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. 273,987 indexed, measured the same four ways as everything else here.

bugfix-worktree

27361

midFang/ai-agent-skills-workflow

Skill Codex

A procedure for fixing one tracked bug in its own Git worktree, which is a separate working copy tied to a branch. It includes self-checking the fix and building an Android APK for human testing.

not rated 2 3mo ago A 144 tokens original MIT

auto-sci-research

27362

Lzy599775/agent-auto-sci-skills

Skill Codex

A coordinating skill for managing a complete research workflow, from choosing a topic and finding literature to analysis, figures, manuscript writing, review, submission, and later revisions.

not rated 2 changed today A 151 tokens original MIT

code-style

27363

Major-Woolfi/Skills_for_AI-Agents

Skill Claude CodeCodex

A set of coding and repository conventions covering Python, Telegram bots, project structure, typing, logging, documentation, Docker, and deployment files.

not rated 2 1mo ago A 35 tokens original MIT

autosurvey-execution

27364

sillyDaibo/reasflow-dev

Skill Claude CodeCodex needs its repo

Use when running the full AutoSurvey-backed outline, draft, related-works, or unattended survey pipeline.

not rated 2 1mo ago A 25 tokens original MIT

cyber-compliance-mapper

27365

arush15june/cyber-sales-agent-skills

Skill Claude CodeCodex

Use when you are given a company name, domain, or short description and need to determine which cybersecurity regulations, compliance frameworks, and data-protection laws apply to it — and which of those obligations mandate security testing, VAPT, red-teaming, or continuous control validation.

not rated 2 3mo ago A 62 tokens

simple-review-helper

27366

wxxsw/skillcheck

Skill Claude CodeCodex

Use this skill when reviewing a small code change and you need a concise checklist for correctness, tests, and maintainability.

not rated 2 1mo ago A 28 tokens original MIT

wanglixin-DLUT/paper-writing-skills

Skill Claude CodeCodex

Use when the user wants to analyze target research articles, reverse-engineer journal or field writing conventions, create a reusable writing blueprint or outline for a scientific paper, integrate contentanalysis.md from a deep learning project, prepare shared context for other research-writing skills, or diagnose the…

not rated 2 4mo ago A 81 tokens

a-share-strategy-library

27369

minguncle/a-share-agent-skills

Skill Codex

Maintain the rolling A-share strategy library that stores imported macro hypotheses, scenario cards, daily market entries, holdings-first actions, and main-board tradable picks under strategylibrary/. Use when Codex needs to convert user macro materials, live market validation, or same-day A-share review into…

not rated 2 6mo ago A 101 tokens original MIT

olakunlevpn-react-skills

27370

olakunlevpn/olakunlevpn-react-skills

Skill Claude CodeCodex

Use when writing, reviewing, or refactoring React or Next.js code — components, hooks, state management, testing, performance, TypeScript patterns, server components, or project structure. Always apply these standards to all React work.

not rated 2 6mo ago A 54 tokens original MIT

ayoubben18/ab-skills

Skill Claude CodeCodex

Interrogate the user about a plan or design, then iterate against user-supplied acceptance checks in a self-scoring loop until every check passes. Use when the user wants their plan stress-tested AND wants the model to keep refining until a concrete set of pass/fail criteria are satisfied. Triggers on "grill me with…

not rated 2 6mo ago A 105 tokens

e2e-runner

27372

Kacper0199/Opencode-Ultrathinker

Skill Claude CodeCodex

End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.

not rated 2 4mo ago A 59 tokens

doc-to-md

27373

ansea09/agent-skills-and-protocols

Skill Codex

Public core for converting trusted local documents and data files to Markdown using the installed Microsoft MarkItDown wrapper, with reusable workflow profiles for standard local documents, EPUB LLM-analysis bundles, and textbook-like PDF audit/OCR. Use when Codex is asked to convert, extract, ingest, normalize, or…

not rated 2 changed 1mo ago A 139 tokens original MIT

peak-scripts

27374

Peak-Studios/peak-agent-toolkit

Skill Codex

Install, configure, integrate, troubleshoot, or improve public Peak Studios FiveM resources using versioned documentation and source provenance. Use when working with peak-bridge, peak-chess, peak-clothingitems, peak-sprays, or peak-trucking; when selecting a compatible Peak script; or when adapting one to ESX…

not rated 2 10d ago A 89 tokens original MIT

mtg-commander

27375

P47Phoenix/Claude-Plugins

Skill Claude CodeCodex

MTG Commander deck builder with multi-agent pipeline. Build synergy-dense, format-legal, budget-compliant 100-card Commander decklists. Synergy-first card selection via Scryfall API. Triggers on phrases like "build a commander deck", "MTG deck", "commander deck", "EDH deck", "build me a deck", "100-card deck"…

not rated 2 23d ago A 92 tokens original MIT

tracker

27376

outputty/claude-plugin

Skill Claude CodeCodex

Gives the exact tracker commands - list and read tickets, create them with dependencies, claim and release, the board's Status moves, stacked PRs. Use whenever a task touches a ticket, the board, or a stacked PR, so nothing is guessed. This copy implements GitHub Issues with gh; a person on another tracker rewrites…

not rated 2 changed 8d ago A 77 tokens

html-to-pdf

27377

yonggao/claude-plugins

Skill Claude CodeCodex

Converts HTML files to PDF or PNG format. Use this skill when the user asks to convert, export, or generate PDF/PNG from HTML files, or when they want to create printable documents, presentations, or long-form images from web pages or HTML reports.

not rated 2 9mo ago A 58 tokens original MIT

provectus/claude-plugins

MCP server Claude CodeCodexCursor +2

MCP server "provectus-claude-plugins-finder" as configured in provectus/claude-plugins. Runs dist/index.js with node.

not rated 2 7mo ago A tokens not measured

arktype

27379

eralmansouri/arktype-claude-plugin

Skill Claude CodeCodex

Runtime TypeScript validation library with 1:1 type syntax. Use when creating validators, parsing data, or working with ArkType schema definitions using type().

not rated 2 9mo ago A 34 tokens original MIT

fpga

27380

george11642/george-plugins

Skill Claude CodeCodex

Master FPGA skill covering Vivado, SystemVerilog/Verilog/VHDL, RTL design, timing closure, CDC, AXI interfaces, FSMs, pipelines, memory interfaces, HLS, verification, and hardware optimization. Uses Context7 MCP for up-to-date library docs. Use when FPGA, Verilog, VHDL, HDL, RTL, synthesis, or hardware design…

not rated 2 6mo ago A 82 tokens

chroma-memory

27381

sfrangulov/claude-shared-memory-plugin

Skill Claude CodeCodex

A shared team memory skill backed by ChromaDB, a system for storing and searching text knowledge. It responds to requests about team knowledge, decisions, and shared memory.

not rated 2 7mo ago A 135 tokens

image-to-code

27382

ashu2012/claude-skill-connectors-plugins

Skill Claude CodeCodex

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…

not rated 2 2mo ago A 116 tokens

status

27383

rogue-security/rogue-plugins

Skill Claude CodeCodex

Check Rogue Security AIDR connection status, active rulesets, and configuration for Google Antigravity.

not rated 2 changed 28d ago A 22 tokens

skills

27384

agentalabs/agenta-plugin

Skill Claude CodeCodex

Single source of truth for all available skills — internal and external (submodule-based).

not rated 2 6mo ago A 0 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: