Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 267,959 indexed, measured the same four ways as everything else here.
Route agent Python tooling to a dedicated venv at /.venvs/omagents, separate from any project's Python environment. Use whenever the agent needs to install or run a Python tool/library to complete a task — e.g. openpyxl to generate Excel, pdf2md/pdfplumber to convert PDFs to Markdown, Pillow to generate images…
Read ghtkn's documentation with ghtkn docs list and ghtkn docs show before answering. ghtkn is a CLI that creates short-lived (8h) GitHub user access tokens from GitHub Apps. Use for any question about ghtkn, GHTKN environment variables, ghtkn get / exec / auth / agent / revoke, the ghtkn git credential helper, or…
A Chinese-language thinking framework based on Charlie Munger’s public talks, writing, decisions, and criticism. It provides mental models and decision heuristics for examining choices and biases.
Author a Tabame launcher plugin — an external Python/Node/Bun script that extends the app launcher, talking newline-delimited JSON over stdin/stdout. Use when the user wants to build, scaffold, debug, or install a Tabame launcher plugin, add a new launcher keyword backed by a script, or asks about the plugin…
Build high-converting cross-border ecommerce PDP, hero image, product image stack, and AI image prompt strategy by resolving minimum inputs in priority order from user input, attachments, context, web research, logic inference, and explicit assumptions/defaults; then diagnose the conversion driver, produce an English…
Use when user wants to analyze China stock reports (A-share or Hong Kong), upload annual/quarterly reports to NotebookLM, or research a Chinese listed company's financials.
A skill for analysing and recreating the browser features that website JavaScript expects when running in Node.js. Node.js is a server-side JavaScript runtime, while browser code may depend on objects such as the DOM, storage, canvas, WebGL, workers, and network APIs.
Capture actionable user requests as persistent tasks, update task status as work progresses, and keep a shared task store in sync. Use when a user asks an agent to do work, check progress, block a task, complete a task, or manage the Kanban board.
An AI news workflow skill for collecting, filtering, writing, publishing, and archiving information from the MakeContents application. A news agent is software that performs these steps automatically.
Drive an agentic loop that iteratively optimizes a GPU kernel for maximum speedup. Use this skill whenever the user wants to optimize / speed up / benchmark a GPU kernel (CUDA, Triton, TileLang, C++, Python), mentions AKO / AKO4ALL / AKO4X / agentic kernel optimization, asks to "make this kernel faster", or has a…
Tool-neutral CLI agent rules for TI MSPM0 development with Code Composer Studio, Keil/uVision, CMake/GCC/OpenOCD, SysConfig, and DriverLib. Use when an agent needs to inspect or modify MSPM0 projects, edit .syscfg configuration, avoid generated SysConfig/build files, use DriverLib APIs, validate SysConfig output…
Run dev servers and terminal commands that AI agents can read, wait on, and type into. Wrap any command in a named background session. Humans get auto-attached; agents get a session they can inspect with read, snapshot, wait, and type.
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
Generate customer testimonial and social proof video prompts for Seedance 2.0 on Higgsfield. Use for customer stories, case study videos, review showcases, social proof content, success story videos, or any content featuring customer results and experiences. Triggers on testimonial, review, case study, social proof…
A skill for creating videos with Remotion, a framework that defines video scenes with React code. It covers animation, subtitles, music visualizations, data-driven videos, tutorials, and some 3D content.
A workflow that turns written dream descriptions, diary entries, or spoken dream material into generated videos. It uses the Jimeng platform and downloads the finished video locally.
Create, maintain, or migrate functional skills; supports creating from a requirement brief and migrating an existing legacy skill directory into a functional skill structure.
Use when a Web JS reverse task has unclear phase selection, mixed source-chain and shell blockers, runtime divergence, validation-only work, or RS/瑞数 clues such as 412, cookie hops, sign, token, JSVMP, worker, wasm, hasDebug, or basearr.
Control Xiaoai speaker via OpenXiaoAI Voice API for high-quality TTS playback. Use when the user wants to play voice notifications, announcements, or TTS through the Xiaoai speaker using the OpenXiaoAI HTTP API. Supports Doubao (ByteDance) TTS with emotions, voice types, and speed control. Triggers on queries like…
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: