InnerVault

Library

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

Results

  1. skill-harness

    Skills

    How do you KNOW if a 'skill' is any good - deterministically? This runs controlled skill-vs-no-skill experiments. It doesn't just ask, “Did the skill work?” It asks “Did we actually give the skill to the model, did the comparison remain fair, what changed, what did it cost, and do we have enough evidence to say that confidently?”

    Stale GitHub, MrBinnacle 16 ★MITUpdated 15 days ago

    git clone https://github.com/MrBinnacle/skill-harness.git
  2. researchforge

    Skills

    A lab protocol for coding agents. Freeze baselines, run hypotheses in isolated worktrees, reject failures and validate improvements from Claude Code, Cursor or a direct API key (Gemini/Anthropic/openAI).

    Indexed GitHub, forger-labs-hq 9 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/forger-labs-hq/researchforge.git
  3. ServerFS_MCP

    Skills

    Secure, scoped filesystem MCP server for ChatGPT and other MCP clients — read-only by default, with controlled mutations, binary transfer, native Codex/Claude/Qoder runtimes, generic ACP v1 profiles, and Agent Skills.

    Stale GitHub, NTLx 6 ★MITUpdated 7 days ago

    git clone https://github.com/NTLx/ServerFS_MCP.git
  4. agent-flow

    Skills

    Guardrails for AI coding agents: run Claude Code, Codex, Gemini CLI, Cursor or Copilot unattended and come back to a reviewed pull request. Implement, review and QA agents, a guard on protected paths, and a tamper-evident audit log.

    Stale GitHub, Drix10 12 ★MITUpdated 6 days ago

    git clone https://github.com/Drix10/agent-flow.git
  5. grimoire

    Skills

    Package manager for AI-agent config. grim installs, updates, and publishes skills, rules, agents, MCP servers, and bundles into Claude Code, Copilot, Cursor, Codex, Gemini, Zed, Amp, Kiro, Junie, and opencode — pinned by digest in a lockfile. Storage is any OCI registry; there is no service to run.

    Stale GitHub, grimoire-rs 14 ★Apache-2.0Updated 25 days ago

    git clone https://github.com/grimoire-rs/grimoire.git
  6. model-citizen

    Skills

    The control plane for your coding agents, however you run them. One checkout of rules, skills, subagents, hooks and stances, projected into Claude Code and Codex with your own primitives: hook-enforced guardrails, usage telemetry, cost postures and model tiering, under any rules library or orchestration layer.

    Stale GitHub, JakeSelby 24 ★MITUpdated 33 days ago

    git clone https://github.com/JakeSelby/model-citizen.git
  7. Fixes the AI reviewer findings on your PR, including the sibling instances the bot missed. Runs your tests before it pushes. Hard capped at 3 rounds. Claude Code and Codex.

    Stale GitHub, OrenAshkenazy 7 ★MITUpdated 31 days ago

    git clone https://github.com/OrenAshkenazy/gh-review-loop.git
  8. Nineteen Claude Code plugins I run every day across a Python backend, a React web app, a SwiftUI client and an ML pipeline: SDLC and ML skills, per-stack reviewer subagents, blocking safety hooks, content and SEO agents, LSP and monitors. One marketplace instead of a copy per repo.

    Indexed GitHub, kulykivska 6 ★MITUpdated 4 days ago

    git clone https://github.com/kulykivska/claude-plugins.git
  9. Skip to production. The open-source (Apache-2.0) production layer for agent-built software — auth, global + China billing, multi-tenancy and an AI gateway in one command, running locally with zero keys.

    Stale GitHub, Nebutra 5 ★Apache-2.0Updated 19 days ago

    git clone https://github.com/Nebutra/Nebutra-Sailor.git
  10. From task to done. One open source workflow of 18 modules for AI coding agents that runs the AI-native SDLC: plan, design, build, test, deploy, maintain, with evidence in every handoff. Free, MIT.

    Indexed GitHub, nobrainer-tech 7 ★MITUpdated 4 days ago

    git clone https://github.com/nobrainer-tech/nobrainer-tech-flow.git
  11. Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

    Indexed Agent skill collections on GitHub, mattpocock MIT1 note

  12. Living Docs — a AI agent skill that runs your project's documentation as a living system: constitution, ADRs, BDRs, PRDs, issues, research notes & Mermaid architecture diagrams under five no-drift governance invariants. OKF-formatted, stack-agnostic. Works with Claude Code, Cursor, Copilot, OpenCode & Pi.

    Indexed GitHub, ejklock 14 ★Custom licence (see repository)Updated 3 days ago

    git clone https://github.com/ejklock/living-docs-skill.git
  13. An AI agent system on Claude Code that runs your whole job search: finds and scores roles, creates and tailors your resume for every role, finds who to message on LinkedIn, and reminds you to follow up.

    Indexed GitHub, aranculleton 7 ★MITUpdated 5 days ago

    git clone https://github.com/aranculleton/last-job-search.git
  14. Supercharge BMAD with Claude Code Goal Mode, Auto Mode, and Auto Memory. Transform Epics into autonomous run-until-done workflows that plan, implement, test, validate, document, and continuously learn from project knowledge to accelerate software delivery.

    Stale GitHub, armelhbobdad 5 ★Custom licence (see repository)Updated 13 days ago

    git clone https://github.com/armelhbobdad/bmad-module-ultracode-goal.git
  15. Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

    Stale Agent skill collections on GitHub, obra MIT1 note

  16. JevFlow

    Skills

    A Claude Code plugin that keeps your AI agents honest. Claude plans tasks as phases with checks, and when it tries to stop, Jevflow runs them and asks Jev if the work is really done. Many agents, one plan, with a live viewer to watch it all.

    Stale GitHub, Parth1811 12 ★MITUpdated 23 days ago

    git clone https://github.com/Parth1811/JevFlow.git
  17. Forge of Thought is an AI cognitive extension: a workshop where your idea is forged into a decision you can stand behind. You and the AI elicit the idea together until it is whole, reviewers that never saw the conversation attack it, and who decided what and why is recorded. Runs in Claude Code.

    Indexed GitHub, pche-broken-artist 14 ★CC-BY-4.0Updated 2 days ago

    git clone https://github.com/pche-broken-artist/forge-of-thought.git
  18. An open registry of 76 fully specified AI agent skills — taxonomy, canonical schema, composer, governance model, and a fleet runner that deploys hundreds of agents against one objective and rehearses them against their own definitions.

    Stale GitHub, jersonboydmilan 6 ★MITUpdated 15 days ago

    git clone https://github.com/jersonboydmilan/Agent-Skills-Compendium.git
  19. ducpt-skills

    Skills

    14 open source Agent Skills (SKILL.md) for one-person companies run with AI: Vietnamese transcripts, copy and voice dictation fixes, Pinterest pins, YouTube titles, mind maps, duplicate cleanup, content originality check, token cost tracking, GitHub repo SEO, 7 day AI kickstart, skill distribution. By ducpt.com

    Indexed GitHub, ducdg88 8 ★MITUpdated yesterday

    git clone https://github.com/ducdg88/ducpt-skills.git
  20. Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.

    Stale Agent skill collections on GitHub, openai 1 note

    $skill-installer <skill-name>
  21. trajecktory

    Skills

    Run your entire job search from one local, AI-powered dashboard: find the roles worth your time, tailor for each, work the right people, and keep every follow-up alive. Open source, your data stays yours.

    Stale GitHub, michaelinghilterra-creator 5 ★MITUpdated 8 days ago

    git clone https://github.com/michaelinghilterra-creator/trajecktory.git
  22. quiver

    Skills

    Development workflow plugin for Claude Code, Codex, Cursor and OpenCode. Skills and agents to brainstorm a spec, plan tasks, build in parallel git worktrees, run a multi-agent code review that checks each finding against the code, debug from hypotheses, write commits and PRs, build UI from Figma, and hand over between sessions.

    Stale GitHub, yagizdo 16 ★MITUpdated 7 days ago

    git clone https://github.com/yagizdo/quiver.git
  23. Claude Code skill for AI image & video generation with Google Gemini — Nano Banana 2 Lite, Nano Banana Pro, Gemini Omni Flash. Cost gates before paid runs, real reference images, a prompt log beside every file.

    Stale GitHub, AntonioCardenas 6 ★Custom licence (see repository)Updated 14 days ago

    git clone https://github.com/AntonioCardenas/generate-nanobanana.git
  24. aizee

    Skills

    The policy layer for AI coding agents. aiZee governs what Cursor, Claude Code, Copilot, Windsurf, Devin & MCP agents may do — 139 enforcement gates, 29 personas, 245 skills, BMAD runtime, hybrid memory, tamper-evident audit. pip install aizee

    Indexed GitHub, m3taz-ahmed 6 ★MITUpdated 2 days ago

    git clone https://github.com/m3taz-ahmed/aizee.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.