AB safari-browser-control
Control the user's real Safari browser on macOS using AppleScript and screencapture. Read pages, click elements, type text, take screenshots, navigate tabs — all through the user's actual browser session with their cookies and logins. Zero dependencies, pure macOS native. Triggers on keywords like "safari", "browser", "web page", "open tab", "screenshot the page", "read this site", "browse", "click on", "fill in the form".
As a process B 68/100 · Nearly there — weak spots: result and completion, progress reporting
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 68/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash) 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
- 85Steps. 11 steps, 1 vague phrases
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3097 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +3Description length 426: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 11 items
- +4Has examples (22 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.