BD built-in-browser
Read this skill before the first step that uses the built-in browser, the browser pane inside the Claude desktop app (also called the in-app browser, the browser pane, Claude's browser, or "your own browser"), whose tools are named mcp__Claude_Browser__* when the session runs in the desktop app and mcp__remote-devices__Claude_Browser__* when a cloud session is linked to the person's computer; before those tools are turned on there may be a single enable__mcp__remote-devices__Claude_Browser tool instead. It covers the pane's persistent sign-ins, tabs and preview_start, reading pages as text, site approvals, what the pane cannot open, and what to do when it cannot be reached. It is not for Claude in Chrome (mcp__claude-in-chrome__* tools), which has its own skill, and it does not decide which browser to use.
Reference guide for Claude's built-in browser: how tabs work, persistent logins, reading pages as text, and what to do when the browser won't load. Promises to cover mcp__Claude_Browser__ tools (desktop) and mcp__remote-devices__Claude_Browser__ (cloud), site approvals, and pane limitations.
Checks show: B grade, 83% quality, 40% process score. No critical findings, two files. 1367 tokens—it's reference material, not a script. Compatible with Claude, Cursor, Copilot, and nine other platforms.
Install if you regularly hit browser snags in Claude or forget how to enable remote tools. If your browser just works, skip it.
Read this skill before the first step that uses the built-in browser, the browser pane inside the Claude desktop app (also called the in-app browser, the…
As a process D 40/100 · Unfinished process — weak spots: steps, result and completion, inputs and preconditions
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 40/100
- 0Steps. Prose only: no discrete steps
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1367 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 817: 120–800 characters recommended
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 9 headings
- +4Has examples (0 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.