Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
agent-formal-verify
SkillsTLA+ model checking and Lean proofs for coding agents, with explicit tool setup.
git clone https://github.com/michael-denyer/agent-formal-verify.git -
skills
SkillsAgent skills for Ultralytics YOLO, covering models, datasets, training, tuning, inference, tracking, and export.
git clone https://github.com/ultralytics/skills.git -
repro-lens
SkillsStatic reproducibility checks, experiment replay, and verification for ML pipelines.
git clone https://github.com/00200200/repro-lens.git -
claude-toolbox
SkillsMinimal by design, explicitly multi-lang, production-ready and battle-tested collection of configs and plugins for your Claude Code agentic development workflows: mcp, configs, skills, agents and more.
git clone https://github.com/serpro69/claude-toolbox.git -
OpenVideoHarness
SkillsA video harness work platform for Agents such as Claude or Codex: the agent writes the code that renders the film, checks its own frames, storyboard and cut. 给 Claude Code 和 Codex 用的视频Harness工作台:agent 写代码渲染成片、自己检查分镜,立意、成片由你拍板;众多风格预设、引擎丰富,配音配乐也用代码做。
git clone https://github.com/ZLHad/OpenVideoHarness.git -
product-video-as-code
SkillsBuild product videos from your IDE instead of a video editor
git clone https://github.com/kritikmodi/product-video-as-code.git -
charakuru-claude-code
SkillsUnofficial Claude Code skill for running きゃらくる / Charakuru: from a character illustration to a VRM with spring bones and expressions. Kit not included.
git clone https://github.com/kokushin/charakuru-claude-code.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 -
slide-wright
SkillsMake a presentation with your coding agent. Compare design directions in short previews, pick one, then build and export to PowerPoint or PDF.
git clone https://github.com/arifszn/slide-wright.git -
paper-reading-skill
SkillsAgent skill for visual, source-grounded paper reading: one standalone HTML atlas of methods, equations, and experiments.
git clone https://github.com/xiaofengShi/paper-reading-skill.git -
agencil
SkillsCreate agentic councils with your favourite harnesses and let your working agents ask tough questions. They gather, debate and respond in a single voice
git clone https://github.com/danieltamas/agencil.git -
eplan-mcp
SkillsMCP server for EPLAN Electric P8: ~200 tools to drive EPLAN from Claude Code, Codex, Cursor or any MCP client (actions, scripts, live DataModel, exports). Includes the eplan-tools plugin marketplace.
git clone https://github.com/Canary-ECAD/eplan-mcp.git -
polish-sci-figures
SkillsScientific figure toolkit and Figure Studio: editable templates, local statistics, multi-panel editing and SVG/PNG/TIFF export, with skills for Codex and Claude. | 科研绘图与组图编辑:模板作图、统计分析、精修排版及高清导出。
git clone https://github.com/zhoy0409-debug/polish-sci-figures.git -
super-video-agent
SkillsFree, source-available Claude Code skill that draws narrated videos in code: YouTube Shorts, explainers, 3D flights. Install in two commands.
git clone https://github.com/ww-w-ai/super-video-agent.git -
e5-real-skills
SkillsA living library of B2B marketing Claude skill files built from the Exit Five B2B marketing podcast. Every skill sourced from expert practitioners. Auto-updates with new episodes.
git clone https://github.com/the-nam-shub/e5-real-skills.git -
wiredkits-free
SkillsFree Claude Code skills and agents: CLAUDE.md writer, commit messages, release notes, code explainer, and smart model/effort picking for subagents. MIT.
git clone https://github.com/electronx/wiredkits-free.git -
task-pipeline
SkillsTake repository changes from a clear brief to implementation, verification and a durable handoff through explicit delivery gates.
git clone https://github.com/ssheleg/task-pipeline.git -
trail-running-pace
Skills耐力学社越野跑体感一致配速表 Skills · Even-effort trail running pace charts with checkpoint splits and SVG export.
git clone https://github.com/yihouzenmeban/trail-running-pace.git -
Recat
SkillsA local workspace for security findings. Review findings from Hermes or other agents, inspect evidence, and export reports. Recat supports Web, Smart contract, and Other assets, including mobile, desktop, networks, and hardware.
git clone https://github.com/0xtbug/Recat.git -
agent-skills
SkillsFive SKILL.md files that give AI agents UX expertise: evaluate interfaces, detect UX smells, audit AI interfaces, check flows. For Cursor, Windsurf, Claude Code and kx
git clone https://github.com/uxuiprinciples/agent-skills.git -
jupyter-notebook
SkillsUse when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.
$skill-installer <skill-name> -
framework-builder
SkillsBuild reusable, agent-readable frameworks from any domain expertise. Open methodology + worked examples from a 1,250+ framework library.
git clone https://github.com/framework-creator/framework-builder.git -
anti-gold-plating
SkillsA skill for strict scope control, explicit user approval, and final compliance checks.
git clone https://github.com/TulossSolutions/anti-gold-plating.git -
SkillSafe
SkillsSkillSafe: portable evidence-linked knowledge vault for AI agents, with a local Python engine, reviewed writes, source anchors and Markdown/OKF exports.
git clone https://github.com/GodModeAI2025/SkillSafe.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.