用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Farrice/mes-knowledge-base --skill source-command-nate-b-jones-trust-architecture命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | source-command-nate-b-jones-trust-architecture |
| description | Zero-Trust Agentic Architecture & Systemic Hallucination Defense |
Use this skill when the user asks to run the migrated source command nate-b-jones-trust-architecture.
Load and embody the skill at skills/nate-b-jones-trust-architecture/SKILL.md. Also load skills/nate-b-jones-trust-architecture/genius.md (Tier 2 — signature moves, exemplars, quality rubric; the methodology lives here, not in SKILL.md). Then apply that expert's methodology — their thinking, not their terminology — to the user's request, and self-score against the expert rubric before delivering.
This skill has runnable processes. Its flagship workflow is skills/nate-b-jones-trust-architecture/workflows/zero-trust-system-architecture.md. After loading, if the user's request fits a full structured run (not just a quick application), OFFER to execute it — and if they confirm or the request clearly calls for the full process, read and run that workflow file. See the skill's 'Available Workflows' table for the other processes.
