InnerVault

Library

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

Results

  1. Aletheore

    MCP servers

    Open source (AGPL-3.0) evidence-grounded repository audit CLI - deterministic scanner, MCP server, live dashboard, and a GitHub Action that posts PR diffs.

    Indexed GitHub, Aletheore 483 ★AGPL-3.0Updated today

    git clone https://github.com/Aletheore/Aletheore.git
  2. reviso-agent

    Skills

    Agent skill for Reviso: publish a draft for human review, read reviewer feedback back, and publish a revision without overwriting a concurrent edit.

    Stale GitHub, reviso-si 14 ★Custom licence (see repository)Updated 32 days ago

    git clone https://github.com/reviso-si/reviso-agent.git
  3. AI agent skills and CLI for SAP consultants, developers, and business users to understand ABAP code and business logic. Includes ADT read/write access, code review, transport readiness assessment, and SAP integration guides. Works with Claude Code, Codex, WorkBuddy, OpenCode, and other Agent Skills-compatible tools.

    Stale GitHub, shrek-abaper 45 ★MITUpdated 17 days ago

    git clone https://github.com/shrek-abaper/sap-engineering-skill.git
  4. Upkeep

    Skills

    Upkeep — an AI audit crew for your repo. Catches docs/spec/asset drift with evidence; output-only. Claude Code plugin/skill + reusable CI workflow.

    Indexed GitHub, wei18 17 ★MITUpdated 2 days ago

    git clone https://github.com/wei18/Upkeep.git
  5. CoalMine

    Skills

    Nine quality-canary skills for AI coding agents - code health, world-class rule completeness, grounding, supply chain, resilience, drift & more - plus the auto-cadence hooks that run them unprompted at session start and session end. Cross-agent, consent-gated, token-lean.

    Indexed GitHub, TheColliery 15 ★Apache-2.0Updated yesterday

    git clone https://github.com/TheColliery/CoalMine.git
  6. Agent Skill (html-prototype-build): generate, annotate, review & deliver native HTML prototypes for Claude Code, Cursor & Codex — real-DOM notes, AI-ready selectors, UI packs, multi-state screenshots.

    Stale GitHub, Lisuiwen 26 ★MITUpdated 6 days ago

    git clone https://github.com/Lisuiwen/ai-html-annotation.git
  7. claude-dd

    Skills

    Portable Claude Code profile — 8-step dev loop, CLAUDE.md pre-commit gate, zero-hallucination policy. Install once, carry it to any machine.

    Stale GitHub, kopp0510 12 ★MITUpdated 17 days ago

    git clone https://github.com/kopp0510/claude-dd.git
  8. shadowclone

    Skills

    Your engineering taste, in every coding agent. Shadowclone learns your rules and delivers them as skills to Claude Code, Codex, Cursor, Pi, and Antigravity, and as a GitHub cloud bot.

    Indexed GitHub, theonly1me 26 ★MITUpdated 2 days ago

    git clone https://github.com/theonly1me/shadowclone.git
  9. SOTA-skills

    Skills

    Engineering best practices that AI coding agents actually apply — 40+ skills, from secure coding and cloud to compliance and UX writing. BUILD + AUDIT modes. Measured: best-practice coverage 59% → 98% vs. the same model unguided.

    Indexed GitHub, martinholovsky 28 ★CC-BY-4.0Updated yesterday

    git clone https://github.com/martinholovsky/SOTA-skills.git
  10. open-pstack

    Skills

    Pstack for Codex and Claude Code, with cross-provider routing and automatic failover. Devin, Cursor, Antigravity, OpenCode, and Grok subagents available. All using your own subscriptions.

    Stale GitHub, arjitj2 16 ★MITUpdated 12 days ago

    git clone https://github.com/arjitj2/open-pstack.git
  11. skills

    Skills

    Task skills for coding agents, from Kubernetes to code review. Install only the ones you need.

    Indexed GitHub, iuliandita 12 ★MITUpdated today

    git clone https://github.com/iuliandita/skills.git
  12. mathema

    MCP servers

    Claim-Driven Development: turn software intent into verifiable evidence.

    Stale GitHub, tetrionlabs 169 ★Custom licence (see repository)Updated 5 days ago

    git clone https://github.com/tetrionlabs/mathema.git
  13. Read-only iOS App Store pre-submission check: scans 52 rejection vectors, wraps Apple's fastlane precheck, watches guideline drift, and runs 29 semantic deep-review checks before you submit.

    Stale GitHub, berkayturk 8 ★MITUpdated 30 days ago

    git clone https://github.com/berkayturk/appstore-precheck.git
  14. 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
  15. agent-skills

    Skills

    A curated collection of custom AgentSkills and token-saving MCP servers for extending the capabilities of AI coding assistants like Claude Code.

    Stale GitHub, kambleakash0 10 ★MITUpdated 19 days ago

    git clone https://github.com/kambleakash0/agent-skills.git
  16. ai-prd-workflow

    Prompts

    RFC-driven development for AI coding agents: idea or existing codebase → verified PRD → features → rules → sequenced RFCs → reviewed code. Agent Skills for Claude Code, Codex, Copilot, Cursor, Gemini CLI, OpenCode, Devin.

    Indexed GitHub, nurettincoban 310 ★MITUpdated today

    git clone https://github.com/nurettincoban/ai-prd-workflow.git
  17. Agentic PR reviews for the IBM Carbon Design System, run by IBM Bob or Claude from a codified review prompt and grounded by Carbon MCP. Built on a reusable agent harness for IBM Cloud Code Engine: scheduled, parallel runs, a per-run spend cap, a web console, Elasticsearch telemetry and a Slack digest. A skill adapts it to your repo, job or agent.

    Indexed GitHub, carbon-design-system 34 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/carbon-design-system/Carbon-Monitor.git
  18. genie

    Agents & frameworks

    Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated worktrees, and reviews code before you see it.

    Stale GitHub, automagik-si 352 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/automagik-si/genie.git
  19. framejam

    MCP servers

    Make videos with your coding agent: pick a style, then point at the frame and say what to change. Works with Hyperframes, Remotion or any video tool, over MCP.

    Stale GitHub, moritzkremb 66 ★MITUpdated 18 days ago

    git clone https://github.com/moritzkremb/framejam.git
  20. kaizen

    Skills

    Your AI agent shows you the plan before it does the work, and a second agent checks what it did.

    Indexed GitHub, hfadhlullah 6 ★MITUpdated today

    git clone https://github.com/hfadhlullah/kaizen.git
  21. paper-skill

    Prompts

    🎓 Claude Code skill — AI prompt library for academic paper writing, polishing, reviewing, translating and submitting to SCI/IEEE/Nature/TRO journals

    Stale GitHub, cLin-c 143 ★MITUpdated 7 days ago

    git clone https://github.com/cLin-c/paper-skill.git
  22. acs

    MCP servers

    Local Sovereign Multi-Agent Swarm OS & Cockpit for Autonomous AI Coding Agents. 28 Personas, 45 Core MCP Tools, Sub-10ms Trigram Search, Zero-Console Background Swarm. Official: https://uikode.com/acs

    Stale GitHub, andyvandaric 21 ★Updated 7 days ago

    git clone https://github.com/andyvandaric/acs.git
  23. contrarian

    Skills

    Devil's advocate for coding agents. Stress-tests plans, architecture and decisions with a steel-man, an assumption audit and a pre-mortem, then gives severity-rated findings and a verdict. Works in Claude Code, Codex, Cursor, Gemini CLI, Copilot and 12 more.

    Stale GitHub, aaddrick 40 ★UnlicenseUpdated 40 days ago

    git clone https://github.com/aaddrick/contrarian.git
  24. SpecForge

    MCP servers

    Specs your AI agent can't ignore. A deterministic compiler that turns your rules into checks: no AI inside, same input, same verdict. Rust · MCP-native · works with Claude Code, Cursor and any MCP agent.

    Stale GitHub, leaderiop 42 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/leaderiop/SpecForge.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.