Designing, evaluating, and shipping autonomous AI agents.
7536 posts
Claude skills for turning messy business context into clear asks, decisions, owners, updates, and follow-ups.
Simulate evidence-grounded timelines from a point of change, mapping causes, people, and branching futures with disciplined uncertainty.
Adversarial agent loops for verifiable vibe researching. Claude Code plugin. Falsification-first, not production-first.
Delegate coding tasks to the Antigravity CLI (agy) as a background implementer; review the diff and commit it yourself.
GitHub repository optimization skills for Claude Code, Codex, and Gemini CLI. Audit repos, improve READMEs, tune metadata, releases, legal f...
A framework for discovering, compiling, and validating reusable skills for scientific agents.
Research-first Agent Skill that runs long-horizon paper pipelines with evaluator gates, heartbeat watchdogs, resume controls, and manifest c...
Agents, skills, commands, and rules for AI-powered coding tools — used daily to supercharge development productivity.
workflows for compound thinking with AI
Get a bigger model to check your smaller model daily runs and improve it on a daily basis
🔐 告别 .env 泄露 — 让任何 AI Agent 安全读取加密密钥。AES-256-GCM 云端加密，一行命令解密。
The elite design intelligence layer for AI agents, synthesized from 10+ legendary design books. It primes your AI with the collective strate...
