Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
GLM-5.3-Flash × J-Space capability realization — benchmark presentation of the J-Space Cognition Suite
git clone https://github.com/Tiger3807861189/GLM-5.3-Flash-J-Space-Capability-Realization-Report.git -
coder_eval
SkillsPlaywright for coding agents. Test that your skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, A/B experiments, CI gates.
git clone https://github.com/UiPath/coder_eval.git -
eval-genius
SkillsTeach 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.
git clone https://github.com/alexgreensh/eval-genius.git -
Hill-Climb
SkillsMake your coding agent prove "done". Each change is kept only if a locked test or benchmark scores it better. Claude Code and Codex skill.
git clone https://github.com/Bil0000/Hill-Climb.git -
SkillEvaluator
SkillsMulti-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.
git clone https://github.com/NVIDIA/SkillEvaluator.git -
autoharness
SkillsAutoharness — 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.
git clone https://github.com/tigerless-labs/autoharness.git -
opencode-skill-creator
SkillsCreate, test, and optimize OpenCode skills. Supports OpenCode V2 and V1 ≥ 1.18.29. Adapted from Anthropic's skill-creator.
git clone https://github.com/antongulin/opencode-skill-creator.git -
An Agent Skill helping you to optimize Xcode incremental and clean builds by running benchmarks and optimizing build settings.
git clone https://github.com/AvdLee/Xcode-Build-Optimization-Agent-Skill.git -
SkillCorpus
SkillsOpen-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
git clone https://github.com/EverMind-AI/SkillCorpus.git -
tne-sdk
SkillsTNE-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.
git clone https://github.com/Firespawn-Studios/tne-sdk.git -
OpenART
SkillsOpenART 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.
git clone https://github.com/AI45Lab/OpenART.git -
evo
Skillsturns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.
git clone https://github.com/evo-hq/evo.git -
blender-agent-studio
SkillsFree, 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.
git clone https://github.com/ifBars/blender-agent-studio.git -
australian-accounting
SkillsLocal engines for ATO benchmarks, Payday Super and Division 7A loans, served by the aus-accounting-mcp server. Synthetic data only.
git clone https://github.com/ryanduguid/australian-accounting.git -
nasde-toolkit
SkillsCLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.
git clone https://github.com/NoesisVision/nasde-toolkit.git -
many-ppt-skills
SkillsEvery 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.
git clone https://github.com/brycewang-stanford/many-ppt-skills.git -
agent-skill-implementation
SkillsEmpirical research into how agent platforms implement Agent Skill loading, management, and presentation. Benchmark skills and per-platform findings.
git clone https://github.com/agent-ecosystem/agent-skill-implementation.git -
ouba-classmate
Skills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
git clone https://github.com/ouxxyy/ouba-classmate.git -
backendskills
SkillsSkills 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.
git clone https://github.com/globalmpc/backendskills.git -
Awesome-Self-Evolving-Agents
SkillsA Survey of Self-Evolving Agents | A curated list of resources (surveys, papers, benchmarks, and opensource projects) on Self-Evolving Agents.
git clone https://github.com/XMUDeepLIT/Awesome-Self-Evolving-Agents.git -
opentai.github.io
SkillsThe official website of the Open Trustworthy AI Community (OpenTAI).
git clone https://github.com/OpenTAI/opentai.github.io.git -
skills
SkillsEdge finds task-fit agent skills, shows available evidence, and loads pinned versions into AI agents.
git clone https://github.com/getedgehq/skills.git -
dokimi
SkillsDokimi (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.
git clone https://github.com/intel/dokimi.git -
hermes-jailbench
SkillsZero-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
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.