Agent skills

Code Review & Quality skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
2,936 found
2,5932,640 · page 55 / 62
restud-identificationUse when selecting, implementing, or stress-testing the causal identification strategy for an empirical The Review of Economic…brycewang-stanfordrestud-literature-positioningUse when positioning a The Review of Economic Studies (REStud) manuscript against the closest related work — confronting the…brycewang-stanfordrestud-rebuttalUse when a referee report or R&R has arrived for a The Review of Economic Studies (REStud) manuscript and a point-by-point…brycewang-stanfordrestud-referee-strategyUse when anticipating the referee pool and their likely objections for a The Review of Economic Studies (REStud) manuscript, and…brycewang-stanfordrestud-robustnessUse when the main results of a The Review of Economic Studies (REStud) manuscript exist but referee-anticipating checks —…brycewang-stanfordrestud-tables-figuresUse when the exhibits in a The Review of Economic Studies (REStud) manuscript need to be made publication-grade — regression…brycewang-stanfordrestud-theory-modelUse when building, sharpening, or stress-testing the theoretical model in a The Review of Economic Studies (REStud) manuscript —…brycewang-stanfordrestud-topic-selectionUse when evaluating whether a research idea clears the REStud top-5 bar, or when sharpening a fuzzy idea into one clean original…brycewang-stanfordrestud-workflowUse when deciding which restud-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through…brycewang-stanfordrestud-writing-styleUse when polishing the prose of a The Review of Economic Studies (REStud) manuscript — introduction, abstract, and overall…brycewang-stanfordretellai-common-errorsDiagnose and fix Retell AI voice agent errors: call failures, webhook issues, voice quality. Use when encountering Retell AI…jeremylongshoreretellai-debug-bundleRetell AI debug bundle \u2014 AI voice agent and phone call automation.\n\ Use when working with Retell AI for voice agents…jeremylongshorewritesretrospect-external-babysitter-runFor a repository in the babysitter-users catalog, locate its babysitter processes and any committed runs (.a5c/runs/<runId>/) and…a5c-airevacc-contribution-framingUse when results exist but the "so what for accounting" is thin for a Review of Accounting Studies (RAST) manuscript — turning…brycewang-stanfordrevacc-literature-positioningUse when the contribution relative to the accounting frontier and the sibling journals is fuzzy for a Review of Accounting…brycewang-stanfordrevacc-review-processUse when calibrating expectations for the Review of Accounting Studies (RAST) review cycle — its fast, first-round-decision…brycewang-stanfordrevacc-topic-selectionUse when scoping or pressure-testing the research question for a Review of Accounting Studies (RAST) manuscript — confirming it…brycewang-stanfordrevacc-workflowUse when deciding which revacc-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through…brycewang-stanfordrevacc-writing-styleUse when the prose is the bottleneck for a Review of Accounting Studies (RAST) manuscript — front-loading the contribution…brycewang-stanfordrevedres-comprehensiveness-and-balanceUse when testing exhaustiveness, risk-of-bias, heterogeneity, and sensitivity for a Review of Educational Research (RER) review…brycewang-stanfordrevedres-editor-strategyUse when anticipating editor and reviewer expectations, framing the contribution, and positioning scope for a Review of…brycewang-stanfordrevedres-organizing-frameworkUse when turning a screened, coded corpus into an analytic spine that advances theory or policy for a Review of Educational…brycewang-stanfordrevedres-proposal-and-commissioningUse when writing the protocol, fixing scope and eligibility, and (where applicable) preregistering a systematic review or…brycewang-stanfordrevedres-revisionUse when an editor/reviewer decision letter arrives on a Review of Educational Research (RER) review or meta-analysis and you…brycewang-stanfordrevedres-topic-selectionUse when deciding whether a question is synthesis-worthy and RER-scale before committing to a Review of Educational Research…brycewang-stanfordrevedres-workflowUse when deciding which revedres-* sub-skill to invoke next, or when sequencing a systematic review, meta-analysis, or critical…brycewang-stanfordrevedres-writing-styleUse when drafting or revising prose, the 150-word abstract, and the introduction in the Review of Educational Research (RER)…brycewang-stanfordreview-a-skillUse when evaluating whether a skill belongs in a library. Preview content, check frontmatter, validate structure, and decide…MoizIbnYousafreview-agent-setupConfigure human-in-the-loop gating for AI agent review actions in Claude Code. Use when setting up a project where an agent may…wshobsonreview-and-refactorReview and refactor code in your project according to defined instructionsgithubreview-and-simplify-changesReview a git diff or explicit file scope for reuse, code quality, efficiency, clarity, and standards issues, then optionally…sickn33gsd:review-backlogReview and promote backlog items to active milestonedavepoonwritesreviewAll quality reviews — routes to appropriate critics based on target file type and flags. Replaces /paper-excellence, /proofread…brycewang-stanfordwritesreview-codeReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this…rengwureview-comments-resolverResolve a document's forty review comments systematically — triage by type (accept, push back, conflict, out-of-scope), batch the…mohitagw15856review-durchfuehrenWenn es um /tabellenreview-3d:review-durchführen in Tabellenreview 3D geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und…Klotzkettereview-engagement-abgrenzung-kammerantwort-uWenn es um Review Engagement Abgrenzung Kammerantwort U in Berufsrecht Wirtschaftsprüfer geht: ordnet Akteninhalt, Belege, Lücken…Klotzkettereview-engagement-abgrenzung-rechtsprechungsWenn es um Review Engagement Abgrenzung Rechtsprechungs in Berufsrecht Wirtschaftsprüfer geht: zerlegt Ergebnis, Frist…Klotzkettereview-engagement-rotation-coolingWenn es um Review Engagement Rotation Cooling in Berufsrecht Wirtschaftsprüfer geht: zerlegt Ergebnis, Frist, Zuständigkeit…Klotzkettereview-engagement-rotation-cooling-sanktionenWenn es um Review Engagement Rotation Cooling Sanktionen in Berufsrecht Wirtschaftsprüfer geht: klärt Rolle, Ziel, Frist…Klotzkettereview-fix-signoff-loopUse when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until…AgentWorkforcereview-grantRun a 6-agent pre-submission panel review for a grant proposal targeting a specified funder or programbrycewang-stanfordreview-implementingProcess and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code review…mhattingpetereview-juliaRun the Julia code review protocol on Julia scripts. Checks code quality, type stability, parallel computing patterns, and…brycewang-stanfordwritesreviewAdversarial senior review of the spec before any code is written. Constructs a skeptical reviewer whose authority comes from the…JuliusBrusseereview-monitoringSet up systematic review monitoring across e-commerce platforms. Track new reviews, detect negative review spikes, monitor…nexscope-aireview-of-accounting-studiesUse when targeting Review of Accounting Studies (RAST) or deciding whether an accounting manuscript fits this venue. Encodes the…brycewang-stanfordreview-of-economic-dynamicsUse when targeting Review of Economic Dynamics (RED) or deciding whether a quantitative-macro / dynamic-economics manuscript fits…brycewang-stanford
← Prev55 / 62Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going