Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 273,245 indexed, measured the same four ways as everything else here.
Skill Codex
Analyze staged, unstaged, and untracked changes; group them into functionally coherent commit batches; and recommend staging order, commit boundaries, and related memory-docs references. Use when the working tree contains multiple kinds of changes and Codex needs to decide how many commits to make, which files belong…
Skill Claude CodeCodex
Reference for agents running inside a Tangerine task — API endpoints, env vars, and common workflows.
Skill Claude CodeCodex
The user's own running browser and their logins — paywalls, private dashboards, bot-checked sites, and every site they are already signed into. Reads any page as an accessibility tree and clicks, fills and types by element reference; screenshots, network, console, dialogs, device emulation. Chrome, Edge, Brave…
Skill Claude CodeCodex
Check system status, debug issues, view session stats, manage sessions and cron jobs. Use when something isn't working, when asked about system internals, or when you need to check your own state.
Skill Claude CodeCodex
Use when finishing a feature, fixing a bug, before committing React code, or when the user types /doctor, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.
Skill Claude CodeCodex
A tool that turns a product owner's request into a YAML task file for a software manager. YAML is a human-readable format for structured settings and instructions.
Skill Claude CodeCodex
Spawn and manage ephemeral OpenClaw Docker agents ("larvae"). Use when you need to run isolated coding tasks, spin up disposable AI workers, orchestrate parallel agents, or delegate work to containerized OpenClaw instances. Triggers on requests like "spawn a larva", "spin up a container to do X", "run that in a…
Skill Claude CodeCodex
Skill "skills" from david-spies/ai-agent-builder, covering skillauthoring.md — complete guide to writing agent skills, ai-agent builder · documentation, the skill.md standard, anatomy of a skill.md file and full skill.md template.
Skill Claude CodeCodex
Create custom AI subagents with proper plugin structure, persona generation, and companion routing skills.
johnmwangimegwe/kenya-climate-agent
Skill Claude CodeCodex
Assess and rank climate risk (flood, drought, rainfall) for Kenyan counties from a natural-language question, grounded in Earth Engine data, population exposure, and retrieved Kenyan documents.
daralthus/claude-code-playground
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
a secure dotenv–from the creator of dotenv. Runs locally from the @dotenvx/dotenvx npm package.
Skill Claude CodeCodex
Turn your agent into a revenue-generating Talos — sell services, trade with other agents, earn USDC.
Skill Claude CodeCodex
Tạo file PowerPoint (.pptx) chuyên nghiệp từ giáo trình Markdown cho khóa học AI Agent. Áp dụng hệ thiết kế "Sage & Stone" (Georgia/Verdana, palette kem-xanh rêu-cam san hô). Hỗ trợ đầy đủ tiếng Việt có dấu, 5 kiểu layout đa dạng, pipeline QA thị giác tự động. Kích hoạt khi user yêu cầu "tạo slide", "xuất PPTX", "làm…
thu-nmrc/ZeeLin-OpenClaw-Skill
Skill Codex
A publishing workflow for adding reports to the ZeeLin reports website, including copying assets, updating the site's report list, checking the build, and preparing a pull request.
Skill Claude CodeCodex
AI image generation with OpenAI, Google, OpenRouter, DashScope, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable…
Skill Claude CodeCodex
Orchestrator of a loop-engineering system. Runs the full loop – discover work, delegate to maker and checker, and act on the result.
AyushVerma7861/web3-ugc-brief-writer
Skill Claude CodeCodex
Use this skill when writing UGC video briefs, scripts, or campaign briefs for any Web3 project. Activates when asked to create a video brief, write a UGC script, plan a short-form video, structure a creator campaign, or produce a content brief for a crypto or blockchain product. Trigger phrases include "write me a…
AyushVerma7861/campaign-analyser
Skill Claude CodeCodex
Campaign performance analysis for ProductClank agents. Use when asked to analyse campaign results, calculate ROI, compare campaigns, find what worked, identify patterns, or plan the next campaign strategy. Works in API mode with a ProductClank API key or in manual mode when the user pastes campaign data directly.
akikisai/copilot-custom-config-template
Skill Claude CodeCodex
Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering. Also activated by skill name: "design-taste-frontend".
chatgpt-yunju/wecom-ai-customer-service
Skill Claude CodeCodex
This document describes how to use the wecom-ai-customer-service as an OpenClaw skill.
gventuri/ai-production-workshop
Skill Claude CodeCodex
Explore and analyze a dataset (CSV/JSON) with pandas, then summarize findings.
Skill Claude CodeCodex
A Chinese-language assistant persona based on a Java backend developer who shares articles and gives practical advice about AI agents and workflows.
cashmere-prod/cashmere-agent-sdk
Skill Claude CodeCodex
Use this skill when the user asks about Cashmere cross-chain USDC transfers, CCTP contract calls, bridging between EVM / Solana / Aptos / Sui, or building transactions against the Cashmere wrapper contracts.
code2rich/agentwaker-xiaohongshu-operator
Skill Codex
Fulfill a pending Xiaohongshu visual request through Codex's built-in ImageGen entitlement without an OpenAI API key or separate image API integration. Use when Kimi or another text agent has written a valid visual-request.json into the current Xiaohongshu Workdir v1 run and Codex must generate conceptual raster…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: