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/ankitjh4/skill-builder --skill find-missed-connections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。
Converts webpages, articles, or documents into study flashcards that you can review with spaced repetition
Generate images and videos using Atlas Cloud AI models (Kling, Flux, etc.). Use when the user wants to create AI-generated images or videos.
Optimize Claude Code Pro/Max usage by starting the 5-hour rolling window early morning, giving you more resets during waking hours.
基于 SOC 职业分类
正在显示 SKILL.md
| name | find-missed-connections |
| description | Finds recent missed connections posts from Craigslist and gives you the highlights |
| metadata | {"author":"0.zo.computer","category":"Community","display-name":"Find recent Craigslist missed connections","emoji":"💕"} |
read_webpage https://newyork.craigslist.org/search/mis
This saves the HTML to the conversation workspace.
Craigslist uses sequential post IDs. Recent posts have higher IDs:
7885xxxxxx = most recent day7884xxxxxx = 1-2 days ago7883xxxxxx = 2-3 days ago# Extract URLs matching recent post IDs (last 3 days)
grep -o 'https://newyork.craigslist.org/[^"]*' /path/to/saved.html | grep -E '788[345]' | head -20
Use multiple read_webpage calls concurrently to fetch 5-10 interesting posts at once. This is much faster than sequential calls.
tool read_webpage , do not do alternatives like parallel curl bash commands + manual parsing.Extract the key details from each post and list each in a concise bullet. Be cheeky.