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. 267,963 indexed, measured the same four ways as everything else here.

laravel-boost

2473

laraowl/laraowl

MCP server Claude CodeCodexCursor +2

MCP server "laravel-boost" as configured in laraowl/laraowl. Launched with php artisan boost:mcp.

not rated 343 +1 14d ago A tokens not measured copy · 100% Apache-2.0

terraform-minio

2474

aminueza/terraform-provider-minio

Skill Claude CodeCodex

Author, plan, and safely apply Terraform for MinIO and S3-compatible object storage using the aminueza/minio provider. Use this skill whenever the user works with the MinIO Terraform provider, writes or reviews any minio resource or data source (minios3bucket, minioiamuser, minioiampolicy, minioiamserviceaccount…

not rated 342 2d ago A SkillSpector: warn 224 tokens AGPL-3.0

documentation-server

2475

andrea9293/mcp-documentation-server

Skill Claude CodeCodex

Use when you need to store, retrieve, search, or manage documents in a local knowledge base with semantic search and hybrid (vector + full-text) retrieval. Also use when interacting with the documentation server web interface, managing uploads, or performing AI-powered document analysis. Use this instead of MCP-native…

not rated 342 17d ago A SkillSpector: warn 71 tokens original MIT

paper_reader

2476

Jennyee1/AcademicAgent

Skill Claude CodeCodex

A skill for reading and analyzing academic research papers in PDF form. It extracts text and figures and supports structured and visual analysis.

not rated 342 3mo ago A 31 tokens

coding_skill

2477

Negai-ai/AgentClaw

Skill Claude CodeCodex

Inspect, edit, test, refactor, and validate project code inside the configured project directory. Use when the task involves source search, code reading, bug fixes, implementation changes, syntax checks, automated tests, file moves, or refactors.

not rated 342 +1 3mo ago A SkillSpector: pass 52 tokens original Apache-2.0

vitest-evals

2479

getsentry/vitest-evals

Skill Claude CodeCodex

Use when authoring, reviewing, or debugging harness-backed vitest-evals suites, custom Harness adapters, first-party ai-sdk or pi-ai harness integrations, judges, replay, reporter-facing normalized run data, or examples and docs for these APIs.

not rated 342 +1 changed 2d ago A SkillSpector: pass 54 tokens original Apache-2.0

video-compose

2480

Utopai-Research/pai-pro

Skill Claude CodeCodex

Generates and prompts video clips on the filmmaking canvas. Use when the user asks to generate, render, animate, continue, restyle, edit, shoot, or compose a video clip; render script or shot notes as video; animate a storyboard, starting frame, image, character, location, or reference; use image, video, audio…

not rated 342 +5 changed yesterday A 127 tokens

luoling8192/software-design-philosophy-skill

Skill Claude CodeCodex

Software design philosophy guide based on John Ousterhout's "A Philosophy of Software Design." Use this skill during: code reviews, architecture discussions, API design, module decomposition decisions, refactoring guidance, complexity analysis, naming and commenting improvements, error handling strategy design.…

not rated 342 +1 2mo ago A 135 tokens original MIT

chenjin-cmd/wechat-miniprogram-builder

Skill Claude CodeCodex

A workflow guide for building, publishing, earning from, and promoting WeChat mini-programs, which are small apps that run inside WeChat. It covers AI-assisted development, account setup, regulatory filing, review, and growth operations.

not rated 342 +3 1mo ago A 126 tokens original MIT

story-long-analyze

2484

zenstory-ai/oh-story-dsh

Skill Claude CodeCodex

A Chinese-language analysis workflow for studying the structure of successful long online novels, from opening chapters to characters, settings, pacing, and plot rewards.

not rated 342 +28 changed 2d ago A 173 tokens copy · 95% MIT

skill-creator-ultra

2485

marketingjuliancongdanh79-pixel/skill-generator

Skill Claude CodeCodex

Tạo AI Skill mới từ ý tưởng hoặc quy trình công việc. Kết hợp phỏng vấn thông minh, pattern detection, và quantitative evaluation để tạo skill chất lượng production. Dùng khi user nói "tạo skill", "biến quy trình thành skill", "make a new skill", "tự động hóa công việc này", hoặc mô tả quy trình lặp lại mà họ muốn AI…

not rated 341 +1 6mo ago A 117 tokens

workspace-dispatch

2486

outsourc-e/clawsuite

Skill Claude CodeCodex

Autonomous multi-agent mission orchestrator. Decomposes a mission into tasks, spawns sub-agents for each step, reviews output against exit criteria, and chains tasks automatically with retry. State persists to disk so missions survive context loss. Triggered by the Conductor UI or by direct user request.

not rated 341 3mo ago A SkillSpector: warn 65 tokens original MIT

neutree-ai/openapi-to-skills

Skill Claude CodeCodex

This is a sample Pet Store Server based on the OpenAPI 3.0 specification. You can find out more about. Use when working with the Swagger Petstore - OpenAPI 3.0 or when the user needs to interact with this API.

not rated 341 +1 2mo ago A SkillSpector: pass 63 tokens original Apache-2.0

camoufox-cli

2488

Bin-Huang/camoufox-cli

Skill Claude CodeCodex

Anti-detect browser automation CLI & Skills for AI agents. Use when the user needs to interact with websites with bot detection, CAPTCHAs, or anti-bot blocks, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task that requires…

not rated 341 +1 26d ago C Socket: warnSnyk: fail 74 tokens original MIT

ai-kline

2489

QuantMLResearch/AI-Kline

MCP server Claude CodeCodexCursor +2

MCP server "ai-kline" as configured in QuantMLResearch/AI-Kline. Runs locally from the ai-kline Python package.

not rated 341 1y ago A tokens not measured

codemogger

2490

glommer/codemogger

MCP server Claude CodeCodexCursor +2

MCP server "codemogger" as configured in glommer/codemogger. Launched with codemogger mcp.

not rated 340 3mo ago A tokens not measured original MIT

termcast

2491

remorses/termcast

Skill Claude CodeCodex

Build TUIs with a Raycast-like React API using termcast. Implements @raycast/api components (List, Detail, Form, Action) rendered to the terminal via opentui.

not rated 340 +1 12d ago A 40 tokens original MIT

blazediff

2492

teimurjan/blazediff

Skill Claude CodeCodex

Run, author, or update BlazeDiff visual regression tests. Trigger on "visual test", "screenshot regression", "blazediff", "/blazediff".

not rated 340 +2 15d ago A SkillSpector: warn 37 tokens original MIT

sutra-commentary

2493

xr843/fojin

Skill Claude CodeCodex

A source-based comparison of how historical Buddhist commentators explained the same scripture passage. It uses aligned commentary texts and links each result back to the original book.

not rated 340 +1 2d ago A SkillSpector: pass 139 tokens original Apache-2.0

lucy-cxy/oss-investment-scorecard

Skill Claude CodeCodex

A framework for judging whether an open-source project or company could be a good investment for a venture-capital fund investing in US dollars during the current AI market cycle.

not rated 340 4mo ago A 180 tokens

afm

2495

scouzi1966/maclocal-api

Skill Claude CodeCodex needs its repo

Maintain and extend AFM (maclocal-api), a Swift OpenAI-compatible local LLM server and CLI for Apple Foundation Models, MLX models, API gateway proxying, and Vision OCR. Use when working on AFM CLI commands (afm, afm mlx, afm vision), OpenAI /v1/chat/completions and /v1/models behavior, streaming SSE, tool-calling…

not rated 340 +3 yesterday A SkillSpector: pass 114 tokens original MIT

taste

2496

senlindesign/taste-skill

Skill Claude CodeCodex

Reverse-engineer the design taste of any website. Given a URL, captures DOM data and a screenshot via real browser, then runs a 4-step analysis to produce {domain}.md + {domain}.json with practical design tokens (colors, typography, spacing, radii, shadows, grid) AND taste DNA (Trigger → Decision → Reason → Evidence…

not rated 340 +8 2mo ago B 223 tokens

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: