InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Sno Station Skills: 39 tested skills that turn Claude Code and Codex into one working team. Review by a different agent, automatic handoff when an agent hits its usage limit, a one-page morning brief, work orders with proof, and a nightly loop that learns from your own sessions. Open source, installed with one sno setup.

    Indexed GitHub, sno-ai 865 ★Apache-2.0Updated yesterday

    git clone https://github.com/sno-ai/sno-station-skills.git
  2. Open-source plugin for designing and reviewing software with agents

    Indexed GitHub, google 20.0k ★Apache-2.0Updated 2 days ago

    git clone https://github.com/google/elephant-goldfish-model.git
  3. One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).

    Indexed GitHub, yzhao062 262 ★Apache-2.0Updated yesterday

    git clone https://github.com/yzhao062/anywhere-agents.git
  4. 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 7 days ago

    git clone https://github.com/kael-odin/awesome-academic-research-skills.git
  5. 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 7 days ago

    git clone https://github.com/Aperivue/medsci-skills.git
  6. Referee report on your economics paper before a real referee sees it — verified comments and a revision plan your agents implement. Agent Skill for Claude Code & Codex.

    Stale GitHub, hanlulong 36 ★Custom licence (see repository)Updated 10 days ago

    git clone https://github.com/hanlulong/econ-paper-review-skill.git
  7. 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 yesterday

    git clone https://github.com/WenyuChiou/ai-research-skills.git
  8. Two Claude Code skills for reading one paper: /paper-review (appraisal with deterministic GRADE and a CrossRef check) and /paper-digest (content digest).

    Indexed GitHub, drpwchen 45 ★MITUpdated 4 days ago

    git clone https://github.com/drpwchen/paper-review-and-digest.git
  9. Standalone skills for Claude Code and Codex: product discovery, architecture, implementation, technical foundations, reviews and delivery, with explicit scope and verification.

    Indexed GitHub, levnikolaevich 596 ★MITUpdated 6 days ago

    git clone https://github.com/levnikolaevich/claude-code-skills.git
  10. reviews

    Skills

    Code review tool for arbitrary diffs

    Indexed GitHub, figitaki 8 ★MITUpdated yesterday

    git clone https://github.com/figitaki/reviews.git
  11. AI-powered contract review skill with CUAD risk detection, market benchmarks, and lawyer-ready redlines. Works with Claude Code, Codex, Cursor, and 26+ tools.

    Stale GitHub, evolsb 469 ★MITUpdated 3 months ago

    git clone https://github.com/evolsb/claude-legal-skill.git
  12. ryugi

    Skills

    Ryugi (ryoo-ghee) — artifacts for coding agents: artboards of mockups, design docs, whiteboards, HTML benches and verify reports you comment on, with every comment sent back to the agent. Install artifacts only, or the full brainstorm → spec → TDD workflow. Claude Code, Codex and more.

    Indexed GitHub, Innei 487 ★Custom licence (see repository)Updated 3 days ago

    git clone https://github.com/Innei/ryugi.git
  13. Light-Science

    Skills

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

    Stale GitHub, Light0305 882 ★MITUpdated 9 days ago

    git clone https://github.com/Light0305/Light-Science.git
  14. cm-workflow

    Skills

    Codex-native, spec-driven AI Agent workflow with Claude Code compatibility, independent review, QA, fixes, and refactors.

    Indexed GitHub, kingxiaozhe 97 ★MITUpdated 2 days ago

    git clone https://github.com/kingxiaozhe/cm-workflow.git
  15. apexyard

    Skills

    Your AI engineering org, governed. Ship agent-built code safely to production.

    Indexed GitHub, me2resh 545 ★MITUpdated yesterday

    git clone https://github.com/me2resh/apexyard.git
  16. Don'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.

    Stale GitHub, wanshuiyin 180 ★MITUpdated 11 days ago

    git clone https://github.com/wanshuiyin/Anti-Autoresearch.git
  17. pstack-claude

    Skills

    Antigravity, Claude Code, Codex, Copilot, Gemini, Muse, OpenCode, Pi, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for other harnesses.

    Indexed GitHub, michael-denyer 4,364 ★MITUpdated 4 days ago

    git clone https://github.com/michael-denyer/pstack-claude.git
  18. squadra

    Skills

    Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.

    Indexed GitHub, dagoSte 1,277 ★MITUpdated 5 days ago

    git clone https://github.com/dagoSte/squadra.git
  19. Production-ready agent skills for engineering, code review, and network tunneling.

    Stale GitHub, dengyie 78 ★Updated 5 days ago

    git clone https://github.com/dengyie/awesome-skills.git
  20. 自媒体视频发布前违规风险审核。检查画面/声音/文字/封面/评论/带货信息/资质/引流,输出 Pass→Blocker 五级风险报告。覆盖抖音/小红书/视频号/B站/快手+千川低质素材。Claude Code、codex、workbuddy、hermes skill

    Stale GitHub, JuneYaooo 101 ★MITUpdated 36 days ago

    git clone https://github.com/JuneYaooo/self-media-compliance-review.git
  21. AI-native SDLC skills for Claude Code: requirement intake & audit, adversarial review gate, AI test orchestration, decision re-check, release config audit

    Stale GitHub, TsCarpe 66 ★MITUpdated 12 days ago

    git clone https://github.com/TsCarpe/claude-sdlc-skills.git
  22. review-squad

    Skills

    Dispatch panels of specialized subagents to review projects — expert audits, first-impression personas, task-completion flows, and pedantic nitpicks

    Stale GitHub, 2389-research 13 ★MITUpdated 15 days ago

    git clone https://github.com/2389-research/review-squad.git
  23. Agent Skills for automating GitHub PR code review workflows

    Stale GitHub, xpepper 6 ★Updated 10 days ago

    git clone https://github.com/xpepper/pr-review-agent-skill.git
  24. AI-powered architecture documentation framework with ADRs, reviews, and pragmatic mode. Now available as Claude Code Plugin for easiest installation.

    Stale GitHub, codenamev 79 ★Updated 10 days ago

    git clone https://github.com/codenamev/ai-software-architect.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.