菜单
Extract Zulip thread HTML dumps into readable plain text. Use when the user provides a Zulip HTML file or asks to parse/read/convert/summarize a Zulip thread.
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/leanprover/lean4 --skill zulip-extract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。
正在显示 SKILL.md
| name | zulip-extract |
| description | Extract Zulip thread HTML dumps into readable plain text. Use when the user provides a Zulip HTML file or asks to parse/read/convert/summarize a Zulip thread. |
Run the bundled script to convert a Zulip HTML page dump into plain text.
python3 .claude/skills/zulip-extract/zulip_thread_extract.py input.html output.txt
The script has zero dependencies beyond Python 3 stdlib. It extracts sender, timestamp, message content (with code blocks, links, quotes, mentions), and reactions.
Retrieve and investigate failing Lean CI job logs. Use when a CI job fails and you need to fetch its logs, or when monitoring a CI run for failures.
Build and run tests against the stage2 Lean compiler. Use when asked to build, rebuild, or test against stage2.
Diagnose a spurious stage1 test failure caused by olean-persisted compiler changes. Use when a stage1 test fails unexpectedly and the change adds or modifies an environment extension or other information persisted into .olean files.
基于 SOC 职业分类
