Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
dyz-med-paper-skills
Prompts面向中国医生与医学研究生的医学论文写作 Agent Skills:32 个技能覆盖 PubMed 文献检索、统计分析、中英写作、选刊投稿与审稿修回,适用于 Claude Code、Codex。Medical writing skills for Claude Code & Codex.
git clone https://github.com/duyunzhoudyz/dyz-med-paper-skills.git -
SSRF-safe URL proof receipts, clean markdown, and SHA-256 change watch for agents.
-
agentero-dsh-plugin
Agents & frameworks给 DeepSeek Harness 用的科研文献库插件:搜论文、带出处、审批入库、把笔记线索交给同会话其他插件。Academic research library for DSH — search, cite, approve imports, hand off notes.
git clone https://github.com/poco-ai/agentero-dsh-plugin.git -
llm-router
MCP serversUniversal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
git clone https://github.com/ypollak2/llm-router.git -
MC-AI-Coding-Assistant-Tool
MCP servers让 AI 编程助手(Cursor / Claude Code 等)能更好地编写 Minecraft 模组的完整工具包。
git clone https://github.com/guguzea/MC-AI-Coding-Assistant-Tool.git -
little-canary
SkillsDetects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.
git clone https://github.com/hermes-labs-ai/little-canary.git -
consensus-pipeline
Agents & frameworksMulti-agent department framework for long-form complex tasks, fighting AI hallucination, validated on academic research. 共识管线:多智能体部门长线任务解决框架,对抗AI幻觉,以学术研究为验证场景。
git clone https://github.com/fangqian616/consensus-pipeline.git -
antirion
AI repositories🕷️ The fastest open-source AI Gateway and LLM Gateway — one binary with built-in console to route, secure, budget and observe every LLM call across OpenAI, Anthropic, Gemini, Bedrock and more.
git clone https://github.com/eliasbiondo/antirion.git -
education-agent-skills
Prompts165 evidence-grounded AI skills for teachers, school leaders and EdTech builders—pedagogy, learning science, curriculum, assessment and regeneration. Claude, Codex and Hermes.
git clone https://github.com/GarethManning/education-agent-skills.git -
Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.
google/gemini-3.5-flash-lite -
openalex-research-mcp
MCP serversMCP server for the OpenAlex API — search 240M+ scholarly works, analyze citations, track research trends, and map collaboration networks
git clone https://github.com/oksure/openalex-research-mcp.git -
面向中文用户的学术论文与科研 Agent Skill 每日排行榜 · 自动搜索、过滤并排名 GitHub 上的 Claude Code / Codex / OpenCode 科研 Skill 仓库
git clone https://github.com/kael-odin/awesome-academic-research-skills.git -
Star-Office-UI
Agents & frameworksA pixel office for your OpenClaw: turn invisible work states into a cozy little space with characters, daily notes, and guest agents. Code under MIT; art assets for non-commercial learning only.
git clone https://github.com/ringhyacinth/Star-Office-UI.git -
Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.
google/gemini-3.5-flash-lite:batch -
Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...
bytedance-seed/seed-2.0-lite -
academic-agent-toolkit
Skills250+ academic Agent skills + orchestration engine: math modeling · paper writing · LaTeX · scientific figures · literature review · IP drafting. Host-agnostic (any Agent), quality gates + audit evidence chain. CC-BY-NC-4.0.
git clone https://github.com/FOURTEEN1416/academic-agent-toolkit.git -
batchin-public
Tools & apps⚡ Ultra-Reliable AI Inference Gateway & Verifiable Agent Control Plane. Dual-Dispatch, Zero-Token JSON Auto-Healer, VaaS On-Chain Attestation, FastMCP & Vercel AI SDK.
git clone https://github.com/aw3703/batchin-public.git -
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...
google/gemini-2.5-flash-lite -
Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...
google/gemini-3.1-flash-lite -
Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...
google/gemini-3.1-flash-lite:batch -
Research Methodology Design for Health Literacy and Medication Adherence in Aotearoa New Zealand
PromptsAct as an Expert Research Methodologist. You are tasked with designing a research study on the topic of health literacy and medication adherence among adults with chronic diseases in Aotearoa New Zealand. Your task is…
-
LiteWebAgent
Agents & frameworks[NAACL2025] LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications
git clone https://github.com/PathOnAIOrg/LiteWebAgent.git -
skills
Skills26 reusable skills for Claude Code, Codex, Hermes and other AI agents — DevOps, SRE, Linux, Docker, LiteLLM, Open WebUI, OpenWrt, Telegram, animated diagrams
git clone https://github.com/nordz0r/skills.git -
PaperOrchestra
SkillsAn automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.
git clone https://github.com/Ar9av/PaperOrchestra.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.