hexbee/hello-skills

doko-page-reader

Read and extract content from web pages through a locally connected Chrome browser using Dokobot local bridge only.

First seen Apr 7, 2026

Installation

$ npx skills add hexbee/hello-skills --skill doko-page-reader

Summary

  • Read and extract content from web pages through a locally connected Chrome browser using Dokobot local bridge only.
  • Use when an agent needs JavaScript-rendered pages, logged-in browser content, or pages that block headless scrapers and should be handled entirely through the user's local browser.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from hexbee/hello-skills · top by installs.

npx skills add hexbee/hello-skills

Browse all from hexbee/hello-skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 2
Default branch main
Open issues 0
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,088 B
  • docs SUMMARY.md 320 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 18 installs

SKILL.md

Dokobot Local

Use Dokobot only through the local bridge and the user's Chrome session.

Prerequisites

  • Ensure dokobot CLI is installed.
  • Ensure Chrome is open with the Dokobot extension enabled.
  • Ensure the local bridge is installed with dokobot install-bridge.
  • Prefer local browser reading when the page needs JavaScript, an authenticated browser session, or a real browser to bypass bot friction.

Core workflow

  1. Read the page in local mode:
dokobot read '<URL>' --local
  1. If the read fails because no local browser is available, tell the user to open Chrome, enable the Dokobot extension, and verify the local bridge is installed.
  1. For long pages, collect more screens or extend timeout:
dokobot read '<URL>' --local --screens 5 --timeout 120
  1. When the response includes a sessionId and more scrolling is needed, continue the same session:
dokobot read '<URL>' --local --session-id <SESSION_ID> --screens 5
  1. Close the session when finished:
dokobot doko close <SESSION_ID> --local

Commands

Read a page

Use:

dokobot read '<URL>' --local [--screens N] [--timeout S] [--format text|chunks] [--reuse-tab]

Notes:

  • Always include --local.
  • Use --screens N to scroll and capture more content.
  • Use --timeout S for slow pages.
  • Use --format chunks only when segmented content is needed.
  • Use --reuse-tab to avoid opening a new tab for the same URL.

Default text response shape:

{
  text?: string
  sessionId: string
  canContinue: unknown
}

Chunked response shape:

{
  text?: string
  chunks: Array<{
    id: string
    sourceIds: Array<string>
    text: string
    bounds: [number, number, number, number]
    zIndex?: number
    containerId?: string
  }>
  sessionId: string
  canContinue: unknown
}

Operating rules

  • Treat this skill as local-only.
  • Keep the command surface minimal: use only read --local and doko close --local.
  • Analyze and summarize content after receiving the raw page text; keep Dokobot focused on extraction.
  • Close sessions explicitly when you are done.
  • Keep concurrent reads modest; up to 5 parallel reads is a reasonable ceiling.

Troubleshooting

  • No registered devices. or similar local-connection failures: Ask the user to open Chrome, enable the Dokobot extension, and confirm the local bridge is installed.
  • 503: Treat it as no local extension/device available and check the local setup.
  • 504: Retry with a larger timeout or fewer screens.
  • 422: Treat it as a cancelled or failed local read and retry if appropriate.

Security

  • Keep usage local to the user's browser session.
  • Treat read as read-only extraction.