AC ad-intelligence
Competitive ad intelligence skill for fetching, analyzing, and reporting on competitor ads across Meta (Facebook/Instagram), Google Ads Transparency Center, and LinkedIn Ad Library. Use this skill whenever a user asks about competitor ads, what ads a brand is running, ad creative analysis, ad copy research, campaign monitoring, ad library lookups, or marketing intelligence on any of these platforms. Also trigger for phrases like "what ads is [company] running", "spy on competitor ads", "find ads from [brand]", "check ad library", "pull ad data", "analyze competitor campaigns", or any request involving scraping or fetching public ad data from Meta, Google, or LinkedIn. This is a two-phase skill — Phase 1 uses web scraping (no API keys needed), Phase 2 unlocks deeper data via official and third-party APIs.
As a process C 53/100 · Has gaps — 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 · 0
✓ No critical or high findings
Files scanned: 5. 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 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (ad-intelligence) differs from the folder (ad-intelligence-skill)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 25 steps
- 100Execution cost. Instruction body is 1426 tokens
- 100Running it twice. No mutating operations
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)
- +3Description length 815: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -243 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 12 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.