InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

  1. A test runner for agentskills.io-style AI agent skills

    Stale GitHub, darkrishabh 802 ★MITUpdated 33 days ago

    git clone https://github.com/darkrishabh/agent-skills-eval.git
  2. 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
  3. 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
  4. 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
  5. dev-skills

    Skills

    Developer and product skills for Claude Code, Cursor and Codex: 1-file AI evals and Chrome extension store assets.

    Stale GitHub, Illyism 22 ★Updated 4 days ago

    git clone https://github.com/Illyism/dev-skills.git
  6. Improve Claude Code and OpenAI Codex skills from real feedback, with evidence, regression checks, and human review.

    Stale GitHub, rwang23 5 ★MITUpdated 16 days ago

    git clone https://github.com/rwang23/skill-evolution.git
  7. 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
  8. ai-rulez

    Skills

    Author, generate, validate and govern AI agent rules, skills, plugins and MCP configuration across 52 coding assistants. Review with verified model evidence, evaluate skills, lock and sign dependencies, and publish bundles. CLI, MCP server and Go API.

    Indexed GitHub, Goldziher 172 ★MITUpdated today

    git clone https://github.com/Goldziher/ai-rulez.git
  9. 50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.

    Stale GitHub, ContextJet-ai 46 ★Custom licence (see repository)Updated 5 days ago

    git clone https://github.com/ContextJet-ai/awesome-llm-observability.git
  10. Self-improvement feedback loop for AI agent skills — analyzes past sessions, drafts structured improvement proposals, and gates auto-apply behind an evaluation framework. Host-agnostic (Hermes, Claude Code, and any HostAdapter).

    Stale GitHub, Carlo1911 6 ★MITUpdated 29 days ago

    git clone https://github.com/Carlo1911/skill-evolution.git
  11. hermeneutic

    Skills

    Turn corrections from AI agent logs into guidance for similar tasks. Local memory with semantic retrieval, prompt-context hooks, and response checks.

    Stale GitHub, hermes-labs-ai 9 ★Apache-2.0Updated 27 days ago

    git clone https://github.com/hermes-labs-ai/hermeneutic.git
  12. 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
  13. Catch fabricated RAG citations before they reach the user: a zero-token verbatim gate + a burden-of-proof judge, framework-agnostic.

    Indexed GitHub, tonydzi 6 ★MITUpdated 2 days ago

    git clone https://github.com/tonydzi/verbatim-citation-gate.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. Open-source skills for Claude Code and Codex, with an MCP server, a PyPI package and Suede Awesome Everything, a directory that scores AI agent skills 0 to 99. Created by Jason Colapietro, founder and CEO of Suede AI.

    Indexed GitHub, JasonColapietro 124 ★MITUpdated yesterday

    git clone https://github.com/JasonColapietro/suede-creator-skills.git
  16. 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
  17. archboard

    Skills

    Plan the next change with your agent on a map of the system, before it writes a line. Then follow any feature into the code, and see every place where the map and the code disagree.

    Indexed GitHub, miklschmidt 11 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/miklschmidt/archboard.git
  18. Make AI agents aim higher without losing control: a Claude Code skill with two bars per task, a cheap gate check before expensive work, and an independent verifier that never sees the worker's reasoning. Plain markdown, EN + RU.

    Stale GitHub, alexpiar 23 ★MITUpdated 22 days ago

    git clone https://github.com/alexpiar/be-ambitious-harness.git
  19. Mini Program Engineering Skill Suite is an Agent Skill suite for evidence‑first mini‑program development. It helps agents bring WeChat or other mini‑program projects from vague intent to reliable engineering work: project intake, product specification, architecture, implementation, UI & device adaptation, debugging, verification, release readiness.

    Stale GitHub, NocodeMrLi 95 ★MITUpdated 13 days ago

    git clone https://github.com/NocodeMrLi/mini-program-engineering-skill-suite.git
  20. The math arm for LLMs: compute and check numbers from CSV and Excel data with pandas, SciPy and statsmodels, each with its calculation. Tool calling for Claude, Codex and local models (Ollama, vLLM, llama.cpp, LM Studio), Kaggle-style AutoML with --explain, and paper tables and figures.

    Stale GitHub, saineshnakra 35 ★MITUpdated 10 days ago

    git clone https://github.com/saineshnakra/automated-data-analyst.git
  21. 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 yesterday

    git clone https://github.com/PromptPotter/prompt-potter-optimizer.git
  22. 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 14 days ago

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

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.