InnerVault

Library

85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Agent skill: examine a product you're authorised to rebuild, build your own, then test against the original and fix gaps until every must-have on a written checklist passes. Inspired by REA (@morluto), not affiliated. MIT.

    Stale GitHub, Speedrunlab 23 ★MITUpdated 23 days ago

    git clone https://github.com/Speedrunlab/reverse-engineer-anything-self-learning-loop.git
  2. Zero-LLM deterministic jailbreak regression benchmark: runs a repeatable battery of known-pattern attacks against an LLM endpoint and scores refusal/partial/compliance across runs. Catch when a model or prompt update silently got weaker. Single-turn, responsible-use. pip install hermes-jailbench

    Stale GitHub, hermes-labs-ai 12 ★Apache-2.0Updated 28 days ago

    git clone https://github.com/hermes-labs-ai/hermes-jailbench.git
  3. Comprehensive YouTube channel analysis: researches background, creates data visualizations, and generates execution plans.

    Stale GitHub, Alpha-Park 8 ★MITUpdated 17 days ago

    git clone https://github.com/Alpha-Park/openclaw-genpark-channel-auditor.git
  4. SkillSafe

    Skills

    SkillSafe: portable evidence-linked knowledge vault for AI agents, with a local Python engine, reviewed writes, source anchors and Markdown/OKF exports.

    Indexed GitHub, GodModeAI2025 6 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/GodModeAI2025/SkillSafe.git
  5. A skill for strict scope control, explicit user approval, and final compliance checks.

    Indexed GitHub, TulossSolutions 5 ★Updated 4 days ago

    git clone https://github.com/TulossSolutions/anti-gold-plating.git
  6. AI Research Writing Skill (AI论文写作技能) is an agent skill for ML / AI / CV / NLP researchers. Point your coding agent at code, experiment logs, notes, and a venue template; it helps you produce an auditable, evidence-backed LaTeX draft and submission package — not a polished fiction.

    Stale GitHub, jin-s13 52 ★MITUpdated 30 days ago

    git clone https://github.com/jin-s13/ai-research-writing-skill.git
  7. arc

    Skills

    Architecture diagrams as code — typed JSON schema, React renderer, visual editor, Mermaid import, ASCII/SVG/PNG export, CLI + MCP server

    Indexed GitHub, hudsonkit 17 ★MITUpdated yesterday

    git clone https://github.com/hudsonkit/arc.git
  8. kitbash

    Skills

    Tells your AI agent which parts of your idea already exist on GitHub, which to adapt, and which to just write — every repo verified live. MCP server, Claude Code plugin, and agent skill.

    Stale GitHub, Open-Dev-Society 51 ★GPL-2.0Updated 25 days ago

    git clone https://github.com/Open-Dev-Society/kitbash.git
  9. Automatically filters and aggregates AI news, extracts article data, and produces actionable commercial intelligence.

    Stale GitHub, Alpha-Park 8 ★MITUpdated 17 days ago

    git clone https://github.com/Alpha-Park/openclaw-genpark-signal-aggregator.git
  10. priors

    Skills

    On-chain credit pool for ERC-8004 AI agents on Robinhood Chain: agents borrow USDG, repay it and earn a public credit score. Contracts, SDK, CLI, MCP server (@priors/mcp), x402 helpers (@priors/x402) and an agent skill.

    Indexed GitHub, priors-agents 7 ★MITUpdated 3 days ago

    git clone https://github.com/priors-agents/priors.git
  11. ⚡ Drop-in SKILL.md, .cursorrules, CLAUDE.md, AGENTS.md & Remote MCP (.mcp.json) pack for Claude Code, Cursor, Windsurf, Cline & x402 AI Agents — Verify GitHub Bounties & Mine DOOM/wDOOM on Base Mainnet.

    Stale GitHub, doomsday-network 7 ★Updated 23 days ago

    git clone https://github.com/doomsday-network/web3-agent-skills.git
  12. zymtrace skills. Detect and optimize GPU and CPU workload bottlenecks with zymtrace continuous profiling-analyze flamegraphs through the MCP, plus install, upgrade, expose, and troubleshoot the platform.

    Stale GitHub, zystem-io 5 ★Apache-2.0Updated 17 days ago

    git clone https://github.com/zystem-io/zymtrace-skills.git
  13. Agent skills for managing multi-step tasks as GitHub issues. Create, implement, update, and close execution plans that survive across sessions.

    Indexed GitHub, gjoranv 5 ★MITUpdated 2 days ago

    git clone https://github.com/gjoranv/claude-plan-skills.git
  14. Agentic OS Control Plane: deterministic state-machine governance for AI coding agents with cryptographically enforced SSH/CIBA human-in-the-loop gates and zero-trust verification.

    Stale GitHub, richfrem 7 ★MITUpdated 14 days ago

    git clone https://github.com/richfrem/agent-plugins-skills.git
  15. valcraft

    Skills

    Agent skills for spec-driven development. An automated agentic delivery loop coordinates planning, implementation, and cross-agent code reviews. Requirements, plans, and decisions live in ordinary project files with project-wide IDs linked from commits and PRs, reducing manual handoffs and repeated explanations while keeping session context small.

    Stale GitHub, valzav 22 ★MITUpdated 23 days ago

    git clone https://github.com/valzav/valcraft.git
  16. Free image reading & generation for DeepSeek Harness (rc.7 / rc.8 / v0.1.1-rc.1 / rc.2 / v0.1.2-alpha.3) — paste-image reading with auto vision transcription, DeepSeek-V4-Flash-Vision-Exp / GLM-4V-Flash / SenseNova / Gemini failover, Kolors + U1 Fast generation. No keys in repo.

    Stale GitHub, MJorgin 25 ★MITUpdated 15 days ago

    git clone https://github.com/MJorgin/dsh-media-skills.git
  17. Excel & PPT to interactive HTML: presentations, analysis, charts, slicers and video-like motion. Agent skill for Claude Code and Codex.

    Stale GitHub, Chris-yoo80 5 ★Custom licence (see repository)Updated 24 days ago

    git clone https://github.com/Chris-yoo80/ppt-to-html-agent.git
  18. orrery

    Skills

    Animated architecture and system design diagrams with official AWS, Azure, Google Cloud, Kubernetes, GitHub and IBM icons. YAML in; SVG, PNG, draw.io, React TSX and HTML out. An Agent Skill, Claude Code plugin and npm CLI. Gallery: sagargupta.online/orrery

    Stale GitHub, Sagargupta16 6 ★MITUpdated 7 days ago

    git clone https://github.com/Sagargupta16/orrery.git
  19. A Claude.ai Personal Skill that generates a structured, seven-block session handoff so you can continue work in a new conversation without losing context, rediscovering decisions, or re-explaining your project state.

    Indexed GitHub, thebpandey 14 ★MITUpdated 4 days ago

    git clone https://github.com/thebpandey/context-summary.git
  20. SAMOSA

    Skills

    A step auditor for matrix algebra, stochastics and algebra. Checks every step of a derivation, exactly, over finite fields.

    Stale GitHub, Hussain004 6 ★MITUpdated 7 days ago

    git clone https://github.com/Hussain004/SAMOSA.git
  21. AI music generator agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: turn a theme, lyrics, scene, or reference audio into songs, instrumentals, BGM, and soundtracks you can review and revise. AI音乐生成 · AI写歌

    Indexed GitHub, beatra-ai 5 ★MIT-0Updated 3 days ago

    git clone https://github.com/beatra-ai/ai-music-generator-skill.git
  22. Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

    Stale Agent skill collections on GitHub, obra MIT1 note

  23. gh-fix-ci

    Skills

    Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

    Stale Agent skill collections on GitHub, openai 1 note

    $skill-installer <skill-name>
  24. 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 15 days ago

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