skills/doko-page-reader/SKILL.md
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.
npx skillsauth add hexbee/hello-skills doko-page-readerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use Dokobot only through the local bridge and the user's Chrome session.
dokobot CLI is installed.dokobot install-bridge.dokobot read '<URL>' --local
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.
For long pages, collect more screens or extend timeout:
dokobot read '<URL>' --local --screens 5 --timeout 120
sessionId and more scrolling is needed, continue the same session:dokobot read '<URL>' --local --session-id <SESSION_ID> --screens 5
dokobot doko close <SESSION_ID> --local
Use:
dokobot read '<URL>' --local [--screens N] [--timeout S] [--format text|chunks] [--reuse-tab]
Notes:
--local.--screens N to scroll and capture more content.--timeout S for slow pages.--format chunks only when segmented content is needed.--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
}
read --local and doko close --local.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.read as read-only extraction.testing
Diagnose and fix Docker image pull failures on macOS with OrbStack, especially Docker Hub EOF/TLS/manifest errors caused by system proxies, Clash/CyberClash/Mihomo/Surge-style TUN mode, fake-ip DNS such as 198.18.0.x, or unstable registry access. Use when `docker pull` or `docker manifest inspect` fails with EOF, SSL_ERROR_SYSCALL, failed to fetch anonymous token, failed to resolve reference, failed to copy, or registry-1.docker.io/auth.docker.io connectivity confusion.
development
Generate and revise job resumes from raw notes, existing resumes, career histories, or profile snippets. Use when Codex needs to create, redesign, tighten, or review a resume/CV, especially for Chinese or English A4 resumes, PDF/HTML output, first-screen hiring signal, skill ordering, pagination balance, header/contact layout, or reframing an engineering background for AI-focused roles.
development
Convert a public webpage URL into Markdown and save it as a reusable `.md` file with the bundled script. Prefer `https://r.jina.ai/<url>` first, and only fallback to `https://markdown.new/` if `r.jina.ai` is unavailable. Use this whenever the user wants to turn a public webpage, article, documentation page, blog post, release note, or reference URL into Markdown for reading, archiving, summarizing, extraction, RAG prep, or downstream agent reuse, even if they do not explicitly mention markdown or saving a file.
tools
Design agent-usable SaaS tool systems using six reusable tool shapes (Search, Summarize, Draft, Update, Notify, Approve) plus connectors and policy guardrails. Use when turning SaaS features into reliable agent actions with clear contracts, permissions, audit trails, and approval gates.