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
1,8251,872 · page 39 / 62
executing-plansUse when you have a written implementation plan to execute in a separate session with review checkpointssickn33expansion-retentionWhen the user wants to reduce churn, build expansion revenue, automate customer success, or optimize net revenue retention. Also…tech-leads-clubexpense-disciplineSubmit expenses that sail through approval — the capture-at-spend habit, the policy-fluency that prevents rejections (thresholds…mohitagw15856experiment-craftUse this skill when the user wants to debug, diagnose, or systematically iterate on an experiment that already exists, or when…BioTender-maxwritesexternal-skills-catalogCurated catalog of 60+ external Claude Code skills across 8 categories with quality rankings, install instructions, and fallback…vibeevalextract_negative_feedback_categoriesAnalyzes product reviews (including Amazon) to identify and list specific categories of negative feedback with brief explanations…ECNU-ICALKf5Humanization Quality Verifier - Ensures transformation integrity and quality Validates that humanization preserves meaning…brycewang-stanfordfacct-author-responseUse when drafting ACM FAccT author responses — the short factual-correction rebuttal after preliminary reviews, and…brycewang-stanfordfacct-review-processUse when reasoning about how an ACM FAccT submission is evaluated — mutually-anonymous review by a mixed CS+law+social-science…brycewang-stanfordfacct-submissionUse when auditing an ACM FAccT submission for OpenReview readiness — the mandatory abstract-registration gate with focus-area…brycewang-stanfordfactsManage .facts files — atomic, validatable truth statements about a project. Install, check, list, add, edit, remove, and lint…avfacts-refineOperate on @draft facts — collaboratively refine them into precise, actionable @spec facts. Resolve ambiguities, fill gaps…avfal-restoreRestore and fix image quality — deblur, denoise, fix faces, and restore old documents using fal.ai's hosted restoration models.nexu-iofast-review-processUse when reasoning about how a USENIX FAST submission is evaluated, covering double-blind program-committee review with outside…brycewang-stanfordfastp-fastq-preprocessingAll-in-one FASTQ QC and adapter trimming. Auto-detects Illumina adapters, filters low-quality reads, corrects paired-end…BioTender-maxfastqc-quality-analyzerSequencing quality control skill for assessing read quality, adapter contamination, and sequence compositiona5c-aiwritesfcr-literature-positioningUse when positioning a Field Crops Research (FCR) manuscript against the agronomy and crop-science literature so it reads as a…brycewang-stanfordfcr-review-processUse to understand how Field Crops Research (FCR) evaluates a manuscript — initial editor screening against the journal's scope…brycewang-stanfordfcr-workflowUse as the entry point for any Field Crops Research (FCR) manuscript. Routes to the right FCR sub-skill based on where you are in…brycewang-stanfordfeature-devGuide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions…waybarriosfigureEconometrics skill for generating publication-quality figures for top economics journals. Activates when the user asks about…brycewang-stanfordfiguresDesign and format publication-quality figures: chart choice, color, scales, legends, captions, reproducibility.brycewang-stanfordfinancial-due-diligenceGenerate a financial due diligence checklist and analysis framework for any investment, acquisition, or partnership. Use when…mohitagw15856find-similar-functionsUse truffler to find similar or pre-existing JavaScript/TypeScript symbols before implementing new code, especially helpers…millioncofind-skills-comboDiscover and recommend **combinations** of agent skills to complete complex, multi-faceted tasks. Provides two recommendation…agentscope-aifinta-debug-bundleCollect Finta diagnostic information for support. Trigger with phrases like "finta debug", "finta support". 'jeremylongshorefirecrawl-advanced-troubleshootingDebug hard-to-diagnose Firecrawl issues with systematic isolation and evidence collection. Use when standard troubleshooting…jeremylongshorefirecrawl-debug-bundleCollect Firecrawl debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing…jeremylongshorefirecrawl-known-pitfallsIdentify and avoid Firecrawl anti-patterns and common integration mistakes. Use when reviewing Firecrawl code, onboarding new…jeremylongshorefirecrawl-observabilityMonitor Firecrawl scraping pipelines with metrics, credit tracking, and quality alerts. Use when implementing monitoring for…jeremylongshorewritesfirecrawl-reliability-patternsImplement Firecrawl reliability patterns: circuit breakers, crawl fallbacks, and content validation. Use when building…jeremylongshorewritesfirecrawl-sdk-patternsApply production-ready Firecrawl SDK patterns for TypeScript and Python. Use when implementing Firecrawl integrations, building…jeremylongshorewritesfireflies-debug-bundleCollect Fireflies.ai debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing…jeremylongshorefirst-client-contractPut your first client agreement in writing — the eight clauses a simple service contract must have, in plain language a…mohitagw15856first-principles-reviewUse when explicitly asked for first-principles or Occam's-razor review, or when complex decisions involve competing constraints…GanyuanRanfix-chinesePROACTIVE SKILL — automatically apply whenever writing, generating, or editing any text that is mainly in Chinese. No user…brycewang-stanfordmuapi-floor-plan-renderingDesign a 2D floor plan and convert it into a realistic, high-quality 3D architectural rendering.SamurAIGPTflyio-debug-bundleCollect Fly.io debug evidence for support tickets including machine status, logs, health checks, volume state, and networking…jeremylongshorefocs-review-processUse when reasoning about how a FOCS (IEEE Symposium on Foundations of Computer Science) submission is evaluated — the…brycewang-stanfordfocused-fixUse when the user asks to fix, debug, or make a specific feature/module/area work end-to-end. Triggers: 'make X work', 'fix the Y…alirezarezvanifp-errorsStop throwing everywhere - handle errors as values using Either and TaskEither for cleaner, more predictable codesickn33fp-pragmaticA practical, jargon-free guide to functional programming - the 80/20 approach that gets results without the academic overheadsickn33fp-ts-errorsHandle errors as values using fp-ts Either and TaskEither for cleaner, more predictable TypeScript code. Use when implementing…sickn33fp-ts-pragmaticA practical, jargon-free guide to fp-ts functional programming - the 80/20 approach that gets results without the academic…sickn33fp-types-refQuick reference for fp-ts types. Use when user asks which type to use, needs Option/Either/Task decision help, or wants fp-ts…sickn33open-knowledge-pack-software-lifecycle-frame-a-proposalFrame a new design proposal (RFC-shape) under proposals/ — problem before solution, named beneficiary and observable change, real…inkeepframer-common-errorsDiagnose and fix Framer common errors and exceptions. Use when encountering Framer errors, debugging failed requests, or…jeremylongshoreframer-debug-bundleCollect Framer debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support…jeremylongshore
← Prev39 / 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