Review & quality
19,195 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
alexei-led/cc-thingz/src/skills/using-git-worktrees Skill
35★ repoCreates isolated git worktrees for parallel development. Use when starting feature work needing isolation or working on multiple branches simultaneously. NOT for simple branch switching, bulk branch cleanup (use cleanup-git), or git hook/config setup (use configuring-git-hygiene).
saadshahd/moo.md/sound/skills/review Skill
34★ repoUse when reviewing a staged diff or a commit range for soundness against the project's taste rules, including a pre-commit pass or an explicit "sound review".
OutlineDriven/odin-claude-plugin/skills/commit-push-current Skill
34★ repoCommit working-tree changes and push to the current branch: no branch creation, no branch switch, no PR. Use when asked to push to the branch you are already on, including the default branch.
OutlineDriven/odin-claude-plugin/skills/commit-push-pr Skill
34★ repoUse when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.
OutlineDriven/odin-claude-plugin/skills/commit-push Skill
34★ repoUse when asked to ship/publish commits without opening a PR.
OutlineDriven/odin-claude-plugin/skills/commit Skill
34★ repoUse when the user asks to commit/save staged or unstaged changes with a repo-appropriate, value-communicating message.
OutlineDriven/odin-claude-plugin/skills/doc-review Skill
34★ repoUse when the user asks to review or critique a prose planning document — a plan, spec, PRD, requirements doc, or design doc.
OutlineDriven/odin-claude-plugin/skills/git-branchless Skill
34★ repoUse when doing multi-commit work, stack edits, rebases, fixups, stacked-PR publishing, or when the user mentions branchless, smartlog, git move, or git undo.
OutlineDriven/odin-claude-plugin/skills/pr-review Skill
34★ repoUse when the user asks to review a pull request, or wants structured quality, security, and testing feedback on a PR diff.
OutlineDriven/odin-claude-plugin/skills/review-fix-grill-loop Skill
34★ repoUse when the user says "grill my changes" or wants their diff reviewed and fixed iteratively until clean.
OutlineDriven/odin-claude-plugin/skills/review Skill
34★ repoUse when reviewing current work or recent commits, or running a deep review.
OutlineDriven/odin-claude-plugin/skills/security-review Skill
34★ repoRun an adversarial security audit using STRIDE, OWASP, supply-chain checks, secrets scans, and auth analysis. Use when changes touch auth, input parsing, dependencies, or network I/O, or before a production release.
OutlineDriven/odin-claude-plugin/skills/setup-pre-commit Skill
34★ repoUse when the user wants commit-time checks, or says "install husky/pre-commit/lefthook".
OutlineDriven/odin-claude-plugin/skills/strict-validation-setup Skill
34★ repoBootstrap strict-mode tooling and per-task GOALS.md scaffolding so an agentic loop can self-verify.
OutlineDriven/odin-claude-plugin/skills/validation-first-driven Skill
34★ repoDefine state machines, invariants, and temporal properties. Use when building protocols, workflows, concurrent systems, or lifecycle-heavy state.
Verification before completion
OutlineDriven/odin-claude-plugin/skills/verification-before-completion Skill
34★ repoRequires fresh, actually-run evidence before any claim that a task is complete. Use when about to tell the user a task, feature, or fix is done, complete, finished, working, or ready, or about to report a DONE or passing status.
OutlineDriven/odin-claude-plugin/skills/worktree Skill
34★ repoSet up isolated git worktrees: create a new branch for fresh work, or attach a worktree to an existing branch/PR/commit.
awrshift/claude-memory-kit/.kit/advanced/orchestration-layer/skills/second-opinion Skill
34★ repoCross-check the agent's own answer with independent reviewers before bringing it to the user. Use when the user says 'second opinion', 'sanity check', 'cross-check', 'am I missing something', 'stress-test', 'devil's advocate', 'run a full review', 'this is important', 'high-stakes', 'help me choose between', 'critique this', or similar. Three review styles: Devil's Advocate (single critique), Boardroom Debate (parallel multi-reviewer validation), Round-Table (multi-round brainstorm for choosing between paths). Not for factual lookups — use WebSearch for those.
awrshift/claude-memory-kit/.kit/advanced/orchestration-layer/skills/session-review Skill
34★ repoEnd-of-session adversarial review loop. Assemble the session's work into a role-assigned, self-contained brief, then run independent reviewers in parallel — an isolated code-reader (the idea-validator agent) that reads the ACTUAL files and web-checks technology currency, plus an external-family model if you have one — synthesize where they agree vs diverge, apply the cheap-safe fixes immediately, record a measurable plan for the rest, and CHALLENGE reviewer claims you disagree with (never blind-accept). Use at the close of a substantive coding or design session, when the user says "session review", "review my session", "stress-test this session", or types /session-review. Skip for trivial one-off edits.
WenyuChiou/agent-collab-skills/skills/agent-debate Skill
34★ repoUse when a consequential decision needs adversarial review, opposing agent arguments, a second opinion via debate, or explicit trade-off analysis before implementation.
social-media-skills/skills/skills/content-research-and-sourcing Skill
33★ repoThe research-and-sourcing craft — verify the substance of a piece before it publishes: trace stats to primary sources, kill zombie stats, catch AI-hallucinated citations, and attribute properly on social. Use when someone has a stat-heavy draft to make publish-ready, wants to check if a viral statistic is real, asks how to cite sources, used AI research output, or is making health/finance claims. Uses the FACTS framework. Reads brand-profile + the piece's format skill first. AI-supplied citations are guilty until verified; a working link is not verification; aggregators are leads, not the source; where none exists, reframe as owned observation or commission data. The agent verifies where it has search; the human clicks links where it doesn't; verification happens before scheduling; WoopSocial publishes. Never invents studies or reuses retracted stats. Distinct from idea-generation, data-and-original-research, quote-cards, and infographic-and-data-viz.
The same file is in 1 other repository
marian2js/trading-skills/skills/review-learning/post-trade-review Skill
33★ repoGuide a disciplined post-trade review across thesis quality, setup quality, execution, adherence, mistakes, and lessons without turning the result into hindsight theater.
marian2js/trading-skills/skills/thesis-validation/evidence-gap-check Skill
33★ repoIdentify the most important missing facts, assumptions, and unresolved questions that should be answered before a trade or investment idea is trusted, sized, or acted on.
marian2js/trading-skills/skills/thesis-validation/thesis-validation Skill
33★ repoPressure-test a trade or investment thesis by clarifying the core claim, evidence, invalidation, timeframe, and dependency chain before the user turns it into an entry, stop, or size.
marian2js/trading-skills/skills/trade-construction/execution-plan-check Skill
33★ repoReview whether a trade plan is operationally executable by checking order type logic, liquidity and spread risk, event timing, stop realism, and whether the user can actually implement the plan cleanly.
marian2js/trading-skills/skills/trade-construction/risk-reward-sanity-check Skill
33★ repoUse when the user wants to test whether a proposed entry, stop, and target structure is coherent, asymmetric enough, and vulnerable to obvious failure modes before the trade is placed.
marian2js/trading-skills/skills/workflows/portfolio-risk-review Skill
33★ repoOrchestrate a whole-book risk review by checking concentration, correlated exposure, catalyst clustering, market-context sensitivity, and live-position fragility before the user adds, holds, or reduces portfolio risk.
marian2js/trading-skills/skills/workflows/pre-trade-check Skill
33★ repoOrchestrate a disciplined pre-trade workflow by routing a watchlist or trade idea through the minimum set of underlying skills needed to decide whether the trade is ready, not ready, or should be resized or reworked first.
zxkane/autonomous-dev-team/skills/autonomous-review Skill
no license33★ repoUse to perform an end-to-end PR review and reach an approve/request-changes verdict — including verifying acceptance criteria, running E2E tests via browser automation, resolving merge conflicts, and (when verdict passes) merging the PR. Triggers on phrases like "review this PR", "decide whether to approve and merge", "run E2E verification", "resolve merge conflicts on PR #N", or when the dispatcher hands off a PR labeled `pending-review` / `reviewing` for autonomous review. Distinct from in-flight dev-side self-review (that lives in autonomous-dev's pr-review step).
aligundogdu/symfony-hexagonal-skill/skills/symfony-validation Skill
no license32★ repoSymfony validation — 3-layer validation strategy, constraints, DTO validation, domain invariants, validation groups, custom validators. Triggers on: validation, validator, constraint, DTO validation, input validation, invariant, assert, validation group
The same file is in 2 other repositories
ZICXR/A-Stock-Skills/skills/04-stock-analysis/trade-review Skill
32★ repoA 股交割单分析诊断工具。当用户说"分析我的交割单"、"看看我的操作问题"、"交易复盘"、"我的操作哪里有问题"、"帮我诊断交易"时,Claude 应使用此 Skill。支持多种券商交割单格式(CSV/Excel)自动识别,从盈亏统计、持仓周期、操作行为、仓位管理、买卖时机 5 个维度诊断问题,结合行情数据 + AI 信号给出改进建议。**核心价值: 让交割单变成教科书**。
jmxt3/gitscape.ai/.agents/skills/code-review-and-quality Skill
32★ repoConducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
The same file is in 9 other repositories
jmxt3/gitscape.ai/.agents/skills/git-workflow-and-versioning Skill
32★ repoStructures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.
The same file is in 9 other repositories
woodfishhhh/EZ_math_model/skills/ez-math-model/external/paper-orchestra/skills/literature-review-agent Skill
32★ repoStep 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover candidate papers via web search, verify them through Semantic Scholar (Levenshtein > 70 fuzzy title match, temporal cutoff, dedup by paperId), build a BibTeX file, and draft Introduction + Related Work using ≥90% of the verified pool. Runs in parallel with the plotting-agent. TRIGGER when the orchestrator delegates Step 3 or when the user asks to "find citations for my paper", "draft the related work", or "build the bibliography".
The same file is in 2 other repositories
woodfishhhh/EZ_math_model/skills/ez-math-model/external/paper-orchestra/skills/plotting-agent Skill
32★ repoStep 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimental_log.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER when the orchestrator delegates Step 2 or when the user asks to "generate the figures for my paper" or "render the plots from this experiment log".
The same file is in 3 other repositories
Verification before completion
woodfishhhh/EZ_math_model/skills/ez-math-model/tools/verification-before-completion Skill
32★ repoUse before EZ_math_model declares quality_audit, packaging, or final delivery complete, especially when pass/fail claims must be backed by files, commands, counts, or concrete evidence.
atlassian/forge-skills/skills/forge-security-review Skill
31★ repoPerforms a white-box security review of Atlassian Forge apps using structured, Forge-specific security rules and evidence-driven reporting. Use when the user asks for a Forge security review, security audit, vuln assessment, pentest-style code review, authz review, tenant isolation analysis, web trigger hardening, or static analysis execution for a Forge app.
The same file is in 3 other repositories
georgekhananaev/claude-skills-vault/.claude/skills/domain-checker Skill
31★ repoBulk domain availability checker. Use when the user wants to check whether one or many domain names are available for registration (e.g., "is acme.com free", "check these 50 domains", "find an available .io for my brand"). Supports any TLD (.com/.net/.io/.ai/.dev/.app/...), parallel checking, three input modes (CLI args / file / stdin), bare-name + TLD-list expansion, and table/JSON/CSV output. Python stdlib only — no pip installs, no API keys.
georgekhananaev/claude-skills-vault/.claude/skills/mermaid-diagram Skill
31★ repoGenerate beautiful Mermaid diagrams — flowcharts, sequence, ER, class, state, pie, gantt, mindmap, timeline, gitgraph, C4, kanban, block, quadrant, sankey, XY charts. Renders to PNG locally and Markdown for GitHub. Use when the user asks for diagrams, visualizations, schemas, flowcharts, architecture overviews, database schemas, API flows, project timelines, git branching strategies, org charts, or any visual representation of systems, workflows, or data.
georgekhananaev/claude-skills-vault/.claude/skills/upgrade-packages-js Skill
31★ repoSafely upgrade JavaScript packages with breaking change detection, migration guidance, and automated code migrations (npm/pnpm/yarn). Cross-platform with git safety branch enforcement.
Borda/AI-Rig/plugins/cc_develop/skills/review Skill
31★ repoA collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.
Borda/AI-Rig/plugins/cc_oss/skills/resolve Skill
31★ repoA collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.
Borda/AI-Rig/plugins/cc_oss/skills/review Skill
31★ repoA collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.
Borda/AI-Rig/plugins/cc_research/skills/verify Skill
31★ repoA collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.
Borda/AI-Rig/plugins/codex-rig/skills/code-review Skill
31★ repoA collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.
Zhonghao1995/agentic-swmm-workflow/skills/swmm-design-review Skill
31★ repoScore a completed SWMM run against a configurable YAML rulebook of design checks — GB50014-style standards for real catchments, or the reference-free physical-plausibility rulebook for synthesized networks. Reads the run's existing manifest.json / model.rpt / model.inp and never re-runs SWMM. Use it post-run for compliance or plausibility review; continuity gating stays with postflight.
maystudios/claude-skills/opencode Skill
31★ repoInvoke OpenCode CLI as a sub-agent to leverage alternative AI models (GPT-5.x, Codex, local models) for code implementation, review, debugging, research, and second opinions. Use when the user asks to "use opencode", "get a second opinion from GPT/Codex", "implement with opencode", "review with opencode", "let opencode handle this", "use a different model", or wants cross-model validation. Also triggers when the user explicitly names an OpenCode model (e.g., "use gpt-5.4", "use codex") or wants to delegate a task to a non-Claude AI system. Supports all providers configured in the user's OpenCode installation (OpenAI, GitHub Copilot, local models via Ollama/LM Studio, and OpenCode's own free-tier models).
eugenelim/agent-ready-repo/.agents/skills/operational-safety Skill
31★ repoProgressive-disclosure operational-safety-depth modules for the work-loop. Holds failure-mode-keyed checklists the quality-engineer reviewer reasons from (state-and-idempotency, blast-radius, environment-isolation, cost-and-teardown, drift-and-rollback, observability-and-smoke), plus cloud-implementation-craft, the module also inlined into the implementer's EXECUTE brief. Each is grounded in standing operational taxonomy (AWS Well-Architected, Google SRE, the Terraform/Pulumi Day-1/Day-2 split). The orchestrator loads only the matching modules and inlines them into the reviewer's REVIEW brief — and cloud-implementation-craft into the implementer's EXECUTE brief — when infra/destructive work is detected; the subagent never self-discovers this skill. Not a reviewer prompt itself — it is the depth library the reviewer and implementer reason from. Carves against security-checklists on the reliability-vs-security lens.
eugenelim/agent-ready-repo/packages/agentbundle/tests/fixtures/creds/skills/conforming Skill
31★ repoA credentialed-CLI fixture skill that satisfies every AC26 check; lint should report zero findings.
eugenelim/agent-ready-repo/packs/architect/.apm/skills/architect-design Skill
31★ repoThe complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discovery → build → release) over a catalogue of curated packs: skills, subagents, and hooks, each installed in one line. It's npm for your coding agent. Any agent, any stack — Claude Code, Codex, Cursor, Copilot, Gemini, Kiro.
eugenelim/agent-ready-repo/packs/architect/.apm/skills/architect-review Skill
31★ repoThe complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discovery → build → release) over a catalogue of curated packs: skills, subagents, and hooks, each installed in one line. It's npm for your coding agent. Any agent, any stack — Claude Code, Codex, Cursor, Copilot, Gemini, Kiro.
eugenelim/agent-ready-repo/packs/converters/.apm/skills/render-proof Skill
31★ repoRender a Markdown file as a self-contained, offline HTML proof artifact styled for human review. Use when the user asks to "render this for review", "proof this draft", "give me a proof of this document", "show me this markdown rendered", or "make this readable for a reviewer". Outputs a single HTML file that opens in any browser with no server or network access at view time. Not for slides, presentations, or publication — use markdown-to-html for that. The rendered output uses a muted stone/slate palette deliberately distinct from the publication look.
eugenelim/agent-ready-repo/packs/core/.apm/skills/operational-safety Skill
31★ repoProgressive-disclosure operational-safety-depth modules for the work-loop. Holds failure-mode-keyed checklists the quality-engineer reviewer reasons from (state-and-idempotency, blast-radius, environment-isolation, cost-and-teardown, drift-and-rollback, observability-and-smoke), plus cloud-implementation-craft, the module also inlined into the implementer's EXECUTE brief. Each is grounded in standing operational taxonomy (AWS Well-Architected, Google SRE, the Terraform/Pulumi Day-1/Day-2 split). The orchestrator loads only the matching modules and inlines them into the reviewer's REVIEW brief — and cloud-implementation-craft into the implementer's EXECUTE brief — when infra/destructive work is detected; the subagent never self-discovers this skill. Not a reviewer prompt itself — it is the depth library the reviewer and implementer reason from. Carves against security-checklists on the reliability-vs-security lens.
eugenelim/agent-ready-repo/packs/desk-research/.apm/skills/desk-research-project-check Skill
31★ repoPassive stop-signal for a research project — reads the synthesis matrix and memos by eye and reports whether the corpus has stopped changing the structure (theoretical saturation), plus a recommendation. Triggers on project-lifecycle phrasing — "is this project saturated", "should I keep gathering", "check the stop signal" — inside an existing project folder. It NEVER advances phase and computes no counter, score, or metric; the saturation judgment is qualitative and the human decides. It MAY optionally write a verdict_status string into overview.md (the single permitted light state write) — nothing more. Prompt-only by construction.
eugenelim/agent-ready-repo/packs/experience-design/.apm/skills/design-review Skill
31★ repoEvaluate an existing screen, flow, or mockup with a severity-rated findings list: quality-floor pass (states, a11y, motion), heuristic eval (Nielsen's 10), marketing clarity pass (tweet test, five-second scan, painkiller-first — fires on above-fold copy with a persuasion goal), and taste critique (grounded aesthetic reference + platform fit). Triggers on 'critique this design', 'review this screen', 'what is wrong with this mockup', 'do a heuristic eval', 'is this usable', 'does this fit our aesthetic', 'does this page convert', 'is this copy compelling', 'tweet test'. Do NOT use to name a felt direction (use creative-direction), to derive tokens (use design-system), or to structure hierarchy (use information-architecture).
eugenelim/agent-ready-repo/packs/product-engineering/.apm/skills/plan-validation Skill
31★ repoUse to turn a converged product's load-bearing assumptions into a validation plan — and to scaffold the primary-research instruments that would test them. Triggers on "plan the validation", "how do we validate these assumptions", "turn assumptions into a validation plan", "scaffold an interview guide / usability test", "what would confirm this". Produces assumption → kill-condition → real-world-activity hooks and the instrument scaffolds (interview guide, usability-test plan, transcript-synthesis frame). Do NOT use to run the sessions (out of charter — a human runs them), to test a single bet (use `de-risk-intent`), or to converge (the discovery loop's job).
soupandpsy/amazing-psycoder-skills/amazing-psycoder/psy-ana-reviewer Skill
31★ repoUse for reviewing data analysis scripts at any stage — from analysis plan through completed script. Performs reproducible-research checks: seed, effect size, multiple comparison correction, assumption testing, exclusion logging, and session info. Detects analysis anti-patterns and outputs a graded audit report with readiness label. Does NOT generate or fix analysis code. Trigger for 检查分析代码、analysis review、统计方法审查、分析脚本有没有问题、check analysis script / 分析コードレビュー、分析監査 / Analyse-Code-Review, Analyse-Audit / revue de code analyse, audit analyse.
soupandpsy/amazing-psycoder-skills/amazing-psycoder/psy-exp-reviewer Skill
31★ repoUse for reviewing psychological experiment code quality at any stage — from early design idea through completed code. Supports five modes: code-audit (full platform-aware code review with smoke test protocol), config-audit (pre-code design review), implementation-plan-review (architecture review), triage-only (missing-information checklist from natural-language idea), and blocked (insufficient input). Does NOT generate or fix code. Trigger for 检查实验代码、code review、实验程序审查、能不能正式采集、代码有没有问题、check experiment code、实验设计有没有问题、帮我看看这个实验方案 / 実験コードレビュー、実験監査 / Experiment-Code-Review, Code-Audit, Experiment prufen / revue de code experimental, audit de code.
EAIconsulting/cowork-skills-library/skills/cowork-health-check Skill
no license30★ repoAudits your Cowork setup across five categories, scores each one, and gives you a prioritized improvement plan. For reviewing how well you are using Cowork, when optimizing your workspace configuration, or during a quarterly productivity review. Use when the user says "health check", "am I using cowork right", "optimize my setup", "cowork audit", "what am I missing", "is my setup good", or "how do I get more out of cowork".
The same file is in 2 other repositories
bjcoombs/ai-native-toolkit/skills/deslop Skill
30★ repoDetect and remove the telltale signs of AI-generated 'slop' from any written text - articles, reports, emails, essays, bios, marketing copy, documentation, encyclopedia entries, or anything meant to read as if a thoughtful human wrote it. Apply silently as a quality gate before finalizing substantial prose, and explicitly when asked to clean a draft. TRIGGER when the user says 'make this sound less like AI', 'remove the AI tells', 'de-slop this', 'check if this reads as AI-written', 'make it sound human', 'edit out the ChatGPT voice', or critiques a draft as generic, puffy, or robotic. Based on Wikipedia's 'Signs of AI writing' field guide.