AF cdp-gmail-delivery
Send Gmail messages from an operator-controlled Chrome debug session using Gmail CDP automation. Use when the user asks to send email from the local machine, with or without an attachment. Default assumption: Chrome CDP is already installed and available. If the CDP endpoint is unavailable, ask the human operator to help restart the debug Chrome session, then send, and verify in Sent by unique subject.
As a process F 56/100 · Will not run — References files that are not bundled: scripts/restart_debug_chrome.sh, scripts/xrdp_chrome_debug_setup.sh
How to improve
- The text references files that are not there: add them or drop the references.
- 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
- warning
missing-refreference to a missing file: scripts/restart_debug_chrome.sh - warning
missing-refreference to a missing file: scripts/xrdp_chrome_debug_setup.sh
Process rating: all ten parameters 56/100
- 0Tools and files. 2 referenced file(s) missing: scripts/restart_debug_chrome.sh, scripts/xrdp_chrome_debug_setup.sh
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 16 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 71 steps
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1709 tokens
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 405: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 71 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (2 of 3)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.