A hardware-aware Codex skill for local MiniMax H3 video generation through ComfyUI

Sub2API 一站式开源中转服务，让 Claude、Openai 、Gemini、Grok订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。

一个面向 IMA 笔记的 CLI — search notes, browse folders, read content, and manage note creation via the IMA OpenAPI

ai + quantative trading

Give your agent a computer 👾

An explorable Japanese suburban railway-crossing neighbourhood on a small planet, rendered 3D-to-2D as a cel-shaded anime background. Three.js, no image assets.

公募基金筛选

同频（Resonance）是一个本地化的 ETF「国家队」资金监控系统。它通过价格位置、份额流向、交易方向、成交额热度、融资杠杆五个指标各自亮灯，当同色灯≥3盏时判定为「危险共振」或「机会共振」，量化识别中央汇金等资金的系统性进出。数据、计算、存储全部在本机，支持一键重建全量历史、定时增量拉取，并提供 CLI 供外部Agent 转 IM 预警。仅用于研究，非投资建议。

The official API document for Seedance 2.5

Code to accompany "A Method for Animating Children's Drawings of the Human Figure"

The design language that makes your AI harness better at design.

The open-source CapCut alternative

代理,快捷切换codex 账号, 监控codex用量的工具,以及对codex进行api反代 , 支持多语言

Edit videos with coding agents

Extracted system prompts from Anthropic - Claude Fable 5, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-5.6-Sol, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Curso…

Claude Code for Financial Market

Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop

The most Token-efficient open-source AI Agent

Academic Research Skills for Claude Code: research → write → review → revise → finalize

A CLI for Xiaohongshu (小红书) — search, read, interact via reverse-engineered API

Code for the paper "AutoPresent: Designing Structured Visuals From Scratch" (CVPR 2025)

Code for "WebVoyager: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models"

personal agent skills for better QoL

trading-api

🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, …

An AI Hedge Fund Team

Lightweight AI Agent Harness for agentic coding: let strong models explore while humans steer with minimal specs, checkpoints, approval, validation, and reverse sync.

Prompt, run, edit, and deploy full-stack web applications using any LLM you want!