Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 267,801 indexed, measured the same four ways as everything else here.
abanoubkhaliil/Ak-Elementor-Studio
Skill Claude CodeCodex
AK Elementor Studio — built by Abanoub Khalil (akstudio.me). Converts ANY input — HTML/CSS/JS code, screenshots, images (PNG, JPG, WebP), PDFs, Figma exports, design mockups, wireframes, or any visual file — into fully structured Elementor page JSON templates importable into WordPress. Activate this skill whenever the…
HHHHHejia/awesome-legal-aiagent-skills
Skill Claude CodeCodex
<Describe the procedure the agent should run to identify the single in-scope subject before drafting — e.g., "walk every file under documentstext/, group by counterparty / signing date / advisor of record, and identify the single cluster whose deal-summary / engagement letter / board minutes matches the task…
slash9494/ai-config-sync-manager
Skill Claude CodeCodex
Paraphrase host-strict-vocab tokens (Claude-only in codex files, Codex-only in claude files) and register per-line overrides through the bundled open-source CLI so the result is masked from future status diffs.
Skill Claude CodeCodex
Create a new reusable skill package from a high-level specification. Use this when you need a capability that does not exist in the skill bank. This tool generates the SKILL.md interface file, optional scripts, tests, and resources, then runs the tests and registers the skill only if they pass.
MCP server Claude CodeCodexCursor +2
MCP server that connects AI assistants to your YNAB budget. Runs locally from the mcp-ynab Python package.
sandraschi/windows-computer-use-mcp
Skill Claude CodeCodex
How to use windows-computer-use-mcp effectively — tool selection, focus rules, safety, and mission design.
MCP server Claude CodeCodexCursor +2
MCP server to manage your Tampermonkey scripts. Runs locally from the tampermonkey-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server "kokkai-giji" as configured in seiichi3141/kokkaigijimcp. Runs in Docker (seiichi3141/kokkai-giji-mcp:latest).
Skill Claude CodeCodex
A cross-platform computer automation tool for Windows, Linux, and macOS. It provides command-line and MCP interfaces for controlling and inspecting a computer.
Skill Claude CodeCodex
Build web3 applications, scripts, CLIs, bots, mobile apps, and desktop apps that need blockchain data via the Blockscout PRO API — a single HTTP API spanning 100+ EVM chains. Invoke this skill whenever the user wants to read blockchain data over HTTP (transactions, blocks, addresses, tokens, NFTs, logs, contract…
quantskills/skill-factor-orthogonalize
Skill Codex
Use when an agent needs to neutralize or orthogonalize a quantitative factor against industry, size, style exposures, or an existing factor library before evaluating, combining, or accepting the signal.
nekopunch11/rodya-caijing-studio
Skill Claude CodeCodex
A Chinese-language adviser for Hong Kong stock initial public offerings, or IPOs—the first sale of a company's shares to the public. It covers how to apply, how much to apply for, and risks such as the share price falling below the offering price.
bluefrog5096-4bmb1/security-advisory
Skill Claude CodeCodex
A drafting tool for open-source security advisories, which are notices explaining a software vulnerability and how to address it. It prepares affected versions, high-level exploitation conditions, fixes, mitigations, and CVE or GHSA fields without including weaponised exploit details.
redcrab2819-ack84/mcp-server-readme
Skill Claude CodeCodex
A writing skill for creating public README files for MCP servers. MCP, the Model Context Protocol, is a standard for connecting AI agents to tools and data; the README explains installation, authentication, capabilities, and risky actions.
Skill Claude CodeCodex
Search repository text through a deterministic first-class fak command.
MCP server Claude CodeCodexCursor +2
Generate and validate a .specs/ bundle for your repo, then hand it to your AI coding agent. Remote server at init.specpilot.dev.
Skill Codex
Coordinates custom specialists through workflow phases, artifact handoffs, approval gates, and autonomous implementation. Use when executing a workflow recipe or routing its next specialist.
Skill Codex
Local open-source Agent Skill for authorized web application, API, browser, business-logic, and supporting server-integrity penetration testing. Use for scoped OWASP WSTG, ASVS, and API Security assessments; authenticated and multi-role validation; attack-surface mapping; bounded DAST; evidence-backed findings…
Skill Claude CodeCodex
Build, edit, and verify QORM apps — an agent-native declarative-UI runtime whose apps are language-neutral JSON (qorm.json + scenes/ + actions/). Use when creating or modifying a UI as QORM JSON, packaging it for web/iOS/Android/desktop, or driving a live QORM app over MCP.
Skill Claude CodeCodex
An official Feishu/Lark integration for an AI agent. Feishu, also called Lark, is a workplace collaboration platform with chat, documents, knowledge bases, and spreadsheet-like Bitable databases.
KingJing1/podcast-transcript-txt-skill
Skill Codex
A workflow for finding and exporting cleaned podcast or video transcripts as TXT files. It accepts sources such as YouTube, episode webpages, podcast searches, social-media links, audio URLs, and episode titles.
Skill Claude CodeCodex
Pair-program a feature with another agent in the office. You drive (scope, design, implement); they review at design and code stages. Optionally takes the peer's name and a feature prompt as arguments.
MCP server Claude CodeCodexCursor +2
UCAI — The ABI-to-MCP Server Generator. Convert smart contract ABIs to AI-ready MCP servers. Runs locally from the abi-to-mcp Python package. Needs 3 environment variables to run.
Skill Claude CodeCodex
Drive the cultivar CLI to test whether an agent skill improves behavior — scaffold tasks, run with/without the skill across Claude/Copilot/Gemini (locally or on Modal), grade against a rubric, and read the results.
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: