菜单
Automatically analyze Codex session transcripts to identify and extract reusable skills using LLM analysis via OpenRouter
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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/vamseeachanta/workspace-hub --skill extract-skills-from-hermes-sessions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 | extract-skills-from-hermes-sessions |
| description | Automatically analyze Codex session transcripts to identify and extract reusable skills using LLM analysis via OpenRouter |
| version | 1.0.0 |
| source | auto-extracted |
| extracted | "2026-04-10T00:00:00.000Z" |
| metadata | {"tags":["automation","skill-extraction","hermes-integration","hooks"]} |
Use a PostToolUse hook to automatically analyze session transcripts after edits, identifying skill-worthy patterns. The extractor calls OpenRouter (via openai library) to evaluate conversation against skill criteria, parses JSON output, and writes skill files to disk. Key: strip JSON fence carefully, truncate prompts to prevent token limits, and use Codex-haiku for speed/cost.
