agent-skills
Agent Skills — agent-neutral autonomous product-building OS for 32+ AI coding tools. 23 skill categories · 28 agents · 149 reference docs · 37 platform variants. One-line prompts → deployed products on Cloudflare Workers.
エージェント・スキル・MCP分野の測定済みカタログ項目です。
結果は「エージェント・スキル・MCP」内に限定されます。代わりに検索: カタログ全体
Agent Skills — agent-neutral autonomous product-building OS for 32+ AI coding tools. 23 skill categories · 28 agents · 149 reference docs · 37 platform variants. One-line prompts → deployed products on Cloudflare Workers.
Turn a reference video, image or idea into a verified physics reconstruction in Blender: measure the clip, solve and benchmark the real physics, verify it independently, render it in the same scene.
Draws the work in your beads trackers as trees, with what each agent is doing beside the bead it works. It also watches beads for whatever waits on them, and settles beads that wait on GitHub.
A cockpit for Claude Code: live plan bars, subagent strips, usage limits with reset countdowns, model routing and a tiny pet, right above your prompt. CLI and Desktop.
Semantic-first multi-agent communication protocol — 4 concepts, 3 operations, infinite collaboration patterns
Standalone skills for Claude Code and Codex: product discovery, architecture, implementation, technical foundations, reviews and delivery, with explicit scope and verification.
Bitbucket CLI with gh-like ergonomics
Find leaks in AI-built apps: open Supabase/Firebase data, exposed keys, unsafe edge functions
The lossless, headless coding agent harness. One 7 MB static binary, four tools, plain stdin/stdout, no silent cuts.
Ready-to-use .claude configuration for Python projects: agents, skills, commands, rules, and MCP server templates for Claude Code.