AC peekaboo-macos-automation
Use Peekaboo for macOS desktop GUI automation, screen understanding, and MCP-backed local app control. Trigger when the user wants to inspect or control native macOS apps, Finder, Notes, Xcode, Terminal, system dialogs, menu bar items, Dock, Spaces, or other non-browser UI; when they ask to click, type, scroll, drag, switch apps, handle popups, or automate a desktop workflow on Mac; or when they explicitly mention Peekaboo. If Peekaboo is missing, detect that first and proactively install it for the user, then continue. Prefer this over browser automation for native macOS interfaces.
As a process C 62/100 · 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: 7. 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 62/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 51 steps, 1 vague phrases
- 100Failures and branches. 11 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1302 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
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
- -34 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 590: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.