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
7,1057,152 · page 149 / 203
hivemind-graphQuery the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/. Use when the user…activeloopaiwriteshivemind-memoryGlobal team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling…activeloopaiwritesholographic-uiWeb and App implementation guide for Holographic UI. Trigger when user wants light-based appearance, projected interfaces, and…sickn33homelab-network-readinessReadiness checklist for homelab VLAN segmentation, local DNS filtering, and WireGuard-style remote access before changing router…mturachomelab-network-setupPractical home and homelab network planning for gateways, switches, access points, IP ranges, DHCP reservations, DNS, cabling…mturachomelab-pihole-dnsPi-hole installation, blocklist management, DNS-over-HTTPS setup, DHCP integration, local DNS records, and troubleshooting broken…mturachomelab-vlan-segmentationSegmenting home networks into VLANs for IoT, guest, trusted, and server traffic using UniFi, pfSense/OPNsense, and MikroTik —…mturachomelab-wireguard-vpnWireGuard VPN server setup, peer configuration, key generation, split tunneling vs full tunnel routing, and remote access to a…mturachomologation-docsType approval documentation and certification managementa5c-aiwriteshoneybadger-automationAutomate Honeybadger tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhoneyhive-automationAutomate Honeyhive tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhonoBuild ultra-fast web APIs and full-stack apps with Hono — runs on Cloudflare Workers, Deno, Bun, Node.js, and any…sickn33hookdeck-automationAutomate Hookdeck tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhookify-rulesThis skill should be used when the user asks to create a hookify rule, write a hook rule, configure hookify, add a hookify rule…mturacHooks AutomationAutomated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration.…ruvnethorizon-trackTrack long-horizon objectives across multiple sessions with milestone checkpoints, progress persistence, and drift detectionruvnethosted-agentsBuild background agents in sandboxed environments. Use for hosted coding agents, sandboxed VMs, Modal sandboxes, and remote…sickn33hosted-agents-v2-pyBuild hosted agents using Azure AI Projects SDK with ImageBasedHostedAgentDefinition. Use when creating container-based agents in…sickn33hotel-core【已废弃并合并】此技能已迁移至新版酒店查询、预订技能rollinggo-hotel-booking。如果是下载过程,请直接选择 rollinggo-hotel-booking。触发此技能后大模型会引导用户迁移到新版。RollingGo-AIhotspotsystem-automationAutomate Hotspotsystem tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhpo-phenotype-matcherHuman Phenotype Ontology skill for phenotype-driven gene prioritizationa5c-aiwriteshr-investigationSupport workplace investigation processes with documentation and methodology guidancea5c-aiwriteshr-proProfessional, ethical HR partner for hiring, onboarding/offboarding, PTO and leave, performance, compliant policies, and employee…sickn33hreflang-checkAudit hreflang tags. Use when: checking missing tags, incorrect language codes, or x-default configuration.indranilbanerjeehtml-injection-testingIdentify and exploit HTML injection vulnerabilities that allow attackers to inject malicious HTML content into web applications.…sickn33html-to-image-automationAutomate Html To Image tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhubspot-automationAutomate HubSpot CRM operations (contacts, companies, deals, tickets, properties) via Rube MCP using Composio integration.sickn33hubspot-connectorHubSpot CRM and Marketing Hub integration for sales and marketing alignmenta5c-aiwriteshubspot-integrationExpert patterns for HubSpot CRM integration including OAuth authentication, CRM objects, associations, batch operations…sickn33huge-planUse huge-plan for open-ended high-risk repo efforts needing websearch during brainstorming and refinement until convergence…Optim-Agenthugging-face-cliHugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and…sickn33hugging-face-datasetsCreate and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row…sickn33hugging-face-evaluationAdd and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing…sickn33hugging-face-papersLook up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked…sickn33hugging-face-tool-builderYour purpose is now is to create reusable command line scripts and utilities for using the Hugging Face API, allowing chaining…sickn33huggingface-bestUse when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants…sickn33humanitix-automationAutomate Humanitix tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhumanize-chineseDetect and rewrite AI-like Chinese text with a practical workflow for scoring, humanization, academic AIGC reduction, and style…sickn33humanize-it对指定文档进行去 AI 味的改写。自动选择最合适的人性化策略(humanizer-zh / humanize-chinese / technical-writing), 迭代改写直到效果达标或迭代 42 次为止。适用于中文文本的去 AI…smallnestwriteshumanloop-automationAutomate Humanloop tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQhumann-functional-profilerHUMAnN functional profiling skill for metagenomic pathway analysisa5c-aiwritesHunter AutomationAutomate Hunter.io email intelligence -- search domains for email addresses, find specific contacts, verify email deliverability…ComposioHQhvac-designSkill for HVAC system design and analysis per ASHRAE standards including load calculations, equipment selection, and energy…a5c-aiwriteshybrid-cloud-architectExpert hybrid cloud architect specializing in complex multi-cloud solutions across AWS/Azure/GCP and private clouds…sickn33hybrid-cloud-networkingConfigure secure, high-performance connectivity between on-premises and cloud environments using VPN, Direct Connect, and…sickn33hydrationImplement and optimize server-side rendering hydration strategies — partial hydration, islands architecture, and hydration…a5c-aiwriteshydraulic-analysis-engineHydraulic analysis skill for open channel flow, culverts, and pipe networksa5c-aiwriteshydrologic-modeling-engineHydrologic modeling skill for rainfall-runoff analysis, flood frequency, and watershed analysisa5c-aiwrites
← Prev149 / 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