AB programmatic-ad-analyst
Use when the user wants to analyze, diagnose, or optimize programmatic advertising campaigns. Triggers on: "why is my CPM high", "analyze ad performance", "explain RTB bidding", "audit targeting strategy", "attribution model comparison", "ROAS optimization", "frequency capping", "audience overlap analysis", "bid strategy", "oCPM setup", "DSP/SSP selection", "viewability issues", "brand safety", or any question involving programmatic metrics, auction mechanics, or campaign diagnostics. Also triggers for Chinese market platforms: 巨量引擎, 阿里妈妈, 腾讯广告, 百度营销, oCPM, 信息流广告, 竞价广告, 程序化购买.
As a process B 69/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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
-
medium Exfiltration
intent-browser-credential-storeSKILL.md:116Accesses a browser credential / cookie store (documentation of a security skill)third-party cookies in Chrome, limited granularity
security skill
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "requirements"
Process rating: all ten parameters 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 52 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2928 tokens
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)
- +2Single-language instructions
- +5Description quotes 13 example trigger phrases
- +3Description length 583: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 52 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.