Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
iv-studio
MCP serversFree, open-source AI film studio on your own PC. Recurring characters, MiniMax H3 and Seedance shots, voices, music, a short-film wizard and a real editor, on your ComfyUI or your own cloud GPU. Windows, Mac and Linux, with 214 MCP tools so Claude Code, Codex or Hermes can run it.
git clone https://github.com/hollisorg/iv-studio.git -
textbook-writer-skills
SkillsUbD 逆向设计驱动的教材写作 skill 组合,一键装进 Claude Code / Codex / WorkBuddy:教学定位 → 五件套 gate → 章节树 gate → 四段式逐章写作 → 审核定稿。学科无关内核 + 可插拔学科档案,理科真算复核、人文社科逐字核对引文出处,验证不了就标注「需作者确认」;关键决策作者拍板,中断随时续写
git clone https://github.com/cabbage2000-lab/textbook-writer-skills.git -
comfyui-mcp
SkillsLocal-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55 installer packs. Local, LAN, VPS, or Comfy Cloud.
git clone https://github.com/artokun/comfyui-mcp.git -
knowledge-rag
AI repositoriesLocal RAG server for Claude Code, Cursor and other MCP clients: hybrid BM25 + vector search with cross-encoder reranking on by default, 13 MCP tools, 33 file types including code, re-indexing on file changes. One Python process with embedded ChromaDB and FastEmbed ONNX: no Docker, database server or API key; offline after the first model download.
git clone https://github.com/lyonzin/knowledge-rag.git -
ai-research-skills
SkillsUniversal SKILL.md catalog for research workflows: literature review, research design, project memory, manuscript writing, and cross-agent delegation for Claude Code, Codex, Gemini, Cursor, OpenClaw, and generic AI clients.
git clone https://github.com/WenyuChiou/ai-research-skills.git -
ManimCat
AI repositoriesEN: ManimCat: AI-generated math animations from natural language. High-quality Manim rendering with LaTeX support and auto-code fixing. 中: ManimCat:AI 数学动画生成器。支持描述即视频,内置 LaTeX 与代码纠错,让数学动效触手可及。
git clone https://github.com/Wing900/ManimCat.git -
image text to text model by nota-ai · transformers
nota-ai/Kimi-K3.1-Pro-Global-Pruned-30 -
workspace-architect
SkillsWorkspace Architect is a zero-friction CLI tool that provides curated collections of specialized agents, instructions, and prompts to supercharge your GitHub Copilot experience.
git clone https://github.com/archubbuck/workspace-architect.git -
paint-video-skill
SkillsAn agent skill for hand-drawn animated shorts and music videos made entirely in code: thirteen styles, each with a finished film and the code that made it. 让 AI agent 用代码画手绘动画短片和 MV,十三套画风,每套都有成片和能跑的代码。
git clone https://github.com/nzl153/paint-video-skill.git -
open-seo-mcp-skills
SkillsFree SEO MCP server + open-source SEO and GEO skills for Claude: keyword research, rank tracking, audits, backlinks, AI visibility on your real GSC/GA4/ads data. claude mcp add ryze --transport http https://connector.get-ryze.ai/mcp
git clone https://github.com/Ryze-AI-Adgent/open-seo-mcp-skills.git -
North Carolina Code
MCP serversNorth Carolina General Statutes — state statutes by citation, plus topic search.
@pipeworx/mcp-north-carolina-code@0.2.1 -
reel-studio
SkillsAgency-quality marketing reels, ads and posts made by Claude Code. Free and open source, no per-video fees. HTML on one clock → MP4.
git clone https://github.com/murathany7/reel-studio.git -
ephemora-cell
MCP serversEphemeral, stateless, capability-bound execution for untrusted AI and agent-generated code.
git clone https://github.com/MichaelS1011/ephemora-cell.git -
OpenQR
Public APIsGenerate QR codes and manage dynamic (editable) QR codes with scan analytics
-
image text to text model by nota-ai · transformers
nota-ai/Kimi-K3.1-Pro-Global-Pruned-37 -
comfy-colab-kit
MCP serversZero-GPU-idle gateway for running ComfyUI on ephemeral Google Colab VMs with Zero-Trust Access
git clone https://github.com/FireTable/comfy-colab-kit.git -
Kimi-K3.1-Pro-pruned75
Modelsimage text to text model by vllm-project · transformers
vllm-project/Kimi-K3.1-Pro-pruned75 -
flutter-flame-harness
Agents & frameworksIdea-to-store autonomous harness for Flutter/Flame games across Claude Code, Antigravity, and Codex. Automates research, planning, design, generator-evaluator loops, AdMob, and store submission.
git clone https://github.com/tjdrhs90/flutter-flame-harness.git -
AI-Skills
SkillsA curated collection of 150+ specialized AI Skills for software development, frontend, backend, automation, UI/UX, SEO, and DevOps. Each skill encapsulates a focused capability: generating code, templates, scripts, and production-ready workflows.
git clone https://github.com/MarcoNasi/AI-Skills.git -
Anti-Autoresearch
SkillsDon't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.
git clone https://github.com/wanshuiyin/Anti-Autoresearch.git -
Moltline Code Review
MCP serversRisk-scan a diff, flag AI-generated-code tells, find secrets. 5 of 7 tools need no account.
-
research-first-writer
SkillsClaude Code skill for research-first articles that rank in Google and get cited by ChatGPT, Perplexity & AI Overviews. Real SERP research, a facts ledger, rule checks, no fake "we tested".
git clone https://github.com/jayanti-prajapati/research-first-writer.git -
session-story
SkillsGenerate a self-contained HTML "session story" that links each prompt in a vibe coding session to the file edits it caused, with a review timeline, a GitHub-style diff view, and a plain-language narrative.
git clone https://github.com/nalaj/session-story.git -
mianstack
AI repositories🚀 面栈 MianStack|程序员面试题库天花板!Java、Python、数据库、算法、大模型、AI Agent、RAG 一栈备齐。真实面经关联高频考点,按公司、岗位定向备考;图文题解、精华专题、项目源码拆解,全系标配。面试官出题,面栈出招!免费开源,持续更新。
git clone https://github.com/didilili/mianstack.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.