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
1,9211,968 · page 41 / 104
mutating-idea-genomesUse when mutating idea genomes is required during creativity work, especially when the result must be traceable, independently…casioreview20-glitchn8n-syntax-ai-nodesUse when building AI or LLM workflows in n8n v1.x (v1.19.4+). Prevents incorrect sub-node wiring by mismatching…majiayu000gemini-image-generatorGenerate images using Google Gemini NanoBanana via browser automation. Use this skill for general-purpose AI image generation…majiayu000Nav2 Navigation SkillSpecialized skill for ROS2 Nav2 navigation stack configuration and behavior treesa5c-aiwritesnavmeshNavigation mesh generation and pathfinding skill for game AI. Enables creation and configuration of navigation meshes…a5c-aiwritesnetwork-packet-labUse this skill whenever the user asks about Wireshark, tcpdump, packet capture, pcap analysis, HTTP/DNS/TCP/DHCP/TLS capture…mingchen666network-simulationSkill for network condition simulation, emulation, and chaos engineeringa5c-aiwritesnetwork-testingComprehensive network testing, benchmarking, and performance validation skilla5c-aiwritesneuro-gashThis skill governs the intentional corruption and reconstruction of the agent’s internal reasoning. By "injecting" specific…majiayu000never-guessBehavioral principle ensuring Claude never guesses when uncertain. Use when Claude's response involves facts it cannot verify…majiayu000new-agent-creationWhen to Use: Creating new AI agents for Unite-Hubmajiayu000news-agentReal-time news analyst. Monitors emergency news, breaking developments, and general news articles to assess immediate market…majiayu000news-intelligence-agentBatch news analyzer for /news page. Processes multiple news articles simultaneously, extracting sentiment, keywords, themes, and…majiayu000newsvendor-problemWhen the user wants to solve single-period inventory problems, optimize stocking levels for perishable goods, or make one-time…majiayu000nexus-graph-visualizerUse this skill when mapping skill ecosystem coherence, analyzing autopoietic loops, visualizing tier interactions, or assessing…majiayu000nexusNexus conversational PI agent architecture, development, and deployment. Use when working on the Nexus orchestrator, gateway, or…majiayu000nixtla-event-impact-modelerQuantifies the impact of exogenous events on contract prices using TimeGPT and CausalImpact. Triggers on "event impact analysis"…majiayu000writesnixtla-timegpt-finetune-labConfigure TimeGPT fine-tuning on custom datasets with Nixtla SDK. Use when training domain-specific forecast models. Trigger with…majiayu000writesnlp-engineerExpert in Natural Language Processing, designing systems for text classification, NER, translation, and LLM integration using…majiayu000nnsight-basicsCore nnsight concepts for neural network interpretability. Use when setting up models, tracing activations, saving values, or…majiayu000noise-modelerQuantum noise modeling skill for simulation and hardware characterizationmajiayu000writesnomi-mesh10-Nomi group chat neural net. Persistent memory as weights, group chat as forward pass, KAM-stabilized phi-frequencies prevent…majiayu000upgradeUpgrade the NotFair plugin to the latest version. Updates the marketplace repo, installs the new version to the plugin cache, and…nowork-studiowritesnse-vcp-screenerScreen Nifty 500 stocks for Mark Minervini's Volatility Contraction Pattern (VCP) — identifying Stage 2 uptrends with tightening…majiayu000numpy-memoryNumPy memory management revolves around the concept of "strides." Strides define the number of bytes to skip in a flat 1D buffer…majiayu000nvidia-nemoNVIDIA NeMo framework for building and training conversational AI models. Use for NeMo Retriever models, RAG (Retrieval-Augmented…majiayu000nw-buddy-command-catalogAll /nw-* commands — what they do, when to use them, which agent they invoke. For the buddy agent to help users pick the right…majiayu000nw-buddy-project-readingHow the nWave buddy agent reads a project to answer questions — detection, order of inspection, and citation discipline.majiayu000nw-buddy-wave-knowledgeWave methodology knowledge for the buddy agent — what each wave does, its inputs and outputs, and how to route questions.majiayu000nw-entity-resolutionCross-platform identity matching techniques for resolving entities across multiple OSINT sources, with confidence scoring…majiayu000Object Detection/Segmentation SkillDeep learning based object detection and segmentation for robotics applicationsa5c-aiwritesObject Detection/Segmentation SkillDeep learning based object detection and segmentation for robotics applicationsmajiayu000writesobservability-pattern-detectorAutomated pattern recognition in Claude Code telemetry. Use when detecting failures, slowness, anomalies, trends, inefficiencies…majiayu000observalCore Observal CLI operations: pull agents into your harness, scan installed components, diagnose and patch harness configs…Observalobserving-automation-runsUse when observing automation runs is required during automation product work, especially when the result must be traceable…casioreview20-glitchoc-create-agentGuides through creating a new OpenCode-compatible agent with interactive interview, permission configuration, and validation. Use…majiayu000writesoc-update-agentUpdates an existing OpenCode agent to match current platform best practices, fixes deprecated patterns, and validates the result.…majiayu000writesocclusion-cullingOcclusion culling skill for visibility determination and GPU queries.a5c-aiwritesoctave-mythologyFunctional mythological compression for OCTAVE documents. Semantic shorthand for LLM audiences, not prose decorationmajiayu000writesollama-ragBuild RAG systems with Ollama local + cloud models. Latest cloud models include DeepSeek-V3.2 (GPT-5 level), Qwen3-Coder-480B (1M…majiayu000ols-regressionEconometrics skill for OLS regression and linear models. Activates when the user asks about: "run OLS", "linear regression"…brycewang-stanfordoma-recapAnalyze conversation histories from multiple AI tools (Grok, Claude, Codex, Gemini, Qwen, Cursor, Antigravity) and generate…first-flukeonboardUse at session start to detect available skills, load active context, and enforce skill usage discipline for the current session.majiayu000onnx-converterConvert onnx converter operations. Auto-activating skill for ML Deployment. Triggers on: onnx converter, onnx converter Part of…majiayu000writesonnx-converterOnnx Converter - Auto-activating skill for ML Deployment. Triggers on: onnx converter, onnx converter Part of the ML Deployment…majiayu000writesOpenAI AgentKit ExpertBuild production-ready multi-agent systems using OpenAI AgentKit and Agents SDK with best practices for agent orchestration…majiayu000OpenAI AgentKit ExpertBuild production-ready multi-agent systems using OpenAI AgentKit and Agents SDK with best practices for agent orchestration…majiayu000openai-agentsBuild AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas…majiayu000
← Prev41 / 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