InnerVault

Library

86,219 resources from 11 public sources. 46 checked by hand; the rest are unreviewed.

Results

4,326 results Clear search and filters
  1. ailmanac

    Skills

    Claude has never seen 68% of the Claude Code docs: research, interactive charts and a plugin that tells it what it missed. Plus a field guide to Claude and AI tools that says when each page was last checked, in 12 languages.

    Stale GitHub, derob98 8 ★Custom licence (see repository)Updated 5 days ago

    git clone https://github.com/derob98/ailmanac.git
  2. 黑客松从报名到领奖的工程脚手架:一张路线图看完 19 份详规 + 42 个模板 + 7 份填好的示例,丢给 Claude Code / Codex 就能开工。四道门、F 点冻结、评分表赛后才给怎么救、多 Agent 靠文件接力——零基础也能从 0 到 1,打完复盘成下一场的资产。

    Stale GitHub, fqyy360t 16 ★Updated 17 days ago

    git clone https://github.com/fqyy360t/hackathon-flow.git
  3. swarm-factory

    Agents & frameworks

    Top Autonomous Research Multi-Agent System for 2026 Lab Experiments

    Indexed GitHub, Usaid22 90 ★Updated today

    git clone https://github.com/Usaid22/swarm-factory.git
  4. Resumable completion protocol for coding agents: obligations live in a durable task record, completion is computed by a validator, and a Stop hook routes execution back to unfinished work.

    Stale GitHub, PyModel 5 ★MITUpdated 28 days ago

    git clone https://github.com/PyModel/done-means-done.git
  5. people-context

    MCP servers

    Local-first memory for AI agents about the people in your life. MCP server + CLI on SQLite. Never phones home.

    Stale GitHub, JinyangWang27 60 ★MITUpdated 4 days ago

    git clone https://github.com/JinyangWang27/people-context.git
  6. 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 2 days ago

    git clone https://github.com/chgagne/claude-skills-research.git
  7. skillet

    Skills

    A skillet full of agent skills that actually ship work. Production-tested SKILL.md workflows for audits, security, releases, and handoffs.

    Stale GitHub, escoffier-labs 5 ★MITUpdated 13 days ago

    git clone https://github.com/escoffier-labs/skillet.git
  8. Names the harness piece behind each problem in your sessions, what it cost, and whether the fix worked.

    Stale GitHub, guilhermebkel 5 ★MITUpdated 11 days ago

    git clone https://github.com/guilhermebkel/harness-ledger.git
  9. ArcRift

    Tools & apps

    Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats (Claude, ChatGPT, DeepSeek) straight to your local IDE agents (Cursor, Claude Code, Windsurf) powered by a local SQLite knowledge graph.

    Stale GitHub, Eshaan-Nair 246 ★MITUpdated 4 months ago

    git clone https://github.com/Eshaan-Nair/ArcRift.git
  10. Skills

    Skills

    Agent Skills for AceDataCloud AI services — music, image, video generation, web search, and more. Compatible with Claude Code, GitHub Copilot, Gemini CLI, and all agentskills.io-compatible agents.

    Indexed GitHub, AceDataCloud 17 ★Custom licence (see repository)Updated today

    git clone https://github.com/AceDataCloud/Skills.git
  11. forge-skills

    Skills

    The Forge Skills Plugin bundles several Forge-focused skills plus MCP-backed tooling so your agent can scaffold apps, review them before deploy, debug production issues, and stay current on Forge APIs and the Atlassian Design System.

    Stale GitHub, atlassian 31 ★Apache-2.0Updated 8 days ago

    git clone https://github.com/atlassian/forge-skills.git
  12. Local AVE timeline editing and exports for Claude Code only. Existing AVE connection required.

    Stale Official MCP Registry, io.github.lemberalla Updated 14 days ago 1 note

    https://github.com/lemberalla/tinythings-mcp-connectors/releases/download/v0.1.3/ave-claude-code-0.1.3.mcpb
  13. possible

    Skills

    See what AI made and the recipe behind it: exact prompts, skills, tools and steps. Search recipes, capture your own Claude Code or Codex session, publish from your repo.

    Stale GitHub, fraylabs 11 ★MITUpdated 5 days ago

    git clone https://github.com/fraylabs/possible.git
  14. gccli

    Skills

    A command-line interface for Garmin Connect - activities, health, workouts, devices, and more - with JSON output, secure credential storage, and a bundled agent skill for AI assistants like Claude Code, Codex, Hermes, and OpenClaw.

    Stale GitHub, bpauli 31 ★MITUpdated 19 days ago

    git clone https://github.com/bpauli/gccli.git
  15. Claude-Abo

    Skills

    Portable Claude Code setup template: 66 skills with provenance, cost-aware model routing, git safety hooks. Adapt, don't run as-is.

    Stale GitHub, Bank848 6 ★Custom licence (see repository)Updated 8 days ago

    git clone https://github.com/Bank848/Claude-Abo.git
  16. MCP Server for Tree-sitter

    Stale Archived GitHub, wrale 309 ★MITUpdated 6 months ago 1 note

    git clone https://github.com/wrale/mcp-server-tree-sitter.git
  17. seo-skills

    Skills

    Free, open-source Shopify SEO audit for Claude Code, Codex and Cursor. Check any store or site from its URL: what Google and AI crawlers can read, and what to fix first. No app, no API keys.

    Indexed GitHub, JittoJoseph 7 ★MITUpdated yesterday

    git clone https://github.com/JittoJoseph/seo-skills.git
  18. domscribe

    Tools & apps

    Domscribe is a pixel-to-code development tool that bridges the gap between running web applications and their source code.

    Indexed GitHub, patchorbit 194 ★MITUpdated today

    git clone https://github.com/patchorbit/domscribe.git
  19. beyondseo

    Skills

    Your AI SEO house. Audit your website, write useful content, compare competitors and plan backlinks inside your AI assistant. Free and open source.

    Stale GitHub, beyondtahir 251 ★MITUpdated 13 days ago

    git clone https://github.com/beyondtahir/beyondseo.git
  20. Multi-tier framework for evaluating AI agent skills and plugins with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

    Indexed GitHub, NVIDIA 3,025 ★Apache-2.0Updated today

    git clone https://github.com/NVIDIA/SkillEvaluator.git
  21. A curated, CI-checked list of Agent Skills (SKILL.md) for Claude Code, Codex, Cursor, Gemini CLI and Copilot

    Stale GitHub, Sagargupta16 5 ★CC0-1.0Updated 4 days ago

    git clone https://github.com/Sagargupta16/awesome-skills.git
  22. engramory

    Prompts

    Agent 通用长期记忆层:Agent 将重要信息按类型记录为多篇可读的 markdown 记忆文档,文档以链接形式列在限长索引中,索引随会话自动注入。DeepSeek Harness(dsh)有专用插件 dsh-engramory。

    Indexed GitHub, tinqiao-oss 207 ★MITUpdated 2 days ago

    git clone https://github.com/tinqiao-oss/engramory.git
  23. smithers

    Agents & frameworks

    Smithers is an agentic workflow framework for defining workflows in simple TypeScript configuration files and executing them quickly, durably, and reliably

    Indexed GitHub, smithersai 449 ★MITUpdated today

    git clone https://github.com/smithersai/smithers.git
  24. OhMyBuddy

    Agents & frameworks

    Self-hosted, self-improving AI buddy with visible memory: personal AI agent + Pi coding-agent workspace for any browser, phone. 自托管私人 AI 助理:记得你,能办事,自进化,可接入微信。

    Stale GitHub, YogurtJ 82 ★ISCUpdated 5 days ago

    git clone https://github.com/YogurtJ/OhMyBuddy.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.