InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. 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
  2. Claude Design access and UI workflows for coding agents, part of QualityLayer. Create and review designs in QualityLayer without a Claude subscription, or use the standalone Claude Design connection.

    Stale GitHub, maxritter 40 ★Custom licence (see repository)Updated 21 days ago

    git clone https://github.com/maxritter/open-claude-design.git
  3. ontology-atlas

    MCP servers

    Understand what your codebase builds, why it is structured that way, and what a change could affect. One shared Markdown ontology for humans and coding agents—visualized for people, accessible to agents through MCP, and reviewed with Git. Local-first. Open source.

    Indexed GitHub, wlsdks 161 ★MITUpdated today

    git clone https://github.com/wlsdks/ontology-atlas.git
  4. superpowers

    Skills

    Jesse Vincent's Superpowers skills (brainstorm, plan, TDD, debug, verify, review) adapted for GitHub Copilot agent mode, with project-scoped installers. MIT, adapted from obra/superpowers.

    Stale GitHub, autovant 9 ★MITUpdated 31 days ago

    git clone https://github.com/autovant/superpowers.git
  5. algo-sensei

    Skills

    Your AI-powered LeetCode & DSA mentor for Claude Code and Claude.ai. Master algorithms through intelligent guidance, progressive hints, and pattern recognition training—not just copy-pasting solutions. Features: Mock interviews, code review, multi-language support (Python, Java, C++, JS, Go). Learn to think like a senior engineer. 🥋

    Stale GitHub, karanb192 287 ★MITUpdated 45 days ago

    git clone https://github.com/karanb192/algo-sensei.git
  6. Deepcode

    Public APIs

    AI for code review

    Indexed public-apis (GitHub list)

  7. review-assist-mcp

    MCP servers

    Turns an AI coding agent session into a reviewable Intent Document, validated against the diff.

    Stale Official MCP Registry, io.github.uditk2 Updated 7 days ago 1 note

    review-assist-mcp@1.1.1
  8. Clean-Backend

    Skills

    Claude plugin for production-hardening practices whenever you're designing, writing, or reviewing your backend code. Featuring endpoints, payment flows, deletes, background jobs, and alerting.

    Indexed GitHub, AllanOps 9 ★MITUpdated 5 days ago

    git clone https://github.com/AllanOps/Clean-Backend.git
  9. The agent-host side of the Miadi Factory: Claude Code plugins, host-neutral skills and apt packages for Chronicle episodes, session capture and restore, and witnessed review.

    Stale GitHub, jgwill 5 ★Updated 12 days ago

    git clone https://github.com/jgwill/miadi-orchestration-kit.git
  10. claude-show-your-work

    Agents & frameworks

    Claude Code plugin to see, review and iterate on your agent's work without leaving the terminal: show images, play videos, and run visual QA with Playwright recordings and before/after comparisons inside the Claude Code terminal. Works in any terminal that supports the kitty graphics protocol, fully cross-platform on macOS, Linux and Windows.

    Stale GitHub, iamumeransari 294 ★MITUpdated 12 days ago

    git clone https://github.com/iamumeransari/claude-show-your-work.git
  11. quest

    Skills

    A quest log for your repo and your agents: plans as Markdown files, explicit dependencies, and reviewable Git changes. For Claude Code and Codex.

    Indexed GitHub, moq-dev 7 ★Apache-2.0Updated yesterday

    git clone https://github.com/moq-dev/quest.git
  12. agent-orchestra

    Datasets & benchmarks

    Agents can work. They cannot declare success. A governed coordination protocol for multi-agent AI work: eight contracts (task, resource, ownership, handoff, verification, evidence, approval, recovery) enforced in code, plus a reproducible conformance benchmark. Apache-2.0 code, CC BY 4.0 specification, zero dependencies, Node 18+.

    Stale GitHub, 3338902669-ops 93 ★Apache-2.0Updated 24 days ago

    git clone https://github.com/3338902669-ops/agent-orchestra.git
  13. semantic-scholar-mcp

    MCP servers

    Semantic Scholar MCP server: 14 typed tools for paper search, citation graphs, author profiles, recommendations, PyPI/Docker.

    Stale GitHub, smaniches 25 ★MITUpdated 4 days ago

    git clone https://github.com/smaniches/semantic-scholar-mcp.git
  14. AI가 청중에 맞는 HTML 발표자료와 발표 노트를 만들고 Chromium 기반 시각 검증까지 수행하도록 돕는 스킬·플러그인

    Stale GitHub, NearLegendspirit 69 ★Updated 11 days ago

    git clone https://github.com/NearLegendspirit/build-html-ppt-rpocket-team.git
  15. Panel Review

    MCP servers

    Guardian agent for AI coding: four frontier models review risky diffs and commits before they ship.

    Stale Official MCP Registry, ai.truverif Updated 4 days ago 1 note

  16. Optimized GitHub skill for coding agents: fewer tool calls, less context burned, lower cost, faster answers. One bounded call each for PR state, review threads, and CI failures.

    Stale GitHub, AVGVSTVS96 52 ★MITUpdated 14 days ago

    git clone https://github.com/AVGVSTVS96/better-github-skill.git
  17. OxiMux

    Agents & frameworks

    A Rust-native, multi-agent development cockpit for macOS — spawn isolated worktrees, run CLI coding agents in parallel, and review every change through a GitLens-grade Git UX.

    Indexed GitHub, nhtera 51 ★Apache-2.0Updated today

    git clone https://github.com/nhtera/OxiMux.git
  18. CodeJury

    Agents & frameworks

    Terminal-first, knowledge-grounded multi-agent software delivery pipeline: scope requirements, implement changes, run tests, and gate pull requests with deterministic QA and ensemble code review.

    Stale GitHub, krishagarwal314 148 ★MITUpdated 3 months ago

    git clone https://github.com/krishagarwal314/CodeJury.git
  19. Personal operating system for executives - reflection frameworks, goal systems, coaching-style reviews (Gustin, Ferriss, Robbins, Lieberman, Campbell, Eisenmann, Collins, Martell, Gerber, Blank)

    Stale GitHub, 2389-research 5 ★MITUpdated 14 days ago

    git clone https://github.com/2389-research/ceo-personal-os.git
  20. otelyssey

    Skills

    OpenTelemetry plugins for every coding agent, in the Agent Plugins format — a marketplace that runs itself: open an issue, the repository validates, reviews, lists and follows your plugin.

    Stale GitHub, using-system 92 ★MITUpdated 26 days ago

    git clone https://github.com/using-system/otelyssey.git
  21. claude-skills

    Skills

    Personal Claude Code plugin marketplace: 9 plugins for orchestration guards (workflow-model-guard), tiered deep research (deep-dive), subagent-driven development, ADRs, session retros, handoffs, and adversarial review.

    Stale GitHub, jasonm4130 5 ★MITUpdated 29 days ago

    git clone https://github.com/jasonm4130/claude-skills.git
  22. curie

    Skills

    Open-source, self-hostable platform that turns agents into co-workers. Start with Software Factory: delegate GitHub issues and review pull requests, with model, approval, and cost controls in your infrastructure.

    Indexed GitHub, curie-eng 49 ★Apache-2.0Updated today

    git clone https://github.com/curie-eng/curie.git
  23. agentic-os

    Prompts

    Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.

    Indexed GitHub, KbWen 236 ★MITUpdated 3 days ago

    git clone https://github.com/KbWen/agentic-os.git
  24. qa

    Skills

    Claude Code plugin marketplace of reviewed QA skills and agents: test automation, API, load, security, accessibility, mobile and manual testing.

    Indexed GitHub, testland 13 ★MITUpdated 4 days ago

    git clone https://github.com/testland/qa.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.