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
2,7852,832 · page 59 / 447
competitor-analysis直接競合・間接競合を分析し、差別化ポイントを明確にする。新規プロダクト企画時、市場参入前の調査、既存プロダクトのポジショニング見直し時に使用。「競合を分析したい」「差別化ポイントを見つけたい」「市場調査」「既存の解決策を調べたい」などのリクエストで起動。majiayu000competitor-analysisDeep competitive analysis + ongoing monitoring. Checks user research for competitor mentions, sales notes, existing analysis.…majiayu000competitor-analystAnalyzes competitors, competitive landscape, market positioning, and competitive advantagesmajiayu000competitor-intel-briefRun a structured competitive teardown in 20 minutes. Covers positioning, ICP, offer analysis, moat assessment, vulnerability…majiayu000competitor-trial-monitorMonitor competitor clinical trial progress and alert on market risksmajiayu000complex-reasoningMulti-step reasoning patterns and frameworks for systematic problem solving. Activate for Chain-of-Thought, Tree-of-Thought…majiayu000writescomplexity-analyzerAutomated Big-O complexity analysis of code and algorithms. Performs static analysis of loop structures, recursive call trees…a5c-aiwritescomplexity-gateEstimate issue complexity before implementation to prevent timeouts. Uses cheap estimation to save expensive implementation…majiayu000compliance-checkerCheck compliance with SOC 2, GDPR, HIPAA, and PCI-DSS standardsa5c-aiwritescomprehensive-system-analyzerDeep comprehensive system status analyzer that provides honest truth reporting about entire Pomo-Flow application health…majiayu000compressI-Lang compression engine. All internal planning uses I-Lang v3.0 syntax. Save 60%+ tokens. User never sees compressed output.majiayu000compressI-Lang compression engine. All internal planning uses I-Lang v4.0 syntax. Save 60%+ tokens. User never sees compressed output.majiayu000compression-progressSchmidhuber's compression progress as intrinsic curiosity reward for learning systems.majiayu000compute-precious-miner-gross-margin以公開金屬價格 + 礦業成本指標(AISC/All-in cost/現金成本)計算「黃金/白銀礦業毛利率代理值」,並判斷當前是否處於歷史高/低檔區間。majiayu000Computer VisionImplement computer vision tasks including image classification, object detection, segmentation, and pose estimation using PyTorch…majiayu000computer-vision-expertSOTA Computer Vision Expert. Specialized in YOLO, Segment Anything, Vision Language Models, and real-time spatial analysis. Use…majiayu000computer-vision-expertSOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time…majiayu000computer-vision-expertSOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time…majiayu000computer-vision-expertSOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time…majiayu000Computer Vision HelperAssist with image analysis, object detection, and visual AI tasksmajiayu000computer-visionBuild computer vision systems using CNNs and modern architectures. Use for image classification, object detection (YOLO, Faster…majiayu000concentrate-forces触发:当多个任务同时争夺时间、注意力、算力或预算,必须确定主攻方向并停止分散用力时调用;常见信号包括优先级过多、资源紧张、推进分散、需要决定先做什么。HughYauconcept-anatomist概念解剖师 - 通过8个维度深度解构任意概念,最终压缩为一个顿悟。当用户要求解释、剖析或深度理解某个概念、术语或想法时使用。生成 org-mode 格式的概念解剖报告。majiayu000concept-development發展研究概念並驗證創新性。觸發:concept、發展概念、研究概念、novelty、創新點、補充概念、幫我補充、擴展概念、加強、驗證失敗、novelty不夠、怎麼改。majiayu000concept-explainerELI5-style explanations with analogies and multiple examples. Explains concepts at different levels (ELI5, high school…mingchen666concept-forgeTransform nebulous ideas into sharp, testable frameworks through multi-perspective dialectical interrogation. Use when developing…majiayu000concise-key-pointsCompress answers to the highest practical information density with minimal wording while preserving essential meaning. Use when…twhsicondensed-analytic-stacksScholze-Clausen condensed mathematics bridge to sheaf neural networks via 6-functor formalismmajiayu000conductor-manageManage track lifecycle: archive, restore, delete, rename, and cleanupsickn33Confidence HonestyForce honest confidence assessment before claiming conclusions. Triggers on 'root cause identified', 'problem identified'…majiayu000confidence-scorerAssign confidence scores (0-100) to every claim in a response. Helps users understand which parts are verified facts and which…majiayu000config-schema-validatorGenerate Zod/JSON Schema configuration validators with defaults and error messages.a5c-aiwritesconfiguration-migratorMigrate configuration files between formats and versions with environment variable extractiona5c-aiwritesconsensus-buildingFrom multiple perspectives, build genuine consensus on what's truemajiayu000constraint-generalizationGeneralization and composition of constraints across navigatorsmajiayu000constraint-programmingWhen the user wants to solve complex scheduling, allocation, or combinatorial problems using constraint programming (CP). Also…majiayu000constructive-dissentStructured disagreement protocols to strengthen proposals through systematic challenge and alternative generation.majiayu000consultTechnical consultation without implementation. Use when the user invokes /consult or asks questions about the code or approach.majiayu000consult-oracleConsult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches. Use when stuck on a very hard…majiayu000consultUse when asking "code like [expert]", "what would [expert] say", "idiomatic", "best practice", "panel", "debate", or needing…majiayu000contact-finder-contactoutFind emails, phone numbers, and enrich profiles using ContactOut. LinkedIn enrichment, people search, company enrichment, and…gooseworks-aicontainerization-assistantAssist in containerizing applications with Dockerfile generation and optimizationa5c-aiwritescontent_post_with_cover生成可直接发布的内容主稿(默认公众号长文风格)并自动生成 1 张头图,最终以 write_file 落盘。limecloudcontext-buildingSystematic codebase investigation before addressing issues. Use when you need to build comprehensive understanding of a problem…majiayu000context-degradationLanguage models exhibit predictable degradation patterns as context length increases. Understanding these patterns is essential…majiayu000context-engineeringContext window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full 200k tokens.…a5c-aicontext7Search GitHub issues, pull requests, and discussions across any repository. Activates when researching external dependencies…majiayu000contextual-pattern-learningAdvanced contextual pattern recognition with project fingerprinting, semantic similarity analysis, and cross-domain pattern…majiayu000
← Prev59 / 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