Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 267,288 indexed, measured the same four ways as everything else here.
Create and read XMind mind map files (.xmind), supporting both modern (XMind Zen/2020+) and legacy (XMind 8) formats. Use this skill whenever the user mentions mind maps, brain maps, XMind, brainstorming diagrams, flowcharts, Gantt charts, project planning with visual maps, or wants to analyze/search existing .xmind…
Autonomous skill generator that learns new technologies from the web. Use when, users want to learn about a new library/framework/tool, need to create a skill for an unfamiliar technology, want to research and document a technology's usage patterns, or invoke with /learn . This skill uses web search and browser tools…
Create or customize OpenSpec workflow schemas in this repository using openspec schema init and openspec schema fork. Use when the user wants to add, fork, or validate a schema under openspec/schemas/.
Manipulate images locally using Python and PIL/Pillow. Use when the user asks to resize, crop, rotate, flip, filter, enhance, combine, overlay, watermark, add text to, convert, compress, create, or edit images locally. Also use for thumbnails, borders, color adjustments, transparency, animated GIFs, or extracting…
A skill for turning source documents such as PDFs, Word files, web pages, or Markdown into designed presentation pages and exporting them as PowerPoint files. It uses a staged workflow with planning, generation, preview, and quality checks.
Persistent memory + FTS5 search MCP server for Claude Code conversation history. Runs locally from the @kunwarshah/claudex npm package. Needs 1 environment variable to run.
★not rated 93 2mo agoA
tokens not measured
originalMIT
A local bridge for reading serial-port text and standard samples, then analysing logs and signal waveforms and adjusting device settings safely. Serial ports are connections commonly used to communicate with embedded devices.
Fetches Defold manuals and documentation. Use when looking up how Defold features work, understanding concepts, components, workflows, platform setup, or needing guidance beyond API reference.
Curador del conocimiento local de un proyecto bajo bucle ralph. Mantiene un conjunto de skills locales (metodologías, pitfalls y decisiones del proyecto) para que futuras iteraciones planifiquen y ejecuten sin dar palos de ciego. Su acción review lee el plan y los logs tras una tarea y crea, extiende o borra esas…
Use when the user asks to explain, walk through, or understand a feature, module, or code flow in the codebase. Triggers on 'explain', 'walk me through', 'how does X work', 'what does this code do'.
Guidance for driving Windows desktop automation from the wincli command-line tool - the token-efficient entry point that mirrors the Windows MCP server. Use when a coding agent has shell access and wants one compact command surface instead of many MCP tool schemas.
A specialist role that coordinates the full patent disclosure workflow, from prior-art searching and idea brainstorming through drafting, review, quality checks, and final editing. It keeps the resulting documents in a separate project folder and Git repository.
Jarvis MCP – Browser-based voice input/output for AI Assistant conversations via MCP (Model Context Protocol). Runs locally from the @shantur/jarvis-mcp npm package.
Lets the agent search and read Sentry issues, errors and traces, and act on them. Runs locally from the @sentry/mcp-server npm package. Needs 1 environment variable to run.
A text-to-speech tool that uses Xiaomi MiMo V2.5 models to turn written text into spoken audio. It supports preset voices, designed voices, cloned voices, and controls for style, emotion, dialect, and singing.
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: