AB converly
Set up server side conversion tracking for ad platforms (Google Ads, Meta, ChatGPT, LinkedIn, TikTok and more) without writing tracking code. Use this whenever the user wants to track form submissions, meetings booked or chats started as conversions, capture GCLID or FBCLID click IDs, fix broken conversion tracking, set up Google Enhanced Conversions or Meta CAPI, check which ads are converting, or connect a form tool like Typeform, Webflow forms, or a custom HTML form to an ad platform, even if they never mention Converly by name.
Set up server side conversion tracking for ad platforms (Google Ads, Meta, ChatGPT, LinkedIn, TikTok and more) without writing tracking code.
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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5673 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 66/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5673 tokens
- 100Steps. 37 steps
- 100Failures and branches. 6 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
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (9 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
- +2Single-language instructions
- +3Description length 537: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (18 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.