InnerVault

Library

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

Results

  1. Evergreen, generally useful Codex skills designed to stay valuable as models improve.

    Stale GitHub, Kbediako 5 ★MITUpdated 32 days ago

    git clone https://github.com/Kbediako/evergreen-codex-skills.git
  2. acumen

    Skills

    A toolkit to test, validate, and improve agentic skills for python packages.

    Indexed GitHub, scverse 20 ★MITUpdated 5 days ago

    git clone https://github.com/scverse/acumen.git
  3. rashomon

    Skills

    Measure prompt and skill improvements with blind A/B comparison.

    Stale GitHub, shinpr 19 ★MITUpdated 26 days ago

    git clone https://github.com/shinpr/rashomon.git
  4. synthadoc

    Skills

    Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.

    Indexed GitHub, axoviq-ai 2,029 ★AGPL-3.0Updated 3 days ago

    git clone https://github.com/axoviq-ai/synthadoc.git
  5. Free home renovation tools: paint & tile calculators, room planner, document generators and design resources for DIY | Darmowe kalkulatory remontowe, planer pomieszczeń i generatory dokumentów

    Stale GitHub, eater2 11 ★MITUpdated 8 days ago

    git clone https://github.com/eater2/homerenovationfreetools.git
  6. rundesk-cli

    Skills

    Persistent proactive self-improving AI teammates with memory, skills, and schedules.

    Stale GitHub, rundesk-ai 6 ★MITUpdated 26 days ago

    git clone https://github.com/rundesk-ai/rundesk-cli.git
  7. Build evals from traces, code, and coding sessions, then measure and improve AI agent behavior, including your coding agents

    Indexed GitHub, relai-ai 14 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/relai-ai/agent-eval-loop.git
  8. recall

    Skills

    A self-improving memory layer for Claude Code: captures every session, distills them nightly into a versioned knowledge vault, and surfaces that knowledge back into new sessions — plus proposes skills from recurring patterns.

    Stale GitHub, maxdmyers 18 ★Updated 29 days ago

    git clone https://github.com/maxdmyers/recall.git
  9. LLM-driven evolution of prompts and pipelines. Evolves the prompt and the pipeline's parameters together against your labeled data, cuts losing candidates early, and shows every measurement behind the winner. Open source.

    Indexed GitHub, PromptPotter 7 ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/PromptPotter/prompt-potter-optimizer.git
  10. 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
  11. A small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.

    Indexed GitHub, Sanexxxx777 16 ★MITUpdated yesterday

    git clone https://github.com/Sanexxxx777/curated-claude-code.git
  12. Claude Code skill that optimizes Android phones over ADB and Fastboot. It asks how far to go first, from reversible tweaks to custom ROMs, root and overclocking. It can also scan and improve the camera and set up a PS1 emulator.

    Stale GitHub, cavaleiro-ai 33 ★MITUpdated 13 days ago

    git clone https://github.com/cavaleiro-ai/android-optimizer.git
  13. Practical AI guides, coding-agent skills, playbooks and tools for solo builders making products and content. Contribute a workflow or improve an existing guide.

    Indexed GitHub, yerdaulet-damir 50 ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/yerdaulet-damir/awesome-solo-ai.git
  14. Based on Anthropic's skill-creator — with bug fixes, working Cowork support, and official best practices baked in. Claude skill for creating, testing, and improving other Claude skills.

    Stale GitHub, yaniv-golan 7 ★MITUpdated 5 days ago

    git clone https://github.com/yaniv-golan/skill-creator-plus.git
  15. oddyssey

    Skills

    CLI toolbox for Observability-Driven Development (ODD): coding agents observe local runs on an OpenTelemetry/Grafana stack - or remote ones on any OpenTelemetry backend - and feed the next spec-driven improvement loop.

    Stale GitHub, using-system 10 ★MITUpdated 27 days ago

    git clone https://github.com/using-system/oddyssey.git
  16. claude-skill

    Skills

    🔍 Enhance code searches with ast-grep, finding patterns in your code structure for improved error handling and analysis.

    Stale GitHub, Kayunangka 5 ★Updated 36 days ago

    git clone https://github.com/Kayunangka/claude-skill.git
  17. Free open-source Claude Code kit: 22 AI agents (17 + 5 UEFN MCP sub-agents), 34 skills and 387 proven UEFN MCP recipes to build, test and improve Fortnite maps (Verse, Niagara, UI)

    Indexed GitHub, mimmo-the-root 18 ★MITUpdated 2 days ago

    git clone https://github.com/mimmo-the-root/UEFN-dream-bot-team.git
  18. Vitrine

    Skills

    Vitrine is an open-soruce UI component library, with more than 500 components, we have ready-made portfolio-temapltes and more than 15 skills for your agents to improve your website. Made for people who want to be unique.

    Indexed GitHub, ham7a311 11 ★MITUpdated 3 days ago

    git clone https://github.com/ham7a311/Vitrine.git
  19. devcycle

    Skills

    Turns a short feature/bug description into a reviewed, on-device-verified implementation — parallel subagents, cross-model review, GitHub reconcile, and a doctor/learn loop that benchmarks and improves the pipeline itself. Built on superpowers.

    Indexed GitHub, KonstantinRoehrl 5 ★MITUpdated 4 days ago

    git clone https://github.com/KonstantinRoehrl/devcycle.git
  20. Mobile AI Skills, Agents and workflow to help you build mobile apps and games faster. A collection of AI skills, agents, prompts, and workflows for Android, iOS, Flutter, React Native, Unity, and Unreal developers. Use these ready-made tools to write code faster, fix bugs, review code, improve performance, automate tasks, and ship faster with AI.

    Stale GitHub, salmanashraf 35 ★MITUpdated 7 days ago

    git clone https://github.com/salmanashraf/mobile-ai-agents.git
  21. 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
  22. Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

    Indexed Agent skill collections on GitHub, mattpocock MIT1 note

  23. Lightweight desktop tool for Call of Duty: Modern Warfare 4. Smart FPS optimization, performance tuning, process management and real-time monitoring. Designed to improve frame rates and stability. Regularly updated.

    Stale GitHub, Demonwave56032 29 ★Updated 25 days ago

    git clone https://github.com/Demonwave56032/call-of-duty-modern-warfare-resocket-4-fps-optimizer.git
  24. skill-creator

    Skills

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    Indexed Agent skill collections on GitHub, anthropics 1 note

    /plugin marketplace add anthropics/skills

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.