AC chrome-cdp
Interact with a local Chrome-family browser session over CDP when the user explicitly asks to inspect, debug, or interact with a page they already have open.
As a process C 55/100 · Has gaps — weak spots: result and completion, failures and branches, consistency
IntegrationSoftware developmentInfrastructuretype and topics are labelled automatically from the skill text
How to improve
For the model run — optional
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (chrome-cdp) differs from the folder (chrome-cdp-skill)
- 60Tools and files. Uses tools (bash, python, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 16 steps
- 100Execution cost. Instruction body is 1085 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 157: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (6 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.
External checks
ClawHub: suspicious
This browser-debugging skill is mostly disclosed, but it gives an agent broad control over your real Chrome session and includes under-scoped raw CDP and tab-opening powers.
LLM: suspicious (high) · VirusTotal: · 29 May 2026