菜单
获取公开网页的正文或 Markdown 内容。当用户要求抓取链接、读取文章、提取网页正文、将页面转为 Markdown，或获取 X/Twitter、微信、知乎、Medium 等公开页面的文字内容时使用。支持在直接抓取失败或内容不完整时，通过内容提取代理和网页搜索逐级回退；不适用于需要登录的页面、付费墙绕过、媒体下载或结构化数据抓取。
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。
基于 SOC 职业分类
根据指定 Git 仓库和日期，从 commit、提交正文、文件变更及必要的 diff 中提炼每日工作内容。用于用户要求按项目和日期生成日报、每日工作总结、根据 Git commit 总结工作，或要求用 1、2、3 编号列出某天或某段日期完成事项的场景。
Git Rebase 分支同步流程，用于将当前功能分支 rebase 到最新的目标分支（如 master/main），保持提交历史整洁。适用于功能分支落后于目标分支时，需要同步最新代码的场景。
Review a completed or nearly completed non-trivial task and maintain durable lessons across project docs, memory, existing skills, or new skills. Use after complex debugging, deployment, live verification, repo documentation work, repeated workflow discovery, creating or updating a skill, or when the user asks whether anything is worth remembering, updating, or deleting.
Use when Codex is about to use, is using, or has just used browser automation MCP tools such as chrome-devtools-mcp, Chrome DevTools MCP, Playwright MCP, @playwright/mcp, browser MCP, or browser/computer automation helpers; when the user mentions high CPU, high energy usage, battery drain, fans, heat, lag, duplicate browser MCP processes, stale Chrome Helper processes, or MCP cleanup; or when long-running Codex sessions may leave browser automation MCP helper processes behind.
Create one or more Git commits grouped by coherent change topic, then push the current branch. Use when the user asks to commit and push, submit by topic, split current changes into topical commits, or do "按照主题提交 commit 并 push"; especially when a worktree has mixed staged, unstaged, or untracked changes that need honest commit boundaries before `git push`. Commit messages must be written in Chinese unless the user explicitly requests another language.
Create copy-ready, verifiable run contracts for long-horizon agent work. Use when the user asks to write, improve, or review Codex `/goal` prompts, Claude Code `/goal` conditions, Claude `/loop` prompts, `.claude/loop.md`, `goal.md`, loop engineering prompts, autonomous run instructions, stop/pause conditions, verification criteria, bounded iteration policy, or persistent Markdown instructions for agents.
| name | web-content-fetcher |
| description | 获取公开网页的正文或 Markdown 内容。当用户要求抓取链接、读取文章、提取网页正文、将页面转为 Markdown，或获取 X/Twitter、微信、知乎、Medium 等公开页面的文字内容时使用。支持在直接抓取失败或内容不完整时，通过内容提取代理和网页搜索逐级回退；不适用于需要登录的页面、付费墙绕过、媒体下载或结构化数据抓取。 |
本 skill 的核心思路：渐进回退，确保拿到内容。
任何 URL 都按以下顺序尝试，不区分网页类型：
r.jina.ai 和 defuddle.md 两种代理前缀，取内容更完整的结果"不完整"的判断：返回正文少于 200 字、明显缺失关键段落、或返回错误/空白页面。
在目标 URL 前加上 https://r.jina.ai/ 前缀，用 WebFetch 抓取：
https://r.jina.ai/<目标URL>
示例
https://r.jina.ai/https://x.com/qoder_ai_ide/status/2036437931867644016
https://r.jina.ai/https://www.anthropic.com/engineering/some-post
https://r.jina.ai/https://any-website.com/any-page
特点
在目标 URL 前加上 https://defuddle.md/ 前缀，用 WebFetch 抓取：
https://defuddle.md/<目标URL>
示例
https://defuddle.md/https://mp.weixin.qq.com/s/ERSjcq9YURHvlsdTUv_Paw
https://defuddle.md/https://example.com/some-article
https://defuddle.md/https://any-website.com/any-page
特点
本 skill 持续更新中。如需添加新的获取方法，按照相同格式补充即可。