AC chrome-browser
Read this skill before the first step that uses Claude in Chrome, the browser extension whose tools are named mcp__claude-in-chrome__* (also called Chrome, the browser extension, or the external browser) and which acts in the person's real Chrome with their own sign-ins; before those tools are turned on there may be a single enable__mcp__claude-in-chrome tool instead. It covers loading the tools in one ToolSearch call, checking the person's open tabs and working in a new tab, site permissions, GIF recordings, console logs, dialogs to avoid, and when to stop and ask. It is not for the built-in browser (mcp__Claude_Browser__* or mcp__remote-devices__Claude_Browser__* tools), which has its own skill, and it does not decide which browser to use.
This skill teaches how to work with the Claude in Chrome extension—the one that connects to the user's real browser with their sessions and permissions. Promises to cover tool loading, checking open tabs, site permissions, and GIF recording. The files contain 1219 tokens of instructions with no critical errors. Quality score 89 shows clear documentation, but process score 61 hints at structural gaps—likely not all edge cases covered. The extension runs on most platforms, including Claude and Cursor.
In practice, the skill helps if you frequently ask the agent to click links, fill forms, or screenshot pages without pasting code. The catch: you need to remember when to stop and ask permission. Install it if you often give your agent browser tasks and want it to work with your actual sites.
Read this skill before the first step that uses Claude in Chrome, the browser extension whose tools are named mcpclaude-in-chrome (also called Chrome, the…
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 61/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. No external tools needed
- 100Steps. 11 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1219 tokens
- 100Progress reporting. Reports progress
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
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 751: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 11 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.