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
3,9373,984 · page 83 / 104
llm-evaluationMaster comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.sickn33llm-from-scratch-guideBuild a ChatGPT-like LLM from scratch using PyTorch step by stepbrycewang-stanfordllm-runtime-architectureUse when designing how one canonical agent core runs across Codex, Claude Code, Gemini CLI, Cursor, and AGENTS.md-compatible…agentlas-aillm-scientific-discovery-guideSurvey of LLM agents for biomedical scientific discoverybrycewang-stanfordlmnt-automationAutomate Lmnt tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQln-31-performance-optimizerOptimizes a measured latency, throughput, memory, CPU, or I/O problem through profiling and keep-or-discard experiments. Use for…levnikolaevichload-optimization-calculatorAI-powered load building and consolidation skill to maximize trailer utilization and reduce transportation costsa5c-aiwritesloading-openmed-modelsLoad OpenMed clinical/biomedical NER models from the Hugging Face Hub or a local path and reuse them efficiently across calls.…maziyarpanahilocal-deep-research-guideDeep research agent searching 10+ sources with local or cloud LLMsbrycewang-stanfordlocal-llm-expertMaster local LLM inference, model selection, VRAM optimization, and local deployment using Ollama, llama.cpp, vLLM, and LM…sickn33Local PDF RAG Pipeline with LangChain and OllamaGenerates a Python script using LangChain to load local PDFs via DirectoryLoader, create embeddings with Ollama, store in Chroma…ECNU-ICALKlodgify-automationAutomate Lodgify tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlogistics-kpi-trackerComprehensive logistics performance measurement skill with KPI tracking, benchmarking, and improvement recommendationsa5c-aiwriteslogo-dev-automationAutomate Logo Dev tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQloomio-automationAutomate Loomio tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQloop-workerRun Ruflo background workers using Claude Code native /loop schedulingruvnetloyverse-automationAutomate Loyverse tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQlv-assignsInspect LiveView socket assigns for memory bloat — missing temporary_assigns, unused assigns, unbounded lists needing streams…oliver-kriskalycheememForceful operating rules for using LycheeMem as the primary structured long-term memory path inside OpenClaw.LycheeMemmacs3-peak-callingPoisson-model peak caller for ChIP-seq/ATAC-seq BAMs. MACS3 callpeak finds enriched regions (TF sites or histone marks) vs…BioTender-maxmadgraph-amplitude-calculatorMadGraph matrix element calculation skill for BSM physics, cross-section computation, and event generationa5c-aiwritesmageck-crispr-analyzerMAGeCK CRISPR screen analysis skill for gene essentiality scoringa5c-aiwritesmagnetic-automationAutomate Magnetic tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmailbluster-automationAutomate Mailbluster tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmailboxlayer-automationAutomate Mailboxlayer tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmailcheck-automationAutomate Mailcheck tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmailcoach-automationAutomate Mailcoach tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmailersend-automationAutomate Mailersend tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmails-so-automationAutomate Mails So tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmailsoftly-automationAutomate Mailsoftly tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmaintain-cross-platformUse when preparing releases, validating cross-platform compatibility, or updating installation infrastructure. Meta-skill for…agent-shmaintainx-automationAutomate Maintainx tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmaintenance-schedulerMaintenance planning and scheduling skill with TPM integration and predictive maintenance supporta5c-aiwritesmake-automationAutomate Make (Integromat) tasks via Rube MCP (Composio): operations, enums, language and timezone lookups. Always search tools…davepoonmake-automationAutomate Make (Integromat) tasks via Rube MCP (Composio): operations, enums, language and timezone lookups. Always search tools…sickn33make-scenario-creatorCreate make scenario creator operations. Auto-activating skill for Business Automation. Triggers on: make scenario creator, make…jeremylongshorewritesmanage-channelsWire channels to agent groups, manage isolation levels, add new channel groups. Use after adding a channel, during setup, or…nanocoaimanage-mountsConfigure which host directories agent containers can access. View, add, or remove mount allowlist entries. Triggers on "mounts"…nanocoaimanage-skillsSearches the SkillsMP registry, installs skills locally or globally, creates custom skills with SKILL.md frontmatter, and manages…open-gitagentmanaged-agentRun an Anthropic Claude Managed Agent — a cloud agent harness (container + filesystem + tools), the cloud counterpart of the…ruvnetwritesmany-chat-automationAutomate ManyChat tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmany_chat-automationAutomate ManyChat tasks via Rube MCP (Composio): chatbot flows, subscribers, broadcasts, and messenger automation. Always search…ComposioHQmapbox-automationAutomate Mapbox tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmapulus-automationAutomate Mapulus tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmaterial-model-libraryBiomaterial constitutive model library skill providing validated material properties for biological tissues and implant materialsa5c-aiwritesmaterial-testingSkill for planning and specifying mechanical material tests per ASTM standardsa5c-aiwritesmath-model-selectorRoutes problems to appropriate mathematical frameworks using expert heuristicsparcadeiMATLAB ARIMA Model Selection and ForecastingGenerates MATLAB code to perform time series forecasting by testing multiple ARIMA models, selecting the best one based on AIC…ECNU-ICALK
← Prev83 / 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