InnerVault

Library

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

Results

  1. Claude Skill that turns lecture transcripts and readings into linked Obsidian notes, adaptive flashcards, and a gap tracker.

    Stale GitHub, OnePathToFreedom 35 ★MITUpdated 28 days ago

    git clone https://github.com/OnePathToFreedom/smart-notes-skill.git
  2. Agent skills that make AI coding assistants write production-grade robotics software. ROS1, ROS2, design patterns, SOLID principles, and testing — for Claude Code, Cursor, Copilot, and any SKILL.md-compatible agent.

    Stale GitHub, arpitg1304 374 ★Apache-2.0Updated 3 months ago

    git clone https://github.com/arpitg1304/robotics-agent-skills.git
  3. marketplace

    Skills

    Skills and plugins from https://daily.dev/marketplace made by daily.dev community.

    Stale GitHub, dailydotdev 8 ★Updated 6 days ago

    git clone https://github.com/dailydotdev/marketplace.git
  4. 🧠 Powerful, tested skills for Claude. Featuring CertMaster OS: turn PDFs, syllabi and lecture transcripts into Obsidian/Notion study notes with quizzes and anti-hallucination guardrails.

    Stale GitHub, HackBepa 16 ★MITUpdated 19 days ago

    git clone https://github.com/HackBepa/claude-skills-hub.git
  5. Replace with description of the skill and when Claude should use it.

    Indexed Agent skill collections on GitHub, anthropics 1 note

    /plugin marketplace add anthropics/skills
  6. Use when executing implementation plans with independent tasks in the current session

    Stale Agent skill collections on GitHub, obra MIT1 note

  7. Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

    Stale Agent skill collections on GitHub, obra MIT1 note

  8. handoff

    Skills

    Compact the current conversation into a handoff document for another agent to pick up.

    Indexed Agent skill collections on GitHub, mattpocock MIT1 note

  9. skill3

    Skills

    Skill3 is a lightweight Java CLI that relearns a technical skill for an AI agent. It discovers documentation sources, scores them for authority and freshness (anchored to a target model's knowledge cutoff), synthesizes them with a local LLM into an Agent Skills SKILL.md, and vets the result with NVIDIA's SkillSpector.

    Indexed GitHub, PIsberg 6 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/PIsberg/skill3.git
  10. ai-rulez

    Skills

    Author, generate, validate and govern AI agent rules, skills, plugins and MCP configuration across 52 coding assistants. Review with verified model evidence, evaluate skills, lock and sign dependencies, and publish bundles. CLI, MCP server and Go API.

    Indexed GitHub, Goldziher 172 ★MITUpdated yesterday

    git clone https://github.com/Goldziher/ai-rulez.git
  11. Use when creating new skills, editing existing skills, or verifying skills work before deployment

    Stale Agent skill collections on GitHub, obra MIT1 note

  12. Pursue a long-running goal in a single session by co-ordinating subagents.

    Indexed Agent skill collections on GitHub, mattpocock MIT1 note

  13. loop-me

    Skills

    Grill me about specs for the workflows I want to build, within this workspace.

    Indexed Agent skill collections on GitHub, mattpocock MIT1 note

  14. The complete Claude Code setup: 94 skills, 9 plugins, working rules (CLAUDE.md) and a guide to 14 connectors. Open it in Claude Code and say "install this".

    Indexed GitHub, mppyxx 5 ★Custom licence (see repository)Updated 7 days ago

    git clone https://github.com/mppyxx/claude-power-pack.git
  15. Scaffolding skill + always-on conventions (CLAUDE.md/AGENTS.md) for Quarkus + LangChain4j agentic AI apps: AI services, multi-agent workflows, and RAG. Installable in Claude Code, Codex, Copilot, Cursor, and any Agent Skills-compatible agent.

    Indexed GitHub, eldermoraes 27 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/eldermoraes/quarkus-agentic-scaffolding.git
  16. Migrate supported instruction files, skills, agents, and MCP config into Codex project and global files.

    Stale Agent skill collections on GitHub, openai 1 note

    $skill-installer <skill-name>
  17. UbD 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

    Stale GitHub, cabbage2000-lab 36 ★MITUpdated 29 days ago

    git clone https://github.com/cabbage2000-lab/textbook-writer-skills.git
  18. A Claude skill that generates a detailed, structured session archive in markdown for long-term logging and cross-session handoff.

    Indexed GitHub, thebpandey 6 ★MITUpdated 4 days ago

    git clone https://github.com/thebpandey/session-detail.git
  19. 수노(Suno)용 한국어 작사 Claude 에이전트 스킬 — 가사와 Style·Exclude·Title을 장르에 맞춰 함께 설계 (v3.1, CC BY 4.0) · Korean lyric-writing Agent Skill (SKILL.md) for Suno

    Stale GitHub, previtlab 5 ★CC-BY-4.0Updated 15 days ago

    git clone https://github.com/previtlab/suno-lyrics-skill.git
  20. Use when completing tasks, implementing major features, or before merging to verify work meets requirements

    Stale Agent skill collections on GitHub, obra MIT1 note

  21. writing-plans

    Skills

    Use when you have a spec or requirements for a multi-step task, before touching code

    Stale Agent skill collections on GitHub, obra MIT1 note

  22. ask-matt

    Skills

    Ask which skill or flow fits your situation. A router over the skills in this repo.

    Indexed Agent skill collections on GitHub, mattpocock MIT1 note

  23. Hand the current conversation off to a fresh background agent that picks up the work immediately.

    Indexed Agent skill collections on GitHub, mattpocock MIT1 note

  24. 呼波特 WhoBot 官方 AI 电话数字员工 Skill:在 WorkBuddy / Claude Code / Codex / OpenClaw / Cursor 里挑选、体验、创建和调优会打真实电话的 AI 员工,上传线索外呼 | Official WhoBot agent skill for AI phone agents (voice agents)

    Indexed GitHub, whobot-com 119 ★MITUpdated 2 days ago

    git clone https://github.com/whobot-com/openclaw-whobot-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.