechanical snapshot of the repository (branch, git status, diff, recent commits, detected build/test commands) independent of conversation memory. Use whenever the user wants a ground-truth record of the repo before a profile switch, asks for "current repo state", "workstate", "snapshot the changes", or as a companion to /ccp:handoff and /ccp:takeover. Writes WORKSTATE.md, GIT_STATUS.txt, DIFF.patch, RECENT_COMMITS.txt under .claude/ccp/handoff/, with secrets redacted.
TonkaToyXL/cursor-agent-skills/terse-commit Skill
0★ repoTerse commit message generator. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /terse-commit. Auto-triggers when staging changes.
skillim-hub/skills/followup-review-solicitor Skill
0★ repoSends follow-up messages and requests reviews in Hebrew at optimal times for Israeli audiences.
skillim-hub/skills/hebrew-email-formatter Skill
0★ repoCompose professional Hebrew emails for Israeli small businesses, freelancers, and consumers. Use for Hebrew email drafts, payment reminders, quotes, invoices, appointment coordination, complaint responses, cancellation notices, service updates, and consumer correspondence. Apply Israeli localization: natural Hebrew phrasing, correct formality, gender-aware verbs when known, neutral alternatives when gender is unknown, ₪ amounts, DD/MM/YYYY dates, and suitable signature blocks. Do not use for legal advice, tax advice, mass-marketing automation, or sending messages without user review.
skillim-hub/skills/parking-fine-checker Skill
0★ repoNeutral operational guide and tools for Israeli parking, traffic, and toll fine workflows.
skillim-hub/skills/privacy-compliance-checker Skill
0★ repoCheck privacy workflows for Israeli small businesses, freelancers, consumers, and lightweight cloud services against Israeli privacy law, Privacy Protection Authority expectations, GDPR touchpoints, and operational data-security controls.
Social security benefit checker
skillim-hub/skills/social-security-benefit-checker Skill
0★ repoOffline-first preliminary checker for Israeli National Insurance allowances and benefits.
lensetek/Research-Agent-Skills-Collection/skills/agent_update_checker Skill
no license0★ repoBertugas untuk mengecek pembaruan (update) agent skills terbaru dari repositori GitHub dan mengonfirmasi pengguna apakah ingin mengunduh versi terbaru.
Citation and reference validator
lensetek/Research-Agent-Skills-Collection/skills/citation_and_reference_validator Skill
no license0★ repoMemvalidasi kebenaran metadata referensi (DOI, tautan, judul, penulis, tahun) dan keselarasan kontekstual antara kalimat klaim di naskah dengan konten paper yang dirujuk.
lensetek/Research-Agent-Skills-Collection/skills/journal_template_formatter Skill
no license0★ repoBertugas mengubah, menyusun, dan memformat draf makalah riset menjadi format jurnal penelitian sesuai dengan panduan penulis (Author Guidelines) atau template yang dituju (misal IEEE, APA, Elsevier).
lensetek/Research-Agent-Skills-Collection/skills/literature_review_generator Skill
no license0★ repoMelakukan tinjauan pustaka terstruktur, menyusun kronologi perkembangan riset, dan mengidentifikasi celah penelitian (research gaps) pada topik tertentu.
lensetek/Research-Agent-Skills-Collection/skills/model_evaluator_validator Skill
no license0★ repoBertugas mengevaluasi, memvalidasi, dan menguji signifikansi statistik dari hasil prediksi model komputasi atau Machine Learning untuk memastikan ketangguhan temuan riset.
lensetek/Research-Agent-Skills-Collection/skills/project-setup-git Skill
no license0★ repoSkill untuk melakukan setup proyek melalui git clone/pull alih-alih menggunakan npx (Mendukung pedoman keamanan kredensial dan desain mobile-view first).
Reviewer response and revision
lensetek/Research-Agent-Skills-Collection/skills/reviewer_response_and_revision Skill
no license0★ repoMembantu proses revisi naskah akademik dengan mengklasifikasikan komentar reviewer, merancang berkas tanggapan (Response to Reviewers), dan merencanakan perubahan teks naskah.
sebastian-software/skills.sebastian-software.com/skills/effective-workflow Skill
0★ repoCoordinate multi-stage or mixed-domain software work from an unclear request through an authorized change, focused verification, and a review-ready handoff. Use when a task spans diagnosis, implementation, validation, review, or delivery and needs sequencing across repository-native workflows and first-party specialist skills. Prefer the matching specialist directly for an already narrow documentation, dependency, test, review, architecture, port, or frontend request.
sebastian-software/skills.sebastian-software.com/skills/pr-review Skill
0★ repoReview and maintain pull requests across GitHub, GitLab, Forgejo, Gitea, and other providers: inspect PRs, approve or request changes, handle feedback, fix valid findings, recover CI, keep branches current, or review caller-supplied context without taking provider action. Use when a user asks to review PRs, catch up on review work, maintain their own PRs, names a PR, requests a dry run, or delegates review analysis while retaining approval and delivery authority.
sebastian-software/skills.sebastian-software.com/skills/software-testing Skill
0★ repoDesign, implement, diagnose, and verify focused non-frontend software tests for services, APIs, databases, async work, CLIs, and Rust. Use when asked to protect a behavior, invariant, regression, failure path, retry, authorization rule, migration, command-line contract, or flaky test; to diagnose test discovery, collection, runner, or framework configuration; to make a rule or state transition directly testable; to add a focused performance-regression guard; or to design, repair, or interpret a repository-native microbenchmark, comparative benchmark, or bounded end-to-end workflow benchmark. Prefer repository-native test conventions and real behavior over mock choreography. For browser, component, or React tests use effective-web. Do not use for visual, accessibility, or browser E2E testing; repository-wide coverage audits; testing-strategy design (use software-architecture); or load, soak, stress, and capacity methodology.
sebastian-software/skills.sebastian-software.com/skills/software-validation Skill
0★ repoDiscover, execute, and report existing repository-native software checks. Use when asked to validate a change, run the repository's established checks against a change or package, run the applicable typecheck, static analysis, lint, format, test, benchmark, load, soak, stress, build, package, documentation, doctest, link, generated-reference, or example checks, or explain what validation evidence is still missing. Do not use to invent or install tooling, design new tests, choose architecture quality targets, prioritize repository improvements, or orchestrate delivery.
KhurrumMahmood/senior-vibe-engineer/.claude/skills/check-ecosystem-consistency Skill
no license0★ repoDiff-aware ecosystem consistency audit for engineering-skills. Snapshots skills, shape routing references, docs skill-count claims, and catalog coverage; compares with the last reviewed state so significant skill changes surface follow-up obligations such as updating /which-shape.
KhurrumMahmood/senior-vibe-engineer/.claude/skills/engineer-init Skill
no license0★ repoBootstrap the engineering-skills runtime so the script-backed skills can actually run. Health-checks candidate Python >= 3.11 interpreters, creates the .venv, installs requirements.txt (PyYAML, ruff, pre-commit), wires pre-commit hooks when the repo is git-tracked, and verifies the install by running a script-backed skill end to end. Idempotent — safe to re-run; each stage skips work already done. Run once per clone, or whenever a skill fails with a missing-module / dependency error. Does not edit production code, does not git-init, and does not scaffold a new project (that is /init-project).
KhurrumMahmood/senior-vibe-engineer/.claude/skills/find-skill-intent-drift Skill
no license0★ repoAdvisory SUSPECT scan that compares each skill under `.claude/skills/` against its machine-checkable intent + provenance contract under `.claude/contracts/skills/<name>.yaml` (schema v2). Flags four drift bands — missing (skill has no contract), orphaned (contract for a deleted skill), malformed (contract missing required schema keys), and stale (SKILL.md committed after the contract's last commit, so captured intent may have silently drifted). This is the "no easy reversion of intent" guard: it cannot block an edit, but it makes intent erosion visible. It is the intent/provenance layer of the skill-meta trio, distinct from frontmatter-contract lint and artifact-coherence drift.
KhurrumMahmood/senior-vibe-engineer/.claude/skills/gut-check Skill
no license0★ repoInstinctive senior-engineer "does this look dumb?" reaction pass over a plan markdown, a commit diff, or a free-form architecture summary. Emits 3-5 cited smell reactions split into un-decided smells (no precedent / ADR covers them — raw signal) and decided-but-still-smell (an ADR or precedent explains why the project did it this way, but the smell still surfaces — surface both so the human can decide whether to re-litigate). Confidence-banded (strong-smell / weak-smell / style-preference). Prompt-only, no helper script.
KhurrumMahmood/senior-vibe-engineer/.claude/skills/prevent-regression Skill
no license0★ repoTurn a closed cleanup cluster into a permanent guardrail: diff-scoped lint when the invariant is lexical/AST-shaped, or focused regression tests when the invariant is behavioral/contract-shaped. Accepts a cluster ID from a recent scan (`cluster:<id>`, `delete:<id>`, `semantic:<id>`, `dormant:<id>`), a free-form pattern description with optional `path:<glob>` qualifier, a product-topology template (`topology:<route-ownership|workflow-registry|frontend-boot|site-endpoints|doc-route-drift>`), or `--dogfood <rule-name>` to rewire an existing rule. Emits a proposal at `reports/prevent-regression/<id>/` containing the guard artifacts, canonical-pattern/testing guidance when needed, and a verification recipe. Read-only against production code — never installs the guard unilaterally; the human reviews and executes.
KhurrumMahmood/senior-vibe-engineer/.claude/skills/rename-concept Skill
no license0★ repoAssess a domain-concept rename against its full lifecycle and a mandatory two-band completeness gate, read-only. Renaming a concept that lives in the glossary spans many surfaces — identifiers, docs, the cross-tool agent mirrors — and is executed from tribal knowledge with no front door and no completeness gate, so renames land half-applied. This skill (v0, assess-only) reports the scope-gate verdict, blast radius, a per-step lifecycle status table, and the completeness gate. It performs strict lexical assessment of Python, JavaScript, TypeScript, TSX, Go, Java, bounded Kotlin/JVM, PHP, Ruby, Rust, Dart, and Swift text. For `.ts`, `.tsx`, and checked `.js`/`.jsx`/`.mjs`/`.cjs`, a host-pinned TypeScript Compiler API resolves glossary identifier candidates, declarations, and references; it does not claim whole-project type-checking, JSX runtime behavior, or codemod safety. For Go, Go 1.22+ `go/types` classifies project-exported concept declarations and their references while retaining fields, import aliases, locals, inactive source, and diagnostics. The old and new names must not co-occur lexically in live code (/find-concept-divergence superseded_co_occurrence, band 3) AND no retired phrasing may remain (/find-concept-divergence avoid_term_hit, band 1) — both must be CLEAN for a lexical candidate assessment to pass. A TypeScript/TSX, checked-JavaScript, Go, Rust, or Swift host additionally needs a successful native semantic evidence run that resolves old/new identifier candidates. Definition of done is the two-band gate, every lifecycle step resolved, and that evidence where a semantic language is in scope — NOT a codemod having run. Drives the two rename-relevant /find-concept-divergence bands through a required coupled installation; the assessment logic does not duplicate their matching rules. The write half (author + dry-run a codemod plan, scaffold a reintroduction lint, --apply) is a v1 gap pending a codemod harness in this ecosystem (see Deferred, below).
knefenk/autowiki/skills/autowiki-validate Skill
0★ repoUse when checking knowledge base health. Trigger: 'validate the wiki', 'check for contradictions', 'audit claims', 'lint the KB', 'drift check', 'health check'.
qchiujunhao/labcoat/skills/labcoat-reviewer Skill
0★ repoPR and diff review skill for biomedical coding-agent output. Use for reviewing generated patches, pull requests, diffs, or final changes involving biomedical software, safety boundaries, reproducibility, evidence claims, dependency bloat, or loop guardrail integrity.
markstent/muster/skills/review Skill
0★ repo(Muster) Check the changes two ways before you merge: do they follow your project's conventions, and do they actually do what the issue asked for? Reports one clear verdict - safe to merge or not. Use before merging any PR, or to "review since X".
vindreshsingh/engineering-skills/skills/agent-verification Skill
0★ repoStops an AI agent from declaring "done" on work it hasn't actually finished, by separating generation from evaluation and refusing self-graded completion. Use whenever an agent reports a task complete — especially in autonomous or long-running runs — to catch early termination, self-grading bias, and gamed tests before the work is trusted or merged.
vindreshsingh/engineering-skills/skills/git-flow Skill
0★ repoSound git practice — focused commits, clear messages, clean branches, safe history. Use when committing, branching, opening or updating a PR, merging, resolving conflicts, cutting a release, or recovering from a git mistake.
vindreshsingh/engineering-skills/skills/review-gate Skill
0★ repoReviews a change across correctness, design, readability, security, and performance before it merges. Use when reviewing a PR, self-reviewing your own diff, or sanity-checking an AI-generated change prior to shipping.
DailybotHQ/pocdd-skill/skills/pocdd/verify Skill
0★ repoValidate that a POC file is well-formed against the POCDD conventions — status header, the three sections, gaps tagged by owner with ids, findings with provenance, and decision gaps carrying an assumption + link. Read-only pass/fail. Use for "/poc verify <name>".
TheSmuks/openspec-hermes/skills/openspec/openspec-verify-change Skill
0★ repoUse when working with OpenSpec in Hermes: check implementation completeness, correctness, coherence, and evidence before archive.
prasadmogulothu/agent-skills/review-gate Skill
0★ repoUse when a task is marked as needing human review. Pause, present the artifact to a human (summary + link), and wait for explicit approval before continuing. Loop on change requests; never proceed on silence.
prasadmogulothu/agent-skills/security-review Skill
0★ repoRun a read-only security audit of sensitive code (auth, data isolation, secret handling, payments, input validation) before merging or deploying. Ships with a reviewer-agent definition. Block on critical/high findings.
Mily-Labs/agent-skills/plugins/milystudio-studio/skills/milystudio-review-quality Skill
0★ repoPerform independent technical, editorial, audio, caption, and visual quality control for MilyStudio. Use before delivery, release, or approval.
Mily-Labs/agent-skills/skills/milystudio-review-quality Skill
0★ repoPerform independent technical, editorial, audio, caption, and visual quality control for MilyStudio. Use before delivery, release, or approval.
StaryMoon/ai-researcher-skills/skills/review-rebuttal-helper Skill
0★ repoPractical skill pack for AI research agents: paper briefing, experiment planning, rebuttal drafting, radar maintenance, and GitHub upkeep.
Go perf bounds check elimination
ctoth/golang-skills-plugin/plugins/performant-golang/skills/go-perf-bounds-check-elimination Skill
0★ repoGuides bounds-check elimination (BCE) in Go — the compiler checks every slice/array index and the SSA pass removes the ones it proves redundant. Covers seeing surviving checks with go build -gcflags="-d=ssa/check_bce/debug=1", prover-friendly idioms (the _ = b[n-1] / b = b[:n] hint, range loops, constant vs variable offsets), the inlining link, and why -B is a footgun not a fix. Fires on "eliminate bounds checks", "why is this loop slow", "bounds check in hot loop", "optimize this numeric loop". Routes should-I to go-perf-methodology, slices to go-perf-slices.
ctoth/golang-skills-plugin/plugins/performant-golang/skills/go-perf-code-review Skill
0★ repoAgent skill plugins for Go code quality and performance work.
xDzaky/solana-skill-quality-gate/scripts/fixtures/benchmark-samples/excellent/skill Skill
0★ repoVerify NFT ownership, metadata, and collection membership on Solana. Uses Metaplex, DAS API, and Helius for comprehensive NFT validation.
xDzaky/solana-skill-quality-gate/skill Skill
0★ repoQuality and trust gate for Solana AI Kit skills. Builders use it to audit skills before installing or submitting them. Checks structure, safety, Solana fit, progressive loading, and supply-chain risks — so you only trust skills that pass the gate.
bndkts/copycraft/skills/du-sie-check Skill
0★ repoPrüft deutsche Copy auf konsistente du/Sie-Anrede und richtet sie an der gewählten Anrede der Marke aus. Use whenever German copy might mix du and Sie, when deciding between du and Sie for a German site, or before publishing German marketing copy. Trigger: "du oder Sie", "Anrede prüfen", "duzt und siezt gemischt", "Anrede vereinheitlichen", "konsistente Ansprache"; English: "check du/Sie consistency", "should this German copy use du or Sie", "audit German formality". Liest die Anrede-Entscheidung aus brand-brief.md.
dbmrq/agent-skills/skills/ios-bootstrap Skill
no license0★ repoBootstrap a new or empty iOS/macOS app repo: XcodeGen project.yml, folder layout, ai-rules-ios (SwiftLint/SwiftFormat/Periphery), warnings-as-errors, and CI/preBuild quality wiring. Use when creating a new iOS project, starting a greenfield SwiftUI app, scaffolding project.yml from scratch, onboarding a repo that lacks .ai-rules, or when the user asks to set up lint/format/deadcode gates. For XcodeGen-only debugging of an existing spec, use xcodegen. For finishing work on an already-bootstrapped app, use ios-quality-gate.
dbmrq/agent-skills/skills/ios-quality-gate Skill
no license0★ repoRun the shared ai-rules-ios quality plug-in (scripts/check.sh, format, Periphery deadcode --strict) before finishing iOS app work. Use when finishing features, refactors, removing APIs, cleanup, PRs, or Melvil/Gregor/Leio iOS changes that must stay lint-clean with zero unused code and no force unwraps.
Yco-0314/strata/skills/l3-execution/using-git-worktrees Skill
0★ repoUse when starting feature work that needs isolation, or before executing implementation plans — creates an isolated git worktree with smart directory selection, ignore-safety verification, and a clean test baseline. Called by subagent-driven-development to bind isolation into the dispatch step.
Finishing a development branch
Yco-0314/strata/skills/l4-review/finishing-a-development-branch Skill
0★ repoUse when implementation is complete and you need to integrate the work — presents the four structured hand-off options (merge locally / open PR / keep / discard), gates every merge-or-PR claim behind verification-before-completion, and tears down the worktree created by using-git-worktrees. The integration step called by subagent-driven-development and review at the end of work.
Yco-0314/strata/skills/l4-review/review Skill
0★ repoUse when asked to review code, audit a diff, or before a merge — runs three independent read-only lenses over the diff (correctness + spec compliance, over-engineering, security) and reports findings by severity. Triggers: "review this", "code review", "what can we delete", "is this over-engineered", "security review".
Verification before completion
Yco-0314/strata/skills/l4-review/verification-before-completion Skill
0★ repoUse when about to claim work is complete, fixed, or passing, before committing or creating PRs — requires running verification commands and confirming output before any success claim; evidence before assertions always.
Yco-0314/strata/skills/l5-meta/skill-validator Skill
0★ repoUse to audit skill QUALITY (distinct from skill-eval, which measures behavioral effect) — scores every SKILL.md on six axes via an LLM judge and runs a deterministic token-budget check. Triggers: "validate the skills", "skill quality", "are the skills well-written", "audit SKILL.md", "skill scorecard".
yuelenghan/orbit/skills/code-review Skill
0★ repoUse when a repository pull-request review needs linked work-item or design-document context, including trigger-only validations that should skip shell or host-resource discovery and collect only missing review inputs.
yuelenghan/orbit/skills/deployment-verification Skill
0★ repoVerify deployment outcomes by checking build status, PR merge state, quality gates, and optional smoke tests. Use for post-deploy verification, rollback decision support, or deployment health assessment. Trigger phrases: '验证部署', '部署验证', '检查部署状态', 'deploy check', 'verify deployment', 'smoke test', '回滚建议', '部署健康度'.
yuelenghan/orbit/skills/github Skill
0★ repoUse when the user needs GitHub repository, branch, pull request, comment, review, or commit operations through the packaged launcher and local CLI runtime.
yuelenghan/orbit/skills/gitlab Skill
0★ repoUse when the user needs GitLab repository, branch, merge request, comment, review, or commit operations through the packaged launcher and local CLI runtime.
yuelenghan/orbit/skills/monitor-check Skill
0★ repoCheck runtime health and metrics from cloud monitoring platforms. Use for service health assessment, alert review, metric queries, or dashboard links. Trigger phrases: '监控检查', '服务健康度', '查看告警', 'check alerts', 'monitoring', 'metric query', '运行时监控', '云监控', 'CloudWatch', '阿里云监控', '阿里云告警'.
poorna-prakash-sr/Cynic/skills/cynic-review Skill
0★ repoReview the current diff or recent changes for over-engineering, dependency bloat, unnecessary abstractions, and scope creep.
poorna-prakash-sr/Cynic/.claude-plugin/skills/cynic-review Skill
0★ repoReview the current diff or recent changes for over-engineering, dependency bloat, unnecessary abstractions, and scope creep.
poorna-prakash-sr/Cynic/.codex-plugin/skills/cynic-review Skill
0★ repoReview the current diff or recent changes for over-engineering, dependency bloat, unnecessary abstractions, and scope creep.
poorna-prakash-sr/Cynic/.opencode/skills/cynic-review Skill
0★ repoReview the current diff or recent changes for over-engineering, dependency bloat, unnecessary abstractions, and scope creep.