MCP servers and skills: search, filter by where they run, and compare.
QwenPaw 专用 DeepSeek 搜索 / 抓取 MCP：已配好 DeepSeek 提供商则 key 免填（自动解密 QwenPaw secret），两个工具 deepseek_search / deepseek_fetch
SkillMITFew starsNo key
Qwen-Image 2.1 NSFW/姿势出图 skill：作者级提示词配方 + NSFW LoRA + 136 姿势 VNCCS 人偶控制；适用 Claude Code / Codex / Cursor / OpenClaw
SkillApache-2.0★ 3.9kNo key
Qwen Image 2.1 for DeepSeek Harness: native image editing on Apple Silicon MLX/MFLUX or self-hosted CUDA, LoRA, ControlNet, inpainting, presets & live agent progress. 本机生图 · 原生参考编辑
SkillApache-2.0★ 31No key
SkillMIT★ 2Few starsNo key
OlaChill Japan travel plugin for Qwen Code
SkillMITFew starsNo key
Claude Code skill: on-demand Qwen worker on a Google Colab A100 via Ollama, started per task and stopped right after
SkillMITFew starsNo key
Fully local, privacy-first AI workbench for Windows: llama.cpp + Qwen with a bilingual Thai/English chat UI, per-project workspaces, guarded MCP tools, OCR and semantic document search, voice input, u
SkillMIT★ 1Few starsNo key
Edit photos by describing the change, on your own GPU. A free, open-source alternative to Nano Banana and ChatGPT image editing: photos stay on your computer, no daily limit. One installer for Windows
Node.jsAGPL-3.0★ 245No key
Open-source production workflow and QA toolkit for local MiniMax H3 photorealistic short-drama generation.
SkillMIT★ 4Few starsNo key
Turn any object into a page from an industrial designer's sketchbook. Four variants (pen, marker, ink, contrast), open image models (Qwen-Image 2.1, FLUX.2, Z-Image). An Agent Skill for Claude Code.
SkillApache-2.0★ 2Few starsNo key
Claude Code skill: turn plans and specs into a narrated explainer video with HyperFrames
SkillMIT★ 1Few starsNo key
一站式 AI 视频制作 Agent Skill 合集：大主题拆系列（series-video-planner）→ 手绘科普短片逐帧渲染（handdrawn-explainer-video）→ 高点击封面生成（douyin-cover-generator，默认 3:4 竖版 + 4:3 横版）。纯代码管线，确定性可复现。
SkillMIT★ 2Few starsNo key
Distill TikTok videos into timestamped knowledge cards - download + local Qwen video understanding, fully offline, no cloud quota.
SkillMITFew starsNo key
Media Lab — your own self-hosted AI media studio: image, video with audio, music, voice and an agent, on your GPUs
SkillAGPL-3.0★ 2Few starsNo key
Run alesha-pro/Qwen3.8-Flash-Next-abliterated on Google Colab
SkillApache-2.0★ 2Few starsNo key
Open-weight AI assistant, Specialist Bot workspace (T Bot), and 12-chapter engineering book built from scratch in Python & vanilla JS (Ollama, MLX, DeepSearch, MCP, SQLite RAG).
SkillApache-2.0★ 2Few starsNo key
Bulk AI image generation on your own Windows PC: FLUX.2, Qwen-Image, SDXL and more via stable-diffusion.cpp. Batches, reference images, LoRAs, upscaling, an OpenAI-compatible API and an MCP server for
SkillMITFew starsNo key
OpenCode: делегирование «лид → воркер» — скилл delegate-implementation + 10 профилей агентов (Qwen/GLM/GPT/Opus + DeepSeek workers)
SkillMITFew starsNo key
面向 Z-Image、Qwen-Image 2.1 与 MiniMax H3 的短剧制作 Skill：角色与场景提示词、图片确认、15秒分镜及按需 A/B 机位。
SkillLink only★ 23
Run LLMs on Intel Arc (B60, B580, B570, B50, B70, A770) with llama.cpp Vulkan: benchmarks, tuning, agent reliability evals, raw data.
SkillMIT★ 10No key
Local ASR on your hardware | 本地部署语音识别：Qwen3-ASR / FunASR, audio & video transcription, speakers, subtitles and independent sound analysis. Docker · HTTP · CLI · MCP · Agent Skill.
PythonApache-2.0★ 1Few starsNo key
Run Qwen3.8-Flash-Next (125B MoE) on a 48GB Apple Silicon Mac — llama.cpp + Metal console with prompt-cache / reasoning-effort / anti-repeat injection, live telemetry and MCP server
SkillMIT★ 1Few starsNo key
Every coding agent at its best, side by side. Run Claude, Codex, Gemini, Qwen and local models in parallel workspaces — switch models mid-conversation, collaborate, and keep going from your phone.
SkillMIT★ 2Few starsNo key
Who stands behind it
