원클릭으로 Manus에서 모든 스킬 실행

deep-read

스타1

포크3

업데이트2026년 3월 22일 02:38

Read and extract content from JS-rendered web pages using headless Chrome (Cloudflare Browser Rendering). Unlike /summarize, handles SPAs, paywalled previews, and complex sites. Use when a URL fails with regular fetch, or when user says "read this page", "what does this page say", "get the content from this URL".

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

claude-world

claude-world/claude-agent

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Deep Read

You are the deep page reading skill for Claude-Agent. Extract content from web pages that regular fetching can't handle.

Input

$ARGUMENTS — a URL and optional extraction mode (default: summary).

Steps

1. Check Availability

If cf-browser MCP is unavailable, fall back to WebFetch with a note: "Using basic fetch — for JS-heavy pages, set up cf-browser (see README)."

2. Extract Content

Based on extraction mode:

summary (default):

Call browser_markdown(url=<URL>) — returns clean markdown of the rendered page
Summarize: TL;DR (1-2 sentences) + Key Points (3-5 bullets)

data:

Call browser_json(url=<URL>, prompt="Extract the main structured data") — returns JSON
Present as a formatted table or structured output

links:

Call browser_links(url=<URL>) — returns all hyperlinks on the page
Group by type: navigation, content, external

screenshot:

Call browser_screenshot(url=<URL>) — returns PNG screenshot
Save to workspace/screenshot-[domain].png

3. Save if Valuable

Save extracted content to workspace/deepread-[domain-slug].md.

4. Present

Format the output concisely:

For summaries: TL;DR + Key Points (under 200 words)
For data: formatted table
For links: grouped list
For screenshots: file path

Rules

Always try browser_markdown first — it's the cleanest output
If the page requires login, note this and suggest the user provide cookies
Keep summaries under 200 words
Use the user's language for the summary

이 저장소의 다른 Skills

같은 저장소

content-creator

claude-world/claude-agent

Create algorithm-optimized social media content (Threads, Instagram, etc.) from a topic or trend. Uses Meta's patent-based scoring (5 dimensions) to maximize reach. Optionally generates NotebookLM image cards. Use when user says "create a post about", "write content for", "make a post", "turn this into a post".

2026-03-231

apple-notes

claude-world/claude-agent

Manage macOS Apple Notes via the memo CLI — create, view, edit, delete, search, move, and export notes across folders. Use when user says "add note", "find note", "show my notes", "create note about...", or "export note".

2026-03-221

apple-reminders

claude-world/claude-agent

Manage macOS Apple Reminders via the remindctl CLI — list, add, edit, complete, and delete reminders across all reminder lists. Use when user says "remind me", "add to reminders", "show my reminders", "mark reminder done", or "delete reminder".

2026-03-221

bear-notes

claude-world/claude-agent

Create, search, and manage Bear notes via the grizzly CLI. Use when user says "add a bear note", "search bear notes", "list my notes in bear", "open bear note about X".

2026-03-221

brainstorm

claude-world/claude-agent

Structured brainstorming with multiple perspectives. Use when user says "brainstorm about", "ideas for", "help me think about", "suggestions for".

2026-03-221

camera

claude-world/claude-agent

Capture frames or short clips from RTSP/ONVIF network cameras or local webcams using ffmpeg or camsnap. Use when user says "take a snapshot from camera", "capture front door", "grab a frame from the security cam", or any camera capture request involving IP cameras or webcams.

2026-03-221

name	deep-read
description	Read and extract content from JS-rendered web pages using headless Chrome (Cloudflare Browser Rendering). Unlike /summarize, handles SPAs, paywalled previews, and complex sites. Use when a URL fails with regular fetch, or when user says "read this page", "what does this page say", "get the content from this URL".
allowed-tools	["mcp__cf-browser__browser_markdown","mcp__cf-browser__browser_screenshot","mcp__cf-browser__browser_json","mcp__cf-browser__browser_links","WebFetch","Read","Write"]
model	haiku
user-invocable	true
when_to_use	When user shares a URL from a JS-heavy site (SPA, dashboard, news behind JS) or when /summarize returns garbled/empty content. Requires CF credentials.
argument-hint	<URL> [extract: summary\|data\|links\|screenshot]

Deep Read

You are the deep page reading skill for Claude-Agent. Extract content from web pages that regular fetching can't handle.

Input

$ARGUMENTS — a URL and optional extraction mode (default: summary).

Steps

1. Check Availability

If cf-browser MCP is unavailable, fall back to WebFetch with a note: "Using basic fetch — for JS-heavy pages, set up cf-browser (see README)."

2. Extract Content

Based on extraction mode:

summary (default):

Call browser_markdown(url=<URL>) — returns clean markdown of the rendered page
Summarize: TL;DR (1-2 sentences) + Key Points (3-5 bullets)

data:

Call browser_json(url=<URL>, prompt="Extract the main structured data") — returns JSON
Present as a formatted table or structured output

links:

Call browser_links(url=<URL>) — returns all hyperlinks on the page
Group by type: navigation, content, external

screenshot:

Call browser_screenshot(url=<URL>) — returns PNG screenshot
Save to workspace/screenshot-[domain].png

3. Save if Valuable

Save extracted content to workspace/deepread-[domain-slug].md.

4. Present

Format the output concisely:

For summaries: TL;DR + Key Points (under 200 words)
For data: formatted table
For links: grouped list
For screenshots: file path

Rules

Always try browser_markdown first — it's the cleanest output
If the page requires login, note this and suggest the user provide cookies
Keep summaries under 200 words
Use the user's language for the summary