Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 274,392 indexed, measured the same four ways as everything else here.
A guide to econometrics, the use of statistics to study relationships in data, based on a 12-part Korean lecture series. It routes questions to explanations of topics such as regression, panel data, instrumental variables, and causal comparisons.
Evidence-first deep investment research for US equities and crypto assets, with independent bull and bear cases, forensic checks, long-horizon valuation, and optional personalized buy, sell, short, and position-sizing decisions. Use when the user invokes SAS, requests deep fundamental or token analysis, asks whether a…
Author Hazelight AngelScript (.as) gameplay code for Unreal Engine 5.x projects using the Hazelight UnrealEngine-Angelscript fork. AngelScript looks like UE C++ but differs in load-bearing ways — no #include, no GENERATEDBODY, default keyword for sub-object config, float is 64-bit, RPCs are reliable by default, no…
Operate TUI (terminal user interface) programs through the tui-agent CLI tool. Use this skill whenever the user asks to interact with, automate, control, or test any terminal-based program — including editors (vim, nano, emacs), system monitors (htop, top, btop), file managers (ranger, mc), database clients (mycli…
Coordinate Polywave scout and wave flows in Codex. Use for parallel implementation planning, IMPL creation, and guarded wave execution with polywave-tools and the installed Polywave agents.
Makes AI-generated Three.js / WebGL / react-three-fiber code produce coherent, playable 3D scenes instead of code that compiles but looks and feels broken — correct model scale and orientation, grounded and non-overlapping placement, real collisions, frame-rate-independent controls, and characters that walk without…
Use when the user needs help installing, authenticating, troubleshooting, or using the local syft CLI for Syft AI news workflows. Trigger for first-time setup, syft login or syft status, followed-topics inspection, top stories, personal search, global search, Codex skill installation via syft install-skill, or any…
A setup process for connecting a new or reset AI agent to a local Second Brain—a personal collection of rules, identity information, and reusable skills. It installs the required skills, connects the supporting service, and checks the setup in a fresh session.
Read and annotate English technical papers in a terminal or chat with concise Chinese translations and explanations while preserving the source text and argument. Use when a user asks to read, explain, translate, annotate, or study an academic paper, arXiv preprint, PDF, DOI, technical passage, figure caption…
Generate a clean, professional IM / work avatar from a personal photo. Upload a selfie and get a business-grade headshot — minimal, polished, no over-the-top styling — ideal for workplace instant-messaging profiles (WeChat Work, DingTalk, Lark / Feishu), LinkedIn, and unified team avatars. Use when the user wants a…
Maintains an Agulater Agent Operational Contract after agent files change. Use when changing AGENTS.md, harness policy, graphs, skills, context layers, evaluation, or handoff behavior.
Read, search, traverse, edit, validate and draw ArchiMate architecture models (.archimate files) from the command line with the amcli binary. Use when the user asks about an enterprise, solution or application architecture model; when they mention ArchiMate, Archi, coArchi, a .archimate file, application components…
A guided resume-writing workflow that turns a person’s experience and a target job description into a professional resume in HTML and Word formats. A job description is the employer’s list of duties and requirements.
Write execution-ready Markdown handoffs for Codex /goal runs, including a short goal launcher prompt, authority stack, ordered phases, hard rules, verification gates, and final report requirements. Use when the user asks for a handoff, next-session plan, goal file, /goal prompt, agent execution contract…
Process and reconcile new Just Press Record iPhone recordings into a configured Git-backed Markdown vault. Use when the user invokes $vcr or asks to process the configured Just Press Record capture source; do not use for generic transcription or unrelated voice apps.
A reference guide for writing and editing skills, which are instruction packages that tell a coding agent how to handle particular tasks. It focuses on making those instructions predictable and easy to follow.
Fast CLI-first LLM council, bundler, and multimodal gateway. Use ONLY when user explicitly mentions "yoetz", "yoetz ask", "yoetz council", "yoetz review", "yoetz generate", "yoetz bundle", "yoetz browser". NOT triggered by generic "second opinion" or "ask another model" requests.
A Chinese-language learning workflow that helps a person use AI to study a new subject or skill. It covers setting goals, making a study plan, learning through conversation, keeping notes, and reviewing progress.
Manually score and audit Codex skills with a custom, modern prompt-fit 100-point rubric. Use when the user asks to rate, score, compare, rank, audit, or review one or more Skill folders or SKILL.md files; when they want before/after skill-quality comparisons; or when they need evidence-backed improvements to metadata…
Route artifact work through either a lightweight direct module or a managed multi-step workflow. Use direct mode for small single-module deliverables without dependencies or consequential choices; use managed task/image/office/video/package DAGs with durable state and human STOP reviews for connected or…
A tool for preparing WeChat Official Account article drafts through WeChat's official server API. It validates an article package, uploads its images, creates a draft, and reads the draft back for checking.
A read-only investigation mode for finding root causes, semantic drift, or incomplete capabilities before making changes. It prevents project files from being edited during diagnosis.
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: