Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
claude-skills-research
SkillsClaude Code skills for academic research support: paper review, bibliography verification, literature surveying, head-to-head paper comparison, and HPC experiment campaigns.
git clone https://github.com/chgagne/claude-skills-research.git -
Maximal Marginal Relevance (MMR) exemplar selector optimizing semantic relevance and diversity for LLM prompt engineering
git clone https://github.com/Alpha-Park/genpark-few-shot-mmr-diversity-selector-skill.git -
OpenIndex Retrieval Plugin API
Public APIsA retrieval API for querying and filtering documents based on natural language queries and metadata
-
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 -
MediaCraft AI
Public APIsChinese content compliance review (17 platforms), EN↔CN translation, and SEO optimization. Pay-per-call via x402 (Solana USDC).
-
skills
SkillsProgramAsWeights agent skill - compile natural-language specs into tiny, locally-running neural functions for fuzzy text tasks (classify, extract, repair, fuzzy-match, triage, route). npx skills add programasweights/skills
git clone https://github.com/programasweights/skills.git -
ML Team Account Management Client
Public APIsThese APIs allow end users to operate on Azure Machine Learning Team Account resources. They support CRUD operations for Azure Machine Learning Team Accounts.
-
flow-map-resp
SkillsA Claude Code skill that turns your pipeline into an animated metro map, replayed from what a real run recorded. Retries as loop arcs, parallel work as rails, checks as hubs with spokes. React + SVG, your colours, light and dark.
git clone https://github.com/Galehashoid/flow-map-resp.git -
vexjoy-agent
Tools & appsVexJoy AI Agent with Jev Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.
git clone https://github.com/notque/vexjoy-agent.git -
lms-front
MCP serversOpen-source multi-tenant LMS for creators and schools: sell courses on your own subdomain. Next.js 16 + React 19 + Supabase (RLS) + Stripe Connect, an AI tutor over MCP, gamification, certificates, i18n (en/es). Self-hostable.
git clone https://github.com/guillermoscript/lms-front.git -
grandma
Tools & appsA memory layer for Claude Code that learns as you work. Persistent, per-context memory as plain markdown in your own git repo. No server, no telemetry.
git clone https://github.com/anshulforyou/grandma.git -
Pandorabots AIaaS
Public APIsAIaaS provides API access to our bot hosting platform and SDKs, allowing developers to easily integrate conversational interfaces into applications.
-
Reviva
AI repositoriesLocal-first AI learning workspace — ask, note, review and create around your own materials. Wiki KB, Agents, Skills, creation tools.Private NotebookLM Alternative.AI 学习工作台,围绕你的资料完成问答、笔记、复习和创作输出。本地优先,多模型,Wiki 知识库,AI Agent,创作工具。本地 NotebookLM
git clone https://github.com/mingchen666/Reviva.git -
ContextLattice
Agents & frameworksThe local-first intelligence layer that gives AI agents durable continuity, explainable retrieval, portable context, and verified learning across harnesses.
git clone https://github.com/sheawinkler/ContextLattice.git -
CLAUDE-CERTIFICATIONS
MCP serversStudy guide for all four Anthropic Claude certifications: Associate Foundations (CCAO-F), Developer Foundations (CCDV-F), Architect Foundations (CCAR-F), Architect Professional (CCAR-P). Official exam guides, blueprints with domain weights, cheat sheets, 320 practice questions, three mock exams each, 110 flashcards, and a printable companion.
git clone https://github.com/Amey-Thakur/CLAUDE-CERTIFICATIONS.git -
HARTOS
Agents & frameworksAn AI-native OS. Models run on your own hardware, nodes federate peer-to-peer with no broker, and the API is OpenAI-compatible. Boots, has its own Wayland compositor, and runs on 8GB. Apache 2.0.
git clone https://github.com/hertz-ai/HARTOS.git -
LLM-PySC2
Agents & frameworksLLM-PySC2 is NKAI Decision Team and NUDT Decision Team's Python component of the StarCraft II LLM Decision Environment. It exposes Deepmind's PySC2 Learning Environment API as a Python LLM Environment.
git clone https://github.com/NKAI-Decision-Team/LLM-PySC2.git -
vividpaper
SkillsVividPaper 视觉化读论文 · Claude Code / Codex skill: turn any paper (arXiv or PDF) into an animated, voiced explainer page · 把一篇论文做成带配音的动效解读页 · 在线示例:Transformer / ResNet / ViT / DDPM / CLIP / RoPE / Flow Matching · 张指导出品
git clone https://github.com/ManagerZhang10/vividpaper.git -
claude-plugins
Agents & frameworksOpen-source Claude Code plugins for multi-agent software delivery. Plan-first SDLC workflow, code review, LLM quality judges, and self-learning — grounded in your codebase. Bootstrap, Plan, & Ship.
git clone https://github.com/closedloop-ai/claude-plugins.git -
agentic-ai-engineering
PromptsHands-on tutorials for building AI agents from scratch. Learn LLM APIs, prompt engineering, tool calling, and the agent loop through practical examples.
git clone https://github.com/agenticloops-ai/agentic-ai-engineering.git -
ai-trending-repos
SkillsA curated list of the most popular and trending AI repositories and LLMs
git clone https://github.com/bobpage0451/ai-trending-repos.git -
ai-research-writing-skill
SkillsAI Research Writing Skill (AI论文写作技能) is an agent skill for ML / AI / CV / NLP researchers. Point your coding agent at code, experiment logs, notes, and a venue template; it helps you produce an auditable, evidence-backed LaTeX draft and submission package — not a polished fiction.
git clone https://github.com/jin-s13/ai-research-writing-skill.git -
evolving-agents
Agents & frameworksA director agent that learns how your team works: it plans by walking your CLAUDE.md and memory as linked statements, delegates to Claude Code or local models, and keeps each lesson as a gated, versioned patch. Measured: 0.929 vs 0.589.
git clone https://github.com/EvolvingAgentsLabs/evolving-agents.git -
The curriculum mapping prompt.
PromptsPrompt: "Task: Based exclusively on the uploaded materials, engineer a comprehensive [Insert Number]-week curriculum map. Constraints: Structure the learning journey using Bloom's Taxonomy, moving learners from basic…
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.