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
1,6811,728 · page 36 / 62
Customer Journey Mapping Presentation Outline GeneratorGenerates a comprehensive slide-by-slide outline for a Customer Journey Mapping presentation based on a specific structure…ECNU-ICALKcustomer_review_response_writerDrafts professional public responses to customer reviews (positive, negative, or rating-only) based on sentiment and specific…ECNU-ICALKcvpr-review-processUse when reasoning about how CVPR review actually works at 16,000-submission scale, covering the OpenReview pipeline and…brycewang-stanforddac-related-workUse when writing or auditing the related-work and positioning of an ACM/IEEE Design Automation Conference (DAC) Research…brycewang-stanforddac-review-processUse when reasoning about how an ACM/IEEE Design Automation Conference (DAC) Research Manuscript is evaluated, covering…brycewang-stanforddac-workflowUse to plan a full ACM/IEEE Design Automation Conference (DAC) Research-Manuscript campaign backward from the…brycewang-stanforddac-writing-styleUse when drafting or tightening the prose of an ACM/IEEE Design Automation Conference (DAC) Research Manuscript, covering the…brycewang-stanforddead-codeFind unused functions and dead code in the codebaseparcadeiwritesdebugDebug issues in the MCP Gateway Registry using first-principles thinking. Invoke when something is broken, timing out, returning…agentic-communitydebugInvestigate-then-decide root-cause analysis for a defect whose cause is unknown (distinct from /fix, which assumes a known bug).…arbiterForgegsd:debugSystematic debugging with persistent state across context resetsdavepoonwritesdebug-hooksSystematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.parcadeiwritesdebugDebug container agent issues. Use when things aren't working, container fails, authentication problems, or to understand how the…nanocoaidebug-packageLobeHub debug package and log namespace guide. Use when adding debug() logging, choosing lobe-* namespaces, troubleshooting DEBUG…lobehubdebugging-broken-jobsTriage entry-point for any "the job ran but something's wrong" situation in a Friday workspace. Loads when a job tool returns…friday-platformdebugging-toolkitUse when working with debugging toolkit smart debug (Alias for debugging-toolkit-smart-debug)sickn33debugging-toolkit-smart-debugUse when working with debugging toolkit smart debugsickn33decision-autopsyJudge a past decision by its PROCESS, not its outcome — because good decisions lose and bad decisions win, and teams that can't…mohitagw15856decision-journalRecord decisions the way good judgment compounds — the reasoning, the alternatives, the probabilities, and what would change your…mohitagw15856deck-review-rubricReview a deck against a rubric instead of taste — the five dimensions (argument, evidence, density, arc, honesty), the…mohitagw15856deeprefineAgent-native DeepRefine refinement loop — same control flow as DeepRefine.refine(), graphify search instead of FAISS, session…HKUST-KnowCompdemand-forecast-reviewInterrogate a demand forecast before the business commits supply and inventory to it. Use when asked to review a demand plan…mohitagw15856demand-letterDraft a firm, professional demand letter that states the facts, the legal/contractual basis, the specific demand, and a deadline.…mohitagw15856demog-rebuttalUse when writing the response to a Demography (PAA / Duke University Press) revise-and-resubmit. Demography review is…brycewang-stanforddemog-review-processUse to understand how Demography (PAA / Duke University Press) evaluates a manuscript — double-blind review, pre-review/desk…brycewang-stanforddesign-negotiationAdvocate for design quality, scope, and time with cross-functional partners and leadership using evidence and shared goals.Owl-Listenerdesign-orchestrationOrchestrates design workflows by routing work through brainstorming, multi-agent review, and execution readiness in the correct…sickn33design-reviewSkill for formal design review preparation and execution (PDR/CDR)a5c-aiwritesdesign-review-facilitatorDesign review planning and execution skill for structured design phase gate reviews per 21 CFR 820.30a5c-aiwritesdesign-review-processEstablish design review gates with criteria, checklists, and approval workflows.Owl-ListenerdeslopUse when user wants to clean AI slop from code. Use for cleanup, remove debug statements, find ghost code, repo hygiene.agent-shdeslopRemove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Cleans up boilerplate…rohitg00devpsych-literature-positioningUse when positioning a Developmental Psychology (APA) manuscript against the developmental literature. Positioning here must…brycewang-stanforddevpsych-review-processUse when you need to understand how Developmental Psychology (APA) evaluates a manuscript — masked peer review, editorial…brycewang-stanforddfg-kollegen-review-organisierenWenn es um DFG: Kollegen-Review organisieren in DFG-Förderantrag geht: erstellt den passenden Entwurf aus Sachverhalt, Norm…Klotzkettedfm-reviewSkill for design for manufacturing review and optimizationa5c-aiwritesdiagnosePerform a systematic diagnostic scan of an AI workflow across 5 quality dimensions — prompt quality, context efficiency, tool…githubqdrant-search-quality-diagnosisDiagnoses Qdrant search quality issues. Use when someone reports 'results are bad', 'wrong results', 'not relevant results'…githubdiff-review-strategyPR size-based review depth, performance review checklist, architecture conformance checks, and framework-specific review patterns.vibeevaldiscovery-eyesRead your team's messages the way opposing counsel would in litigation discovery — prevention training that makes communication…mohitagw15856Discrete Math Study Guide and Practice GeneratorGenerates a comprehensive study guide, expected problem formats, general solution strategies, and similar practice problems with…ECNU-ICALKdispatching-parallel-agentsThe parallel fan-out primitive. Routed to by any skill or command that splits work across independent units and dispatches an…arbiterForgeDissertation Exclusion Criteria WriterWrites first-person paragraphs for a dissertation methodology section explaining why studies were excluded from a systematic…ECNU-ICALKdoc-restructure-liveRestructure the user's REAL Google Doc — open it, tighten and reorganise it, and return a clean version — not advice on how to…mohitagw15856doc-versioning-disciplineKeep living documents trustworthy over time — the status header (draft/active/superseded) that tells readers what they're…mohitagw15856docs-reviewReview documentation changes for compliance with the Metabase writing style guide. Use when reviewing pull requests, files, or…foryourhealth111-pixelwritesdocumentation-writerDiátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by…githubdocxCreate, edit, and analyze Word documents with tracked changes, comments, and formatting. Useful for design briefs, copy docs, and…nexu-io
← Prev36 / 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