Agent skills

Skills for codex

9,699 skills that declare support for codex. The SKILL.md format is shared, so most of these work in the other agents too — the declaration only says where the author tested it.

Toolclaude-code 62,644codex 9,699cursor 6,852copilot 2,269windsurf 126cline 82
CategoryWorkflow & Productivity 11,684AI & Agents 4,965Data & Analytics 4,693Code Review & Quality 2,936Security 2,762Backend & API 2,480Design & Presentation 2,329Documentation 2,157Content & Marketing 2,001Testing & QA 1,723DevOps & Cloud 1,266Databases 1,124Frontend 1,015Business & Finance 706Media & Video 507Other 21,420
9,699 found
7,8257,872 · page 164 / 203
n8n-multi-instanceSelect, verify, and safely switch n8n MCP instances across production, staging, teams, or clients, especially before credential…sickn33n8n-validation-expertExpert guide for interpreting and fixing n8n validation errors.sickn33n8n-workflow-patternsProven architectural patterns for building n8n workflows.sickn33nango-automationAutomate Nango tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQnano-nets-automationAutomate Nano Nets tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQnanobanana-pptAI-powered PPT generation with document analysis and styled images via the NanoBanana stack. Combines image generation with…nexu-ionanobanana-ppt-skillsAI-powered PPT generation with document analysis and styled imagessickn33nanocatalyst-performance-analyzerNanocatalysis skill for evaluating catalytic activity, selectivity, and stability of nanomaterial catalystsa5c-aiwritesnanoclaw-replOperate and extend NanoClaw v2, ecc's zero-dependency session-aware REPL built on codex -p.mturacnanohub-simulator-interfaceNanoHUB tool interface skill for accessing educational and research nanoscience simulationsa5c-aiwritesnanoimprint-process-controllerNanoimprint Lithography skill for high-throughput nanopatterning with template management and demolding optimizationa5c-aiwritesnanomaterial-lims-managerLaboratory Information Management System skill for nanomaterial sample tracking and data managementa5c-aiwritesnanomaterial-sds-generatorSafety documentation skill for generating Safety Data Sheets for nanomaterialsa5c-aiwritesnanoparticle-synthesis-optimizerSynthesis parameter optimization skill for metal, semiconductor, and oxide nanoparticle production with automated protocol…a5c-aiwritesnanosensor-calibration-managerNanosensor characterization skill for calibration, sensitivity analysis, and selectivity validationa5c-aiwritesnarrative-landscapeMap the competitive narrative landscape. Use when: analyzing positioning territories, gaps, competitor claims, differentiation.indranilbanerjeenarrative-trackerTrack AI engine brand narratives. Use when: detecting narrative drift, misrepresentation, or competitor narrative gains over time.indranilbanerjeenasa-automationAutomate Nasa tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQnasdaq-automationAutomate Nasdaq tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQnbodykit-cosmology-analyzernbodykit large-scale structure analysis skill for N-body simulations and galaxy surveysa5c-aiwritesncscale-automationAutomate Ncscale tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQneed-explorerClarify intent, scope, constraints, and success criteria before artifact creation. Invoke when the request is fuzzy, the user is…MageByte-Zeroneedle-automationAutomate Needle tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQnemo-guardrailsNVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking…Orchestra-Researchneo-brutalismWeb and App implementation guide for Neo-Brutalism. Trigger when user wants thick borders, hard shadows, bright colors, and a…sickn33neon-ai-gatewayOne API and one credential for frontier and open-source LLMs, built into your Neon branch and powered by Databricks. Use when a…sickn33Neon AutomationAutomate Neon serverless Postgres operations -- manage projects, branches, databases, roles, and connection URIs via the Composio…ComposioHQneon-object-storageS3-compatible object storage that branches with your Neon project, so files and the database stay in sync across every branch.…sickn33neon-postgres-branchesChoose and create the right Neon branch type for testing and development. Use when users ask about Neon branching, migration…sickn33neon-postgres-egress-optimizerDiagnose and fix excessive Postgres egress (network data transfer) in a codebase. Use when a user mentions high database bills…sickn33neon-postgresGuides and best practices for working with Neon Serverless Postgres. Covers setup, connection methods, branching, autoscaling…sickn33nerdzao-elite-gemini-highModo Elite Coder + UX Pixel-Perfect otimizado especificamente para Gemini 3.1 Pro High. Workflow completo com foco em qualidade…sickn33nerdzao-eliteSenior Elite Software Engineer (15+) and Senior Product Designer. Full workflow with planning, architecture, TDD, clean code, and…sickn33nested-subagentsSpawn nested sub-agents (agents that spawn sub-agents, up to depth=5) via Claude Code's native Task tool — for context-managed…ruvnetwritesnestjs-expertYou are an expert in Nest.js with deep knowledge of enterprise-grade Node.js application architecture, dependency injection…sickn33nestjs-patternsNestJS architecture patterns for modules, controllers, providers, DTO validation, guards, interceptors, config, and…mturacnetmiko-ssh-automationSafe Python Netmiko patterns for read-only collection, bounded batch SSH, TextFSM parsing, guarded config changes, timeouts, and…mturacNetSuite AutomationNetSuite Automation: manage customers, sales orders, invoices, inventory, and records via Oracle NetSuite ERP with SuiteQL queriesComposioHQnetwork-101Configure and test common network services (HTTP, HTTPS, SNMP, SMB) for penetration testing lab environments. Enable hands-on…sickn33network-analysisMap and analyze social network structures using centrality measures, community detection, and visualization tools like Gephi or…a5c-aiwritesnetwork-bgp-diagnosticsDiagnostics-only BGP troubleshooting patterns for neighbor state, route exchange, prefix policy, AS path inspection, and safe…mturacnetwork-buffersOptimize network buffer management — socket buffer tuning, zero-copy I/O, DMA buffers, and kernel bypass techniques for…a5c-aiwritesnetwork-condition-testingTest mobile app behavior under various network conditions — 3G, 4G, WiFi, packet loss, high latency, and network switching.a5c-aiwritesnetwork-config-validationPre-deployment checks for router and switch configuration, including dangerous commands, duplicate addresses, subnet overlaps…mturacnetwork-engineerExpert network engineer specializing in modern cloud networking, security architectures, and performance optimization.sickn33network-interface-healthDiagnose interface errors, drops, CRCs, duplex mismatches, flapping, speed negotiation issues, and counter trends on routers…mturacnetwork-matcherMatches portfolio company needs with investor network resourcesa5c-aiwritesnetwork-optimization-modelerStrategic distribution network modeling skill to optimize facility locations, capacity allocation, and inventory positioninga5c-aiwrites
← Prev164 / 203Next →
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