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
1,2491,296 · page 27 / 62
testing-properties-and-invariantsUse when testing properties and invariants is required during quality work, especially when the result must be traceable…casioreview20-glitchtesting-service-contractsUse when testing service contracts is required during quality work, especially when the result must be traceable, independently…casioreview20-glitchtesting-service-resilienceUse when testing service resilience is required during quality work, especially when the result must be traceable, independently…casioreview20-glitchtesting-state-machinesUse when testing state machines is required during quality work, especially when the result must be traceable, independently…casioreview20-glitchtesting-state-modelsUse when testing state models is required during quality work, especially when the result must be traceable, independently…casioreview20-glitchtiktok-script-writerWrite short-form video scripts for TikTok, Instagram Reels, and YouTube Shorts that promote affiliate products with strong hooks…Affitortimeshare-contract-decoderDecode a timeshare contract before signing — the lifetime cost math, the perpetuity and fee-escalation clauses, the rescission…mohitagw15856tools-repo-reviewComprehensive GitHub repository analysis for engineering managers with contribution stats, code quality review, team health…majiayu000transformers-jsRun Hugging Face models in JavaScript or TypeScript with Transformers.js in Node.js or the browser.majiayu000triageTriage review findings interactively — approve, skip, or prioritize each issue. Use after /phx:review to filter findings before…oliver-kriskatrueskill-rankDomain-agnostic TrueSkill batch ranking via LLM-as-judge. Ranks any list of text items using overlapping subsets dispatched to…majiayu000twinmind-performance-tuningOptimize TwinMind transcription accuracy and speed with Ear-3 model configuration, audio quality tuning, and caching strategies.…jeremylongshorewritestypescriptTypeScript configuration, strict mode, generics, and type utilities.a5c-aiwritestypescript-advanced-typesComprehensive guidance for mastering TypeScript's advanced type system including generics, conditional types, mapped types…sickn33typescript-advanced-typesMaster TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility…wshobsonunfair-dismissal-screener-andrew-birdScreens a dismissal — proposed or already done — against the unfair dismissal framework for England & Wales, and shows where it…lawve-aiunsloth-ttsUnsloth-tts brings the library's performance optimizations to speech synthesis models. Specifically optimized for the Llama-based…majiayu000using-trajectories-sdkUse when programmatically creating or managing agent trajectories in TypeScript - provides TrajectoryClient for persistent…majiayu000video-explorerThis skill should be used when analyzing video files. You cannot process video directly, so this skill extracts frames…majiayu000vigil-incidentIncident response — diagnose production issues, find root cause, propose fix with rollback. Use when asked about "something is…jeremylongshorewritesvolt-reconFirmware reconnaissance for takeover — inventory the MCU, peripherals, RTOS, protocols, OTA, power management, and assess code…jeremylongshorewriteswavecap-audioAnalyze recorded audio files from WaveCap. Use when the user wants to inspect audio recordings, check audio quality, list…majiayu000wavecap-llmConfigure WaveCap LLM-based transcription correction. Use when the user wants to enable/disable LLM correction, change models…majiayu000web-search-andiFast, high-quality web search with intelligent ranking and instant answersgooseworks-aiwebshop-result-page-navigatorNavigates through paginated search results by moving to the next or previous page. Use this skill when the current page of…zjunlpweekly-gtm-reportUse when generating weekly GTM performance reports, summarizing pipeline activity, reviewing outreach metrics, or creating…majiayu000weekly-reportGenerate weekly performance reports aggregating metrics across accounts and campaigns, highlighting winners and losers…majiayu000whatsapp-logsRead and analyze WhatsApp bot logs for debugging, monitoring, and troubleshooting. Use this skill when asked to "check WhatsApp…majiayu000when-debugging-ml-training-use-ml-training-debuggerDebug ML training issues and optimize performance including loss divergence, overfitting, and slow convergencemajiayu000when-optimizing-prompts-use-prompt-optimization-analyzerActive diagnostic tool for analyzing prompt quality, detecting anti-patterns, identifying token waste, and providing optimization…majiayu000win-loss-analysisAnalyze why deals are won and lost and turn it into an action plan. Use when asked to run a win/loss analysis, review closed-won…mohitagw15856workflows:reviewRun multi-agent econometric review on estimation code, identification arguments, and research artifactsbrycewang-stanfordwriteswriting-promptsUse when crafting prompts for LLMs to improve response quality, accuracy, consistency, and task performancemajiayu000writing-promptsUse when crafting prompts for LLMs to improve response quality, accuracy, consistency, and task performancemajiayu000writing-promptsUse when crafting prompts for LLMs to improve response quality, accuracy, consistency, and task performancemajiayu000writing-styleStructural pattern analysis for writing-mode review. Performs paragraph-level decomposition and pattern aggregation. Invoked by…majiayu000yaml-prompt-makerHelp users who struggle with prompt design by turning their vague questions or tasks into high-quality, structured Japanese YAML…majiayu000yargs-scaffolderGenerate Yargs-based CLI applications with commands, positional args, middleware, and TypeScript support. Creates a complete…a5c-aiwritesmeta-evalUse when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to start — they have…agentscope-ai01-content-calendar-globalMonthly content calendar for global businesses — multi-channel posting schedule with funnel ratio, content pillars, repurposing…minhnv0807aaag-review-processUse when you need to understand how the Annals of the American Association of Geographers evaluates a manuscript —…brycewang-stanfordaaai-author-responseUse when drafting an AAAI author response (rebuttal) under the single short character-limited author-feedback window, the no-URL…brycewang-stanfordaaai-review-processUse when explaining or planning around AAAI's two-phase review process, Phase 1 rejection risk, Phase 2 additional reviews…brycewang-stanfordaaai-workflowUse when planning an AAAI project timeline from topic selection through abstract, OpenReview submission, two-phase review…brycewang-stanfordaamas-review-processUse when explaining or planning around AAMAS peer review, covering OpenReview review release, the double-blind rebuttal on…brycewang-stanfordaas-review-process当你在需要理解《自动化学报》(Acta Automatica Sinica, AAS)…brycewang-stanfordabridge-webhooks-eventsImplement Abridge webhook handling for clinical documentation events. Use when receiving note completion notifications, encounter…jeremylongshorewritesacademic_expert_reviewer_with_recommendationsReviews academic text from a domain expert perspective, identifying specific areas for modification one by one with revision…ECNU-ICALK
← Prev27 / 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