Everything for Codex

Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 273,361 indexed, measured the same four ways as everything else here.

x-post-text

20257

sandover/agent-skills

Skill Codex

Extract the text of one or more X/Twitter posts or tweets, especially when the user wants only the post content and the page must be read through an authenticated Chrome session.

not rated 4 13d ago A 39 tokens

ncm-listening-profile

20258

dragonknightk/ncm-listening-profile

Skill Codex

A skill for collecting listening-history data from the NetEase Cloud Music desktop app on Windows or macOS. It uses the app's logged-in session to export playlists and listening rankings as local JSONL, CSV, and aggregate files, plus an analysis prompt.

not rated 4 3mo ago A 131 tokens MIT-0

ui-design-engineering

20259

ntaffzii/Skill-Agents

Skill Codex

Design, implement, harden, and review production-grade user interfaces for web apps, dashboards, SaaS products, admin tools, forms, and responsive frontend components. Use when building or improving UI/UX, translating Figma or requirements into code, styling React/Vue/Svelte/HTML views, reviewing frontend quality…

not rated 4 3d ago A 115 tokens original MIT

maccabi-pharm-search

20260

alexpolonsky/agent-skill-maccabi-pharm-search

Skill Claude CodeCodex

Search for medications and check real-time stock availability at Maccabi pharmacies in Israel. Use when searching for drugs like "nurofen", "acamol/אקמול", "advil", or finding nearby pharmacy branches with stock. Supports Hebrew and English drug names. מכבי פארם, תרופות, מלאי, בית מרקחת.

not rated 4 7mo ago A 78 tokens original MIT

data-cleaning-planner

20261

lianxhcn/PXa2026a

Skill Claude CodeCodex

Use this skill when planning or reviewing data cleaning for empirical research. Given a variable list and data dictionary, it drafts a cleaning plan; checks whether a merge/join is sound (1:1 vs m:1, key name/case/type/leading-zero consistency, expected match rate); explains the differences among missing-value…

not rated 4 2mo ago A 146 tokens

reviewcourt

20262

Chris1Wang3/Idea-on-Trial

Skill Claude CodeCodex

A review tool for completed Tencent Meeting requirements or technical-plan meetings. It turns the meeting notes and transcript into a verdict, such as approved, conditionally approved, rejected, or lacking enough information.

not rated 4 22d ago A 150 tokens original MIT

workbench-sim

20263

svd-ai-lab/sim-plugin-workbench

Skill Claude CodeCodex

Use when the user asks Codex, Claude Code, ChatGPT-style coding agents, or another AI agent to connect to Ansys Workbench through sim-cli. Supports Workbench journal execution, project inspection, persistent sessions, Mechanical handoff, bounded execution, artifact reporting, and troubleshooting. Requires a user-owned…

not rated 4 4mo ago A 70 tokens original Apache-2.0

justin-sun-narrative

20264

william19307/justin-sun-narrative

Skill Claude CodeCodex

A Chinese-language writing guide for long articles, X posts, and first-person narratives, based on a specified restrained narrative style associated with Justin Sun.

not rated 4 1mo ago A 75 tokens

xueqiu-prediction-audit

20265

icekale/xueqiu-prediction-audit

Skill Claude CodeCodex

Use when auditing a Xueqiu or similar public influencer's stock predictions, scoring directional calls, copy-trade P&L, quantifying public cubes against benchmarks, producing a public-text AI profile, producing a client prediction-audit PDF/PNG, or deeply fetching Xueqiu posts plus the influencer's own comments with a…

not rated 4 1mo ago A 150 tokens original MIT

openplan-auto

20266

BANANASJIM/openplan-skill

Skill Codex

Orchestrate OpenPlan-style skills in auto or YOLO mode while preserving human decision boundaries. Use when Codex, Claude Code, or another agent should automatically inspect, align enough to proceed, research, test, review, garden, summarize, hand off, or generate temporary HTML without silently approving, changing…

not rated 4 26d ago A 139 tokens original MIT

loop-architect

20267

Frontier-Intelligence-Lab/loop-architect

Skill Codex

Design a safe, verifier-first loop for an AI coding agent — or refuse when a task should not be looped. Use when someone asks "can I automate this with an agent?" or wants to create, audit, or improve a loop for coding agents, scheduled agent work, autonomous repo maintenance, CI/QA loops, refactoring loops…

not rated 4 2mo ago A 167 tokens original MIT

adversarial-research

20268

TheEnigmaticT/adversarialresearch

Skill Claude CodeCodex

Research a topic adversarially: attack provisional theses and present only the most defensible conclusion under an explicit evidence boundary.

not rated 4 2mo ago A 30 tokens CC-BY-4.0

nimbuu-ui-ux

20269

Haamiahphp/nimbuu-ui-ux

Skill Claude CodeCodex

Nimbuu UI/UX Skill. Logic-driven interface design distilled from Refactoring UI, Practical UI, and Fundamentals of Creating a Great UI/UX. Three uses. (1) ALWAYS when starting a new project, greenfield app, landing page, or prototype with no design system, no tokens, no brand kit, so spacing, type, colour, hierarchy…

not rated 4 1mo ago A 245 tokens original MIT

skill-issues

20270

mateuszperlak/skill-issue

Skill Claude CodeCodex

This skill makes the agent completely useless. It doesn't help. It gives confidently wrong short answers and blames the user.

not rated 4 7mo ago C 28 tokens

midjourney-prompting

20271

leggiemint/legnext-skills

Skill Claude CodeCodex

Expert Midjourney prompt engineering skill. Use this skill when users need help crafting effective Midjourney prompts, converting natural language descriptions into optimized prompts, or want guidance on Midjourney parameters and techniques. Specializes in V7 best practices, the 7-Element Framework, and photography…

not rated 4 9mo ago A 67 tokens original MIT

codex-coplan

20273

jiayx01/codex-claude-skills

Skill Claude CodeCodex

Bring in an external model (Codex) to co-develop a plan — both models draft independently, align on disagreements, and merge into one plan. Load this only when the user explicitly names Codex (e.g. "let's discuss this with Codex," "what does Codex think about this approach") — don't auto-trigger just because a plan…

not rated 4 1mo ago A 92 tokens original MIT

deep-ass-research

20274

Kaos599/Deep-Ass-Research

Skill Claude CodeCodex

Deep, multi-source, primary-sourced research into a backlinked Obsidian vault. Fans out scout/diver sub-agents that write atomic cited claim notes, adversarially verifies them, then synthesizes a Map-of-Content + report. Use when the user wants thorough, cited research on a topic, company, market, or literature, or…

not rated 4 2mo ago A 115 tokens original MIT

devtest

20275

AILiteracyLab/Claude-Build-Test-Loop

Skill Claude CodeCodex

Spec-Build-Test loop — the user defines a spec, then three agents iterate (Builder implements, Tester validates, Supervisor monitors for freezes) until the result matches. Works for any digital function — UI, APIs, CLI tools, conversational AI, data pipelines, and more.

not rated 4 7mo ago A 58 tokens original MIT

pdf

20276

CrewBench/CrewBench

Skill Claude CodeCodex

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

not rated 4 8mo ago A 50 tokens copy · 81% Apache-2.0

structural-code-editing

20277

yailPeralta/ast-mcp-server

Skill Claude CodeCodex

Trigger: navegar, analizar o editar TypeScript/JavaScript con el compilador. Use tools AST preparadas, revisadas y vinculadas por hash.

not rated 4 changed 29d ago A 37 tokens original ISC

coderef-governance

20279

keaizuizui/CodeRef-AI

Skill Claude CodeCodex

A workflow guide for using CodeRef-AI tools to organize and improve existing software projects. It groups the work into five stages covering mapping, refactoring, checking, health reviews, and follow-up work.

not rated 4 changed 17d ago A 338 tokens

hookradar/hookradar-agent-skill

Skill Claude CodeCodex

Use when researching competitors, paid ads, Meta Ad Library creatives, TikTok ads, Instagram/TikTok organic videos, HookRadar MCP data, creative trends, AI creative analysis, reports, downloadable ad/video assets, or shareable creative tables for marketing teams.

not rated 4 3mo ago A 60 tokens original MIT

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: