Designing, evaluating, and shipping autonomous AI agents.
7572 posts
Reusable agent skills for scaffolding C++ and embedded projects
Visual alignment and explicit approval gates for complex Codex tasks
Portable, evidence-driven agent development harness for Codex, Claude Code, and generic Agent Skills. Active beta v0.1.2.
The Supabase deploy-gate that runs where you vibe-code. Static OSS scanner for the RLS/secret holes that leak vibe-coded apps — CLI + Claude...
Runtime-evidence debugging for coding agents: session-scoped probes, bounded logs/query CLI, and an agent skill.
Spec-driven coding skills for AI agents: plan with acceptance criteria, self-correct from feedback, and remember reusable project knowledge.
Video OSINT agent: senses + OSINT reach for any agent.
The largest community-driven library of Agent Skills (SKILL.md + scripts/references/examples) for Claude, Codex, Gemini CLI, Cursor and frie...
Claude Code skill for managing skills, MCPs, and plugins by categories
判断一个skill适不适合你用的skill——啥好用。它可以根据你的需求，把候选 Skill 的用途、安装代价、风险和需求匹配度做成清晰易懂的 HTML 说明书，提...
Agent Skill teaching Claude Code and Codex to author, validate, and consume Open Knowledge Format (OKF) v0.1 bundles
多智能体群聊工作台：本地圆桌 Agent 用于方案讨论，战略分析、风险复盘。自定义名人角色进行群聊争论出最佳方案
