Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
d3-mini
Modelszero shot classification model by vllm-sr · transformers
vllm-sr/d3-mini -
d3-nano
Modelszero shot classification model by vllm-sr · transformers
vllm-sr/d3-nano -
d3-ultra
Modelszero shot classification model by vllm-sr · transformers
vllm-sr/d3-ultra -
d3-lite
Modelszero shot classification model by vllm-sr · transformers
vllm-sr/d3-lite -
opencompass
Datasets & benchmarksOpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.
git clone https://github.com/open-compass/opencompass.git -
cc-thinking-skills
Skills28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools
git clone https://github.com/tjboudreaux/cc-thinking-skills.git -
suede-creator-skills
SkillsOpen-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.
git clone https://github.com/JasonColapietro/suede-creator-skills.git -
jev-mode
SkillsClaude Code/Codex skills, evals, harnesses/context tools, and learning resources that make it easy to build with Jev, TypeSafe's System One model. All materials pull directly from their canonical cookbooks and documentation.
git clone https://github.com/tiffygk/jev-mode.git -
skillcheck
PromptsBlind A/B testing for AI agent skills, .cursorrules, CLAUDE.md, and system prompts. Detects placebo and harmful instructions.
git clone https://github.com/sx4im/skillcheck.git -
image text to text model by nvidia · transformers
nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 -
hwatu
MCP serversVerification browser for coding agents: headless WebKit, DOM eval, screenshots, pixel-diff.
https://github.com/hongnoul/hwatu/releases/download/v0.6.0/hwatu-mcp-linux-x86_64.tar.gz@0.6.0 -
founder-pipeline
SkillsA gated 25-step pipeline for validating and launching a business idea with Claude Code. Evidence over assumption, a fresh-context critic and a human signature at every step, three gates that can kill the idea. 23 skills, 4 subagents, 2 workflows, an approval hook, evals and CI. MIT.
git clone https://github.com/marian-kamenistak/founder-pipeline.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 -
Agent-Skills
SkillsSkills SDK for Codex/AI coding agents: author, validate, evaluate, and sync runtime projections through ask.
git clone https://github.com/jscraik/Agent-Skills.git -
uptrain
PromptsUpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them.
git clone https://github.com/uptrain-ai/uptrain.git -
claude-skills
SkillsSix Claude Code skills + an unattended build loop, each measured with and without the plugin. 19/19 evals passing.
git clone https://github.com/alonbaron/claude-skills.git -
vetted
SkillsAgent skills that prove they work, plus a zero-dependency scanner that vets any skill before you install it.
git clone https://github.com/Xnadir/vetted.git -
measured-type
SkillsAgent skill for web typography: Bringhurst applied to modern CSS, with claims measured in the browser and a baseline eval suite
git clone https://github.com/PetriLahdelma/measured-type.git -
be-ambitious-harness
SkillsMake 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.
git clone https://github.com/alexpiar/be-ambitious-harness.git -
forgejudge
MCP serversOpen eval leaderboard + CI gate for autonomous coding agents (solve, score, trace).
forgejudge@0.1.0 -
remnic
MCP serversOpen-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
git clone https://github.com/joshuaswarren/remnic.git -
github-bounty-scanner
Skills🛡️ Autonomous GitHub Bounty Scanner & On-Chain Escrow Verifier — Find Real Crypto/USDC/wDOOM Bounties & Filter Fake Scraper Traps
git clone https://github.com/doomsday-network/github-bounty-scanner.git -
bounty-guard
SkillsZero-dependency Python CLI, GitHub Action, and MCP server scanning untrusted GitHub issues and repositories for prompt injection, CI secret exfiltration, and cryptographic bounty escrow.
git clone https://github.com/doomsday-network/bounty-guard.git -
source-to-skill
SkillsTurn YouTube videos, podcasts, meetings, papers, books, docs sites (llms.txt) and notes into agent skills for Claude Code, Codex, Cursor & Gemini CLI. Exact-second links, built-in evals, local Whisper, no API keys.
git clone https://github.com/michalstrnadel/source-to-skill.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.