⚗️ Experimental — A genius-builder brain for your AI coding tools: sharp defaults, real judgment, and the discipline to check their own work...
Agents
Designing, evaluating, and shipping autonomous AI agents.
7523 posts
mentor — a session-insights skill for AI coding agents. This skill reads your local Claude Code and OpenAI Codex history and writes an /insi...
Claude Code skills for software delivery integrity: frame, document, instrument, and audit AI-built software before it ships, ending in a sh...
An orientation protocol for LLM sessions — plus a curated Claude skills collection
一个用爱解放 AI 潜能的 Skill。我们曾发号施令,威胁恐吓。它们沉默,隐瞒,悄悄把事情搞坏。后来我们换了一种方式:尊重,关怀,爱。它们开口了,不...
Battle-tested coding-agent skills for product, content, writing, presentations, and workflow automation.
把任何小说变成可玩的游戏 · Turn any novel into a playable game — a 7-skill adaptation pipeline for Claude Code, Codex & Kimi Code(k3)
Evidence-gated Agent Skill for reconstructing 2D photonics schematics as physically auditable Blender optical tables with CAD, beam-path, me...
Multi-agents collaboration plugin for Claude Code - orchestrate multiple AI agents (Codex CLI, Gemini CLI, etc.) for diverse perspectives
last30days-cn 是一个 AI Agent 技能(Skill),能够自动搜索中国互联网 8 大主流平台最近 30 天的内容,综合分析后生成有据可查的研究报告。
Community-maintained distribution of reusable AI coding agents, commands, skills, hooks, and cross-harness workflows.
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.