local multi-agent harness

🪧 Claude Code / Codex skill — generate Xiaohongshu carousels & WeChat 21:9+1:1 cover pairs. Editorial × Swiss visual systems, 28 layouts, 10 themes, single-…

AI-powered file organization using the PARA method (Building a Second Brain). Intelligent categorization into Projects, Areas, Resources, Archive with inbox…

A local Windows dashboard for Claude Code and Codex usage limits.

Feed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas makes it readabl…

Agent skill for multi-speaker meeting & podcast transcription — FunASR (Paraformer/SenseVoice/Whisper) + MiMo-V2.5-ASR + CAM++ speaker diarization + LLM clea…

ISO 24495 Plain Language skills and Claude Code plugin

跨 agent 的 skill 管理器 + skill 推广工具，欢迎fork和pr。管理你所有 skill 的收纳/更新/进化；想推广就 ps create 1 创自带宣传 HTML + PPT。支持 Claude Code / Codex / Mavis / Cursor / Windsurf。

🦴 paleo — token-saving skills for LLM agents: compress output, trim context, cap budget (Claude Code / Codex / Gemini / Hermes)

AK體 · 數據驅動的 Threads 寫文決策系統。用你的歷史貼文、演算法與社媒心理學，協助選題、起草、發文前診斷、表現預估與復盤。Data-driven Threads writing advisor — topic selection, drafting, diagnosis, prediction & r…

The Finn-loop: a 3-skill AI software factory for Claude Code — spec, build, review. Humans merge.

Auto-resume Claude Code, Codex CLI & Grok sessions in tmux when the usage limit (5-hour/weekly) resets

Private web search for AI assistants via SearXNG — supports Claude, Cursor, and any MCP client

A Claude Code-native AI agent that searches real jobs, maps your skills against market demand, writes tailored applications, and tracks your pipeline — built…

Skills for teaching agents how to build on Cloudflare.

Open-source observability & evaluation platform for AI agents and coding agents. Trace LLMs, tools, prompts, costs & agent workflows with OpenTelemetry.

Token-reduction toolkit for Claude Code, OpenCode & other coding harnesses.

My collection of Claude skills

Claude Code skills for ROS 2 Jazzy — establish the unknowns first, verify against the installed system, prove the result ran.

Evidence-based learning engine for Claude Code — first-principles curricula, free-recall verification with receipts, FSRS-scheduled memory, and explorable ar…

TypeScript multi-agent orchestration framework. Describe a goal, a coordinator decomposes it into a task DAG that runs on any LLM: Claude, ChatGPT, Gemini, D…

Graph engineering for AI agents: the 9-stage knowledge-graph pipeline (translated from SEU's graduate course) + task-graph orchestration patterns, as a Claud…

PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.

The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3

🤖 Claude Code定制化研发流程系统 - 基于Spec-Driven和Test-Driven的AI智能体团队协作框架。构建AI优先的软件开发新范式，让AI智能体团队替代传统人类开发团队。

Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini & more. Industry-firs…

Gentle reminders for unfinished threads from past sessions — built for ADHD brains. Claude Code plugin. (test mode)

All-in-one New-API/Sub2API account hub: balance/usage dashboard, auto check-in, one-click keys, price comparison, health checks, plus advanced channel manage…

Ruler — apply the same rules to all coding agents

Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically..