AB gsk-phone-outreach
Use when making an AI phone call with gsk to get something done in the real world that is bigger than one dial — booking a restaurant/bar table, negotiating a bill down, ordering from one of many vendors in an area, or any goal where the call needs upfront research, real outbound calls to businesses, retries, fallbacks, and approval before committing. Also when the request is a range ("call around / find the best / cheapest"), or the outreach needs scheduling, waiting, calling around to many candidates, or monitoring across time.
As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5015 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Execution cost. Instruction body is 5015 tokens
- 100Steps. 34 steps
- 100Failures and branches. 13 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (5 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
- +1No license
- +2Single-language instructions
- +3Description length 535: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.