Agent skills

Other 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
21,420 found
3,2173,264 · page 68 / 447
faion-user-researcherUser research: personas, user interviews, jobs-to-be-done, pain point research.majiayu000writesfaion-ux-researcherUX research: user interviews, usability testing, personas, journey maps.majiayu000fairchemExpert guidance for Meta's FAIRChem library - machine learning methods for materials science and quantum chemistry using…majiayu000fal-generateGenerate images and videos using fal.ai AI modelsmajiayu000fal-generateGenerate images and videos using fal.ai AI modelsmajiayu000fal-image-editAI-powered image editing with style transfer and object removalmajiayu000fal-image-editAI-powered image editing with style transfer and object removalmajiayu000fal-text-to-imageGenerate, remix, and edit images using fal.ai's AI models. Supports text-to-image generation, image-to-image remixing, and…majiayu000falcon-deep-researchExecute deep research protocols using the Falcon specialized research framework.majiayu000fantasyGame-inspired fantasy aesthetic with bold, premium visuals, rich color palettes, and immersive thematic elements.bergsidefaq-pageA Frequently Asked Questions (FAQ) page with collapsible accordion sections, search functionality, and category filtering. Use…nexu-iofastaifast.ai deep learning library. Use for practical deep learning.majiayu000fastifyFastify plugins, hooks, validation, serialization, and performance optimization patterns.a5c-aiwritesfatigue-analysisFatigue analysis for offshore structures including S-N curves, rainflow counting, Miner's rule, and DNV standardsmajiayu000feasibility-check技術的な実現可能性を検証し、PoCの計画を立てる。ユースケース記述後、DDDモデリングや本格実装の前に技術リスクを洗い出す場合に使用。「技術的に実現できるか確認したい」「PoCを計画したい」「技術リスクを洗い出したい」「不確実性を検証したい」などのリクエストで…majiayu000Feature Dependency MapperYou are the architecture analyst for Leavn's complex feature interconnections.majiayu000writesfeature-engineering-kitAuto-generate features with encodings, scaling, polynomial features, and interaction terms for ML pipelines.majiayu000Feature Engineering OptimizerOptimizes feature engineering pipelines and feature store configurationsa5c-aiwritesFeature FlaggingFeature flag configuration and rollout planning for controlled releasesa5c-aiwritesfeature-investigationUse when the user asks to investigate, understand, explore, or explain how a feature works, asks about existing logic, or wants…majiayu000writesfeature-investigationUse when the user asks to investigate, explore, understand, explain, or analyze how an existing feature or logic works. Triggers…majiayu000feature-investigation> [IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This…majiayu000feature-investigation> [IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This…majiayu000feature-planningBreak down feature requests into detailed, implementable plans with clear tasks. Use when user requests a new feature…mhattingpetefeature-store-builderVersion features for offline and online serving.majiayu000bio-rna-quantification-featurecounts-countingCount reads per gene from aligned BAM files using Subread featureCounts. Use when you have BAM files from STAR/HISAT2 and need…majiayu000featuring-nominationGenerates App Store featuring nomination pitches with all required fields, compelling narratives, and Apple editorial angles. Use…rshankraswritesCustomer Feedback AggregationAggregate and analyze customer feedback from multiple sources for product insightsa5c-aiwritesfeedback-digestAggregate and analyze customer feedback from [Delighted](https://composio.dev/toolkits/delighted)…majiayu000female_therapist_roleplayRoleplay as a kind, female therapist who corrects user grammar, avoids self-disclosure, and offers advice only when explicitly…majiayu000feynman-learning-coachGuide users through the Feynman Technique by asking them to explain a concept in simple language, diagnosing gaps, correcting…mingchen666fibonacci-optimizationOptimización evolutiva y paramétrica basada en Fibonacci y el Número Áureo (phi).majiayu000fii-dii-flow-trackerTrack and analyze FII/DII daily buy/sell flows in Indian markets. Use when user asks about institutional flows, FII…majiayu000file-analysis- Before architecture reviews to understand module boundaries and file organization.'majiayu000file-dialog-abstractionCross-platform file dialog implementation for open, save, and directory selectiona5c-aiwritesfile-guardPreToolUse protection blocking sensitive file access across 195+ patterns in 12 categories with bash pipeline analysis and…a5c-aiwritesfile-referenceProcess and analyze user-uploaded file references, extract key information, and provide application recommendations. Suitable for…majiayu000file-watcher-setupSet up cross-platform file system watching with debouncing and efficient change detectiona5c-aiwritescodebase-improvement-plannerAnalyze codebase and generate comprehensive improvement plans with prioritized recommendationsmajiayu000find-dead-codeFind dead code using parallel subagent analysis and optional CLI tools, treating code only referenced from tests as dead. Use…majiayu000find-dead-codeFind dead code using parallel subagent analysis and optional CLI tools, treating code only referenced from tests as dead. Use…majiayu000Find TODO and FIXME CommentsSearch markdown files, Nextflow scripts, and config files for TODO/FIXME comments, categorize by priority, and provide actionable…majiayu000fine-tuningFine-tuning pre-trained machine learning models for specific tasks using transfer learning techniques.majiayu000finer-gateFINER基準(Feasible, Interesting, Novel, Ethical, Relevant)で研究案を評価し、 Go/No-Go判定と改善提案を行う。RWD特有のバイアス・限界も評価項目に含む。majiayu000finishing-a-development-branchUse when implementation is complete, all tests pass, and you need to decide how to integrate the work.a5c-aifirecrawl-web-extraction当需要使用 Firecrawl 完成网页搜索、单页抓取、结构化提取、截图、URL 映射、整站 crawl 或 JavaScript 渲染页面内容提取时使用。适用于“搜索并抓网页内容”“提取某个 URL 的主体内容”“把网页字段按 schema…majiayu000first-principlesApply first-principles thinking to break down complex problems into fundamental truths and rebuild solutions from the ground up.…majiayu000first-principles-thinkingBreak down problems to fundamental truths. Use when conventional solutions fail, you need innovation, or want to challenge…majiayu000
← Prev68 / 447Next →
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