菜单
Clean Markdown extraction from any URL via markdown.new. Reduces token usage by ~80% vs raw HTML. Use when reading web pages, articles, documentation.
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
Fetch a SPECIFIC Twitter/X tweet, article, thread, profile, or timeline by URL/id via the SocialData API. Use when: a Twitter link, read a known tweet, check a profile, read a thread. For SEARCH / discovery / 'what's trending in a niche', use the `x-research` skill (Grok Live Search) instead — this skill is fetch-only.
Agentic skills framework (pcvelz fork): TDD, debugging, planning, code-review, git-worktrees, parallel agents. 15 skills with .tasks.json persistence between sessions.
Generate Excalidraw diagrams from JSON. Pipeline, mindmap, flowchart. Use when: draw diagram, visualize, architecture schema, mindmap.
Create charts, tables, and data visualizations via Datawrapper API
Web research via Perplexity Sonar API -- search, fact-check, analyze trends
Local kanban board for AI agents. Agents create/update/complete tasks, track status visually. Use when: manage tasks, kanban, create task, update status, task board.
| name | markdown-new |
| description | Clean Markdown extraction from any URL via markdown.new. Reduces token usage by ~80% vs raw HTML. Use when reading web pages, articles, documentation. |
| user-invocable | false |
Converts any webpage to clean Markdown. Reduces tokens by ~80% compared to raw HTML.
Prepend https://markdown.new/ to any URL:
curl -sL "https://markdown.new/https://example.com/article"
| Feature | Supported |
|---|---|
| Web pages | Yes |
| PDFs | Yes (OCR) |
| Images | Yes (description) |
| Audio | Yes (transcription) |
Instead of:
# Raw HTML -- wastes tokens
curl -sL "https://example.com/docs/guide"
Use:
# Clean Markdown -- 80% fewer tokens
curl -sL "https://markdown.new/https://example.com/docs/guide"
No signup required. Free service. No API key needed.
If markdown.new is down, alternatives:
https://r.jina.ai/