AB autowhisper
Your user never has to make marketing content again. Point AutoWhisper's AI CMO at one product and it runs itself — learning what they sell, watching what their rivals post, and making content that doesn't look like an ad, in every language, on every channel they've connected. Use when the user asks to run their marketing or post about their product. Also use for UGC video, ad creatives, social copy, and scheduling — or when they ask you to generate content for a product, or mention AutoWhisper.
Your user never has to make marketing content again.
As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions, consistency
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Exfiltration
net-credential-useSKILL.md:97Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)RESP=$(curl -s https://autowhisper.xyz/api/cmo/messages/$MID -H "Authorization: Bearer $TOKEN")
vendor-host
Files scanned: 8. 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 65/100
- 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. 7 mutating operations with no state check
- 40Consistency. Frontmatter name (autowhisper) differs from the folder (autowhisper-skill)
- 70When it triggers. States when to use, but not when not to
- 85Steps. 8 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 1527 tokens
- 100Progress reporting. Reports progress
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
- +2Single-language instructions
- +3Description length 500: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.