Use My Browser

Do not treat this skill as a generic browsing default. Route from the evidence you need, not from tool preference.

Every task must be classified before you choose a route:

• static-capable: the evidence can be produced without live browser state, visible confirmation, or page interaction
• browser-required: the evidence depends on rendered state, interaction, live session behavior, or browser-only structures

Only static-capable tasks may fall back to static retrieval, curl, or other non-browser paths. Once a task is browser-required, stay on the browser path and mark missing capability as blocked instead of silently downgrading.

Prerequisite check

This skill is for work inside the user's live browser session, not for launching a separate fresh automation browser.

Before doing browser automation, confirm that your environment already has access to a live browser stack that can provide the capabilities the task depends on.

Treat as browser-required by default

• localhost, 127.0.0.1, or benchmark-style local fixtures
• uploads, downloads, drag-and-drop, hover, keyboard-native entry, or visible confirmation states
• same-origin iframe inspection, Shadow DOM inspection, details / collapsed evidence, or lazy-loaded content
• any task where "what the page visibly shows" is itself the evidence

Decision guide

1. Decide whether the task is static-capable or browser-required
2. If static-capable: stay on the cheapest route that still satisfies the evidence target
3. If browser-required: load the browser playbook reference
4. If browser-required capability is uncertain: check the browser capability matrix
5. If the user has an active browser debugging context: prefer handoff from that context

Hard rules

• Use browser interaction only when live browser state is part of the evidence or required action
• Once a task is browser-required, do not silently downgrade
• Prefer site-generated DOM links over hand-built URLs
• Prefer MCP-native actions over script-driven interaction
• Only close pages you created
• Do not use curl, Invoke-WebRequest, or shell HTTP fetches for browser-required tasks
• Do not treat a generic page-opening tool as evidence that localhost deep interaction is available

Experience loop

For browser-required work:

1. Check if a matching note exists under references/site-patterns/ for the target domain
2. If a note exists, read it before the first meaningful browser mutation
3. During the run, watch for verified site-specific facts
4. Before finishing, decide whether the run produced a reusable fact and update the note

Mirrored from https://github.com/xixu-me/skills — original author: xixu-me, license: MIT. This is an unclaimed mirror. Content and ownership transfer to the author when they claim this account.