InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. ego-lite

    Skills

    The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero config.

    Indexed GitHub, citrolabs 23.0k ★MITUpdated today

    git clone https://github.com/citrolabs/ego-lite.git
  2. 把法律画出来 · 给法律人的诉讼可视化工具集:重画诉讼图、读材料画时间轴、庭前三大法宝(大事记表、庭审对抗图、法律关系图),以及法律图表大师与法律课件大师。七个模块,Claude Code、Codex、DeepSeek Harness 等通用。

    Stale GitHub, MiaoQichuan 137 ★AGPL-3.0Updated 19 days ago

    git clone https://github.com/MiaoQichuan/new-litigation-visualization.git
  3. 五个开源文献综述 agent skills:问题提炼、综述模块、方法比较、矛盾梳理、研究空白发现 | Five open agent skills for literature reviews: question refinement, review modules, method comparison, contradiction mapping, research gap discovery

    Stale GitHub, xingtaxueshu 75 ★MITUpdated 14 days ago

    git clone https://github.com/xingtaxueshu/literature-review-skills.git
  4. litgravity

    Skills

    Add one word, `lit`, to an Antigravity CLI (agy) prompt and get a planned, tested, reviewed workflow, plus a handoff note for the next session. Formerly antigravity-swarm.

    Stale GitHub, wjgoarxiv 166 ★MITUpdated 21 days ago

    git clone https://github.com/wjgoarxiv/litgravity.git
  5. Light-Science

    Skills

    A research workflow skill pack connecting literature, experiments, figures, writing, memory and project coordination.

    Stale GitHub, Light0305 882 ★MITUpdated 8 days ago

    git clone https://github.com/Light0305/Light-Science.git
  6. 🤖 The strongest curated list of open-source AI-agent tools for literature review — 70+ tools across 11 categories (Claude Code skills, deep research, MCP servers, PDF parsing, systematic review). 面向智能体文献综述的最强工具大全。

    Stale GitHub, brycewang-stanford 44 ★CC0-1.0Updated 14 days ago

    git clone https://github.com/brycewang-stanford/lit-review-agent-tools.git
  7. Opinionated first-party agent skills, plugins, subagents, slash commands, and MCP servers for the Litestar framework ecosystem — publishable to Claude Code, Gemini CLI, Codex CLI, Cursor, OpenCode, and VS Code/Copilot from a single repo.

    Indexed GitHub, litestar-org 18 ★MITUpdated 3 days ago

    git clone https://github.com/litestar-org/litestar-skills.git
  8. Curated skills, sub-agents, and config templates that supercharge Claude Code — research, image gen, GitHub automation & more.

    Stale GitHub, feiskyer 1,674 ★MITUpdated 11 days ago

    git clone https://github.com/feiskyer/claude-code-settings.git
  9. Use Claude Code like a Director, not a Programmer. MIT toolkit with Auto-Loop, guided setup, 27 commands, 14 agents, and 32 skills.

    Stale GitHub, claude-world 80 ★MITUpdated 26 days ago

    git clone https://github.com/claude-world/director-mode-lite.git
  10. Universal 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.

    Indexed GitHub, WenyuChiou 667 ★MITUpdated today

    git clone https://github.com/WenyuChiou/ai-research-skills.git
  11. ai4s-skills

    Skills

    Open-source agent skills for AI for Science: topic exploration, literature survey, experiments, paper writing, and integrity audit — driven by any coding agent.

    Stale GitHub, ai4s-research 237 ★MITUpdated 3 months ago

    git clone https://github.com/ai4s-research/ai4s-skills.git
  12. ego-jev

    Skills

    ego lite skill — each DOM step decided in ~0.4s, no LLM turn

    Stale GitHub, ZephyrDeng 15 ★MITUpdated 24 days ago

    git clone https://github.com/ZephyrDeng/ego-jev.git
  13. Custom elements catalog for all kind of projects and frameworks.

    Stale GitHub, Polydile 106 ★MITUpdated 28 days ago

    git clone https://github.com/Polydile/dile-components.git
  14. medsci-skills

    Skills

    Agent Skills for medical research — literature search, reporting-guideline & citation checks, statistics, publication figures, submission. Works with Claude Code, Codex, Cursor & GitHub Copilot. Built by a physician-researcher, tested on real publications. MIT.

    Stale GitHub, Aperivue 375 ★MITUpdated 6 days ago

    git clone https://github.com/Aperivue/medsci-skills.git
  15. End-to-end humanities writing assistant — an Agent Skill (open SKILL.md format). 11 modes from Socratic research-question sharpening through AI-use disclosure. Bilingual (EN/中文), discipline-aware (literature/history/philosophy/art/religion/linguistics + cross-disciplinary). Four-layer critique, calibratable devils advocate, voice preservation.

    Stale GitHub, tizzy916 444 ★Custom licence (see repository)Updated 55 days ago

    git clone https://github.com/tizzy916/humanities-writing-companion.git
  16. Handler

    Skills

    A2A protocol client for your terminal

    Stale GitHub, alDuncanson 46 ★GPL-3.0Updated 27 days ago

    git clone https://github.com/alDuncanson/Handler.git
  17. Claude Code skills for academic research support: paper review, bibliography verification, literature surveying, head-to-head paper comparison, and HPC experiment campaigns.

    Indexed GitHub, chgagne 7 ★MITUpdated yesterday

    git clone https://github.com/chgagne/claude-skills-research.git
  18. little-canary

    Skills

    Detects 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.

    Stale GitHub, hermes-labs-ai 39 ★Apache-2.0Updated 27 days ago

    git clone https://github.com/hermes-labs-ai/little-canary.git
  19. 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

    Stale GitHub, kael-odin 203 ★MITUpdated 6 days ago

    git clone https://github.com/kael-odin/awesome-academic-research-skills.git
  20. 250+ 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.

    Stale GitHub, FOURTEEN1416 11 ★Custom licence (see repository)Updated 21 days ago

    git clone https://github.com/FOURTEEN1416/academic-agent-toolkit.git
  21. skills

    Skills

    26 reusable skills for Claude Code, Codex, Hermes and other AI agents — DevOps, SRE, Linux, Docker, LiteLLM, Open WebUI, OpenWrt, Telegram, animated diagrams

    Stale GitHub, nordz0r 7 ★Updated 23 days ago

    git clone https://github.com/nordz0r/skills.git
  22. An 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.

    Stale GitHub, Ar9av 698 ★Custom licence (see repository)Updated 13 days ago

    git clone https://github.com/Ar9av/PaperOrchestra.git
  23. Agent skill for visual, source-grounded paper reading: one standalone HTML atlas of methods, equations, and experiments.

    Stale GitHub, xiaofengShi 11 ★MITUpdated 6 days ago

    git clone https://github.com/xiaofengShi/paper-reading-skill.git
  24. shidi-skill

    Skills

    AI4S 科研 Agent 技能 | AI-for-Science research workflow skill for coding agents: literature review · experiment design · figures · paper reading — files out, cross-verified, zero deps | 文献调研/实验方案/作图/精读,交付文件+交叉验证,零依赖,MIT

    Stale GitHub, IcyCreamDAS 14 ★MITUpdated 19 days ago

    git clone https://github.com/IcyCreamDAS/shidi-skill.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.