Agent skills

Workflow & Productivity 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 29,139codex 4,760cursor 3,079copilot 978windsurf 55cline 34
CategoryWorkflow & Productivity 4,987AI & Agents 3,033Data & Analytics 2,347Code Review & Quality 1,377Backend & API 1,243Security 1,197Design & Presentation 1,129Documentation 967Content & Marketing 917Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 258Other 9,845
11,700 found
145192 · page 4 / 244
campaign-orchestratorOrchestrate full campaign lifecycle. Use when: planning, launching, managing, UTM setup, media plan, post-mortem.indranilbanerjeecherry-tool-guideCherry Studio first-party tool routing guide for general agents. Use this WHENEVER a task could be served by Cherry's built-in…CherryHQdoca-bf4-deploymentoperations (PLDM firmware burns, ISO reflashes, power cycles, BMC factory resets) that can brick firmware, corrupt boot media, or…NVIDIAdoca-compressUse this skill for hands-on DOCA Compress programming on a BlueField DPU, ConnectX NIC, or host with DOCA — enabling…NVIDIAdoca-dmaUse this skill when the user is doing hands-on DOCA DMA programming — bringing up a doca_dma context, configuring the single…NVIDIAdoca-gpiUse this skill for hands-on DOCA GPI programming — wiring a GPU-Packet-Initiator context so a CUDA kernel drives RDMA queues…NVIDIAdoca-rdmaUse this skill when the user is doing hands-on DOCA RDMA programming on a BlueField DPU, ConnectX NIC, or DOCA host — bringing up…NVIDIAinfluencer-creatorPlan influencer and creator partnerships. Use when: discovering creators, UGC campaigns, or FTC compliance.indranilbanerjeemulti-agent-meeting模拟多个AI智能体协作开会并进行决策讨论的场景。适用于需要从多个专业角度分析问题、进行辩论和达成共识的场景,如项目决策、技术方案评审、商业策略制定等。anbeimeopenrouter-routing-rulesDefine custom routing rules for OpenRouter requests based on user tier, task type, cost budget, and availability. Triggers…jeremylongshorewritesresults-reportThis skill should be used when the user asks to "write an experiment report", "summarize experimental results", "do experiment…brycewang-stanfordsetup-my-iqCreate, set up, or update the personal context portfolio: structured markdown files describing who you are, how you work, your…githubcrossframe-criticalUse only when the user explicitly names crossframe-critical for a Chinese structural critique dossier, article plan, or long-form…sickn33cursor-composer-workflowsMaster Cursor Composer for multi-file AI editing, scaffolding, and refactoring. Triggers on "cursor composer", "multi-file edit"…jeremylongshorewritesdigital-prPlan digital PR campaigns. Use when: pitching journalists, journalist-request responses, thought leadership, or E-E-A-T building.indranilbanerjeeet-unitybridgeUnityBridge workflow for AI operations in Unity Editor. Use when checking UnityBridge connectivity, Unity compile or PlayMode…FlameskyDexivelamindbUse when working with LaminDB, the open-source lineage-native lakehouse for biological datasets and models. Covers setup…K-Dense-AImatlab-model-robot-kinematicsUse whenever a MATLAB robot model (rigidBodyTree) is needed — whether for simulation, visualization, IK, motion planning…matlabnotion-knowledge-captureCapture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos…Haohao-endnotion-meeting-intelligencePrepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and…Haohao-endoma-pmProduct manager that decomposes requirements into actionable tasks with priorities and dependencies. Use for planning…first-flukephysicsnemo-discoverOfficial NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task…NVIDIAultracodeRun a lightweight Ultracode workflow for serious coding tasks: plan, split, delegate when useful and allowed by the host…PabloNAXwalkie-talkieUse when two or more agent sessions — same or different platforms (Claude Code, Codex, Gemini CLI, Copilot, Cursor) — work the…jeremylongshorewritesaibridge-development-workflowAIBridge/Unity 项目的标准开发工作流。Use when creating, modifying, fixing, refactoring, or validating C# code, Unity assets, prefabs, editor…FlameskyDexivediscover-interview-synthesisSynthesizes user research interviews into actionable insights, patterns, and recommendations. Use after conducting user…product-on-purposei4h-workflowOverview of `workflows/agentic/` (IsaacLab-Arena + GR00T/openpi). Use when the user asks what i4h workflow is, what's supported…NVIDIAindian-foreign-investment-approval-assessment-siddhi-kudalkarAssess whether Government of India approval is required for foreign investment in an Indian company under Foreign Exchange…lawve-ailamina-systemsReason about causal product systems and change over time. Use when mapping stocks, flows, delays, purposes, or interconnections…aryaniyapslangchain-deep-agentsBuild a LangGraph 1.0 Deep Agent \u2014 planner + subagents + virtual\ \ filesystem +\nreflection loop \u2014 without the…jeremylongshorewritessdd-riperSDD-RIPER workflow executor with phase gatingalibabanemo-mbridge-perf-moe-optimization-workflowSystematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper. Covers the Three…NVIDIAtao-analyze-gaps-vlm-bcqExtract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions. Use when the…NVIDIAwritesagent-signalBuild or extend LobeHub Agent Signal pipelines. Use for signal sources, signal/action types, policies, middleware, workflow…lobehubagentsop-session-state-hygieneDecision protocol for managing the context/session state of an AI coding tool: when to /clear, when to keep context, and how to…agentsopecommand-creatorThis skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash…softaworkscomputer-useDrive native desktop apps through DeepChat's built-in Computer Use tools. Use when the user asks to operate, inspect, automate…ThinkInAIXYZdeliver-prdCreates a comprehensive Product Requirements Document that aligns stakeholders on what to build, why, and how success will be…product-on-purposeet-asyncET async and EntityRef safety workflow. Use when adding, modifying, or reviewing async/await, ETTask, generic ETTask results…FlameskyDexiveflowchart-creatorCreate HTML flowcharts and process diagrams with decision trees, color-coded stages, arrows, and swimlanes. Use when users…mhattingpetefoundation-meeting-briefProduces a private strategic preparation document for the user before a meeting that matters. Captures stakes, stakeholder…product-on-purposefoundation-meeting-synthesizeCross-meeting archaeology skill. Consumes multiple meeting recaps (or raw notes) over a period and surfaces patterns invisible in…product-on-purposefriday-cliInteracts with a running Friday daemon via CLI and HTTP — lists/creates/modifies workspaces, triggers signals, watches sessions…friday-platformgolang-popular-librariesRecommends production-ready Golang libraries and frameworks. Apply when the user explicitly asks for library suggestions, wants…samberwritesi4h-catheter-navigationOverview of `workflows/catheter_navigation/` (fluorosim DRR, XPBD physics, vasculature digital twin). Use when the user asks what…NVIDIAi4h-catheter-navigation-setupVerify host/GPU requirements and PYTHONPATH for the catheter navigation workflow. Use when asked to set up, install, or bootstrap…NVIDIAi4h-workflow-setupVerify host requirements and run `workflows/agentic/setup.sh`. Use when asked to set up, install, or bootstrap the agentic…NVIDIAi4h-workflow-validateValidate, evaluate, or run i4h envs. Use for policy/checkpoint rollouts and scripted state-machine smoke runs.NVIDIA
← Prev4 / 244Next →
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