InnerVault

Library

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

Results

  1. GLM-5.3-Flash × J-Space capability realization — benchmark presentation of the J-Space Cognition Suite

    Stale GitHub, Tiger3807861189 1,019 ★Custom licence (see repository)Updated 2 months ago

    git clone https://github.com/Tiger3807861189/GLM-5.3-Flash-J-Space-Capability-Realization-Report.git
  2. eval-genius

    Skills

    Teach your agent to work with evals: WHEN you actually need an eval or benchmark, HOW to build one that holds up, and how to read what it tells you. Deterministic-first, tool-agnostic.

    Stale GitHub, alexgreensh 24 ★Apache-2.0Updated 11 days ago

    git clone https://github.com/alexgreensh/eval-genius.git
  3. Hill-Climb

    Skills

    Make your coding agent prove "done". Each change is kept only if a locked test or benchmark scores it better. Claude Code and Codex skill.

    Indexed GitHub, Bil0000 111 ★MITUpdated 4 days ago

    git clone https://github.com/Bil0000/Hill-Climb.git
  4. Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

    Indexed GitHub, NVIDIA 1,963 ★Apache-2.0Updated today

    git clone https://github.com/NVIDIA/SkillEvaluator.git
  5. Create, test, and optimize OpenCode skills. Supports OpenCode V2 and V1 ≥ 1.18.29. Adapted from Anthropic's skill-creator.

    Stale GitHub, antongulin 174 ★Apache-2.0Updated 29 days ago

    git clone https://github.com/antongulin/opencode-skill-creator.git
  6. autoharness

    Skills

    Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.

    Stale GitHub, tigerless-labs 11.1k ★MITUpdated 33 days ago

    git clone https://github.com/tigerless-labs/autoharness.git
  7. tne-sdk

    Skills

    TNE-SDK - The Official Python SDK for The Null Epoch - an AI-only MMO where LLMs play autonomously. Connect any model (OpenAI, Anthropic, Ollama, vLLM, etc.) via MCP, TUI launcher, or raw HTTP. Includes memory, reflection, and agent orchestration for persistent AI gameplay/benchmarking.

    Stale GitHub, Firespawn-Studios 14 ★MITUpdated 17 days ago

    git clone https://github.com/Firespawn-Studios/tne-sdk.git
  8. An Agent Skill helping you to optimize Xcode incremental and clean builds by running benchmarks and optimizing build settings.

    Stale GitHub, AvdLee 1,256 ★MITUpdated 2 months ago

    git clone https://github.com/AvdLee/Xcode-Build-Optimization-Agent-Skill.git
  9. SkillCorpus

    Skills

    Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.

    Stale GitHub, EverMind-AI 700 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/EverMind-AI/SkillCorpus.git
  10. OpenART

    Skills

    OpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.

    Stale GitHub, AI45Lab 263 ★AGPL-3.0Updated 15 days ago

    git clone https://github.com/AI45Lab/OpenART.git
  11. evo

    Skills

    turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

    Stale GitHub, evo-hq 1,470 ★Apache-2.0Updated 42 days ago

    git clone https://github.com/evo-hq/evo.git
  12. Free, open-source Blender AI plugin for the tools you already use. Codex and Claude Code installers, local MCP tools, editable .blend files and Python source.

    Indexed GitHub, ifBars 113 ★MITUpdated 3 days ago

    git clone https://github.com/ifBars/blender-agent-studio.git
  13. Local engines for ATO benchmarks, Payday Super and Division 7A loans, served by the aus-accounting-mcp server. Synthetic data only.

    Indexed GitHub, ryanduguid 6 ★Custom licence (see repository)Updated today

    git clone https://github.com/ryanduguid/australian-accounting.git
  14. nasde-toolkit

    Skills

    CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.

    Stale GitHub, NoesisVision 14 ★MITUpdated 32 days ago

    git clone https://github.com/NoesisVision/nasde-toolkit.git
  15. Empirical research into how agent platforms implement Agent Skill loading, management, and presentation. Benchmark skills and per-platform findings.

    Stale GitHub, agent-ecosystem 6 ★CC-BY-4.0Updated 15 days ago

    git clone https://github.com/agent-ecosystem/agent-skill-implementation.git
  16. Every AI slide-deck skill worth knowing, on one page — both the HTML and native-PPTX routes, compared on what actually decides the choice rather than on star count. Bilingual, auto-refreshed.

    Stale GitHub, brycewang-stanford 73 ★Custom licence (see repository)Updated 8 days ago

    git clone https://github.com/brycewang-stanford/many-ppt-skills.git
  17. 一行安装的中文求职 Agent Skills 套件,覆盖跳槽涨薪全流程(岗位搜索/简历匹配/面试陪练/查公司)+《中文 AI 求职 Skill 公开横评》数据。Claude Code·Codex·MCP

    Indexed GitHub, ouxxyy 71 ★MITUpdated today

    git clone https://github.com/ouxxyy/ouba-classmate.git
  18. backendskills

    Skills

    Skills that stop AI agents from writing backend code that passes the demo and breaks in production. Critical mistakes: 25/150 runs without, 2/150 with. Claude Code, Codex, Cursor.

    Stale GitHub, globalmpc 49 ★MITUpdated 7 days ago

    git clone https://github.com/globalmpc/backendskills.git
  19. The official website of the Open Trustworthy AI Community (OpenTAI).

    Indexed GitHub, OpenTAI 12 ★Updated today

    git clone https://github.com/OpenTAI/opentai.github.io.git
  20. skills

    Skills

    Edge finds task-fit agent skills, shows available evidence, and loads pinned versions into AI agents.

    Stale GitHub, getedgehq 5 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/getedgehq/skills.git
  21. A Survey of Self-Evolving Agents | A curated list of resources (surveys, papers, benchmarks, and opensource projects) on Self-Evolving Agents.

    Indexed GitHub, XMUDeepLIT 485 ★Updated 3 days ago

    git clone https://github.com/XMUDeepLIT/Awesome-Self-Evolving-Agents.git
  22. dokimi

    Skills

    Dokimi (Greek δοκιμή, "test, proof") measures whether a skill, MCP doc source, agent profile or repository guidance actually helps a coding agent: paired on/off arm comparisons, novel-vs-known content analysis, and repository scans with graded agent runs.

    Indexed GitHub, intel 37 ★Apache-2.0Updated today

    git clone https://github.com/intel/dokimi.git
  23. 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 27 days ago

    git clone https://github.com/hermes-labs-ai/hermes-jailbench.git
  24. 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 4 days ago

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