3671 posts
A read-only weekly audit for Codex automations and personal skills, with approval-gated fixes.
Task-aware native capability manager for DeepSeek Harness — use, prepare, and verify built-in DSH tools before adding another plugin.
AI agent 通用任务治理框架：对齐目标与事实，规划和调度能力，守住授权与风险边界，治理任务执行到真实验收与交付。Governance framework for eviden...
The context layer for AI agents — open, structured, searchable knowledge protocol (Domain → Concept → Link). Skills-first, no MCP server nee...
Skill-Atlas
My personal agent skills
红狐数据 技能合集：面向 Agent 的可复用 SKILL 集合，覆盖灵感、选题、文案创作、数据复盘等场景，持续更新。
OKF (Open Knowledge Format): durable, structured memory for AI agents. This ecosystem includes: Skills, MCP, Interactive Graph, TUI, CLI, Do...
Verified Agent Skills registry for Codex and Claude Code: curated installs, provenance, license checks, reproducible evidence, and daily sou...
亚马逊评论分析 Agent Skill：卖家精灵 Review 表 → 一/二/三级分类树（格子里是买家原话）→ HTML 看板 + 交付 Excel
Open-source adversarial verification Agent Skill for Claude Code, OpenAI Codex, and Cursor. Make AI coding agents prove bug fixes, CI, logs,...
Turn your Grok Bot into a 7-agent Hyperliquid trading desk. Roles, system prompts and skills your Bots use to research, size, execute and re...
