Agent skills

AI & Agents 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
4,965 found
3,8893,936 · page 82 / 104
latex-document-compilerSkill for compiling and managing LaTeX documentsa5c-aiwriteslatex-paper-conversionThis skill should be used when the user asks to convert an academic paper in LaTeX from one format (e.g., Springer, IPOL) to…sickn33latex-tableLaTeX回归表格生成Skill。辅助生成符合AER/QJE等顶刊格式的三线表,包括标准误聚类标注、显著性星标、固定效应标注。触发词:LaTeX表格/回归表/三线表/table制作/latex tablebrycewang-stanfordLaunchDarkly AutomationAutomate LaunchDarkly feature flag management -- list projects and environments, create and delete trigger workflows, and track…ComposioHQlaunch_darkly-automationAutomate LaunchDarkly tasks via Rube MCP (Composio): feature flags, environments, segments, and rollout management. Always search…ComposioHQlaunch-day-conductorUse when the user asks to "run my launch day", "build a launch day runbook / war room", or "decide CONTINUE or ROLLBACK after the…aaron-he-zhulayered-recallProgressive memory recall with 4 scope layers AND 3 depth layers. Scope: identity > project > room > deep. Depth: IDs only >…vibeevallbo-model-builderLeveraged Buyout model construction skill for private equity transaction analysisa5c-aiwriteslca-analyzerLife Cycle Assessment skill for environmental impact evaluation and sustainability analysisa5c-aiwritesleadfeeder-automationAutomate Leadfeeder tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQleadoku-automationAutomate Leadoku tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlean-theorem-proving-guideLLM agent for formal theorem proving in Lean 4brycewang-stanfordlearnHizlica kural/ogrenim kaydet. CLAUDE.md'ye ve memory'ye yazar. Kullanim: /learn <kural>vibeevallearning-rate-schedulerManage learning rate scheduler operations. Auto-activating skill for ML Training. Triggers on: learning rate scheduler, learning…jeremylongshorewriteslearning-scienceSpaced repetition, active recall, interleaving, dual coding, metacognition, and study techniquescosmicstack-labslease-accounting-calculatorASC 842/IFRS 16 lease accounting skill for right-of-use asset and liability calculationsa5c-aiwriteslegal-agent-skills-guideAgent skills collection for legal research and automationbrycewang-stanfordleiga-automationAutomate Leiga tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQLemon Squeezy AutomationAutomate Lemon Squeezy store management -- products, orders, subscriptions, customers, discounts, and checkout tracking -- using…ComposioHQlemon_squeezy-automationAutomate Lemon Squeezy tasks via Rube MCP (Composio): products, orders, subscriptions, checkouts, and digital sales. Always…ComposioHQlessonspace-automationAutomate Lessonspace tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlever-sandbox-automationAutomate Lever Sandbox tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQleverly-automationAutomate Leverly tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlexoffice-automationAutomate Lexoffice tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQligand-exchange-protocol-managerSurface chemistry skill for managing ligand exchange reactions, bioconjugation protocols, and functional group quantificationa5c-aiwriteslinear-automationAutomate Linear tasks via Rube MCP (Composio): issues, projects, cycles, teams, labels. Always search tools first for current…davepoonlinear-automationAutomate Linear tasks via Rube MCP (Composio): issues, projects, cycles, teams, labels. Always search tools first for current…sickn33linear-issue-generatorGenerate linear issue generator operations. Auto-activating skill for Enterprise Workflows. Triggers on: linear issue generator…jeremylongshorewriteslinear-program-modelerMathematical programming skill for formulating and solving linear programming models for resource allocation, production…a5c-aiwriteslinear-programming-solverLinear programming skill for resource allocation, scheduling, and optimization problemsa5c-aiwriteslinguapop-automationAutomate Linguapop tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlinkedin-automationAutomate LinkedIn tasks via Rube MCP (Composio): create posts, manage profile, company info, comments, and image uploads. Always…davepoonlinkedin-automationAutomate LinkedIn tasks via Rube MCP (Composio): create posts, manage profile, company info, comments, and image uploads. Always…sickn33linkhut-automationAutomate Linkhut tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlinkup-automationAutomate Linkup tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlinux_high_concurrency_sysctl_tuningGenerates a comprehensive list of Linux sysctl parameters for maintaining high simultaneous connections, covering connection…ECNU-ICALKLinux TCP Memory Parameter CalculationCalculates and configures Linux kernel TCP memory parameters (tcp_mem, tcp_rmem, tcp_wmem) based on specific connection counts…ECNU-ICALKLinux TCP Memory Parameter CalculatorCalculates the net.ipv4.tcp_mem kernel parameter values based on the number of simultaneous TCP connections and minimum buffer…ECNU-ICALKgsd:list-phase-assumptionsSurface Claude's assumptions about a phase approach before planningdavepoonwriteslist-subsList all active skill-bus subscriptions across global and project scopes, showing merge status, insert-level and…composio-communitylistclean-automationAutomate Listclean tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlistennotes-automationAutomate Listennotes tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlivesession-automationAutomate Livesession tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQllm-app-patternsProduction-ready patterns for building LLM applications, inspired by [Dify](https://github.com/langgenius/dify) and industry best…sickn33llm-application-dev-langchain-agentYou are an expert LangChain agent developer specializing in production-grade AI systems using LangChain 0.1+ and LangGraph.sickn33llm-application-devBuilding applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered…MoizIbnYousafllm-configConfigure RuVLLM local inference with model selection, MicroLoRA fine-tuning, and SONA adaptationruvnetwritesllm-evaluation-guideEvaluate and benchmark large language models for research applicationsbrycewang-stanford
← Prev82 / 104Next →
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