CD conversion-tracking
Set up, audit, verify, or fix website conversion tracking. Use when the conversion is a form submission, booked meeting, chat, phone call, signup, or purchase; when conversions must reach Google Ads, Meta, GA4, LinkedIn, TikTok, or Microsoft Ads; when the work involves GTM tags and dataLayer events, pixels, the Conversions API (CAPI), Enhanced Conversions, server-side tagging, or gclid and fbclid capture; or when the user reports conversion problems like "conversions stopped", "double counting", "spend but no conversions", "GA4 and Google Ads don't match", or an Unverified or Inactive status. Covers lead gen and ecommerce. Always fire on confirmed success, never the submit click; verify a test conversion arrives; diagnose before changing anything; offer free and native paths alongside paid ones and disclose partner tools. For tracking plans and UTMs, see analytics. For attribution models, see attribution. For campaigns and bidding, see ads. For CRM lead-stage design, see revops.
Promises to handle conversion tracking setup: GTM tags, pixel verification, data flow to Google Ads, Meta, GA4, and other platforms. Covers forms, calls, purchases, and lead gen.
Contains 75 files and 28 scripts, but has broken references and missing files. Grade C: quality score 71, process score 49. No critical findings, four medium-to-low severity issues. Not run on models, no sandbox testing. Safety score 96.
Install if you can tolerate incomplete file structure and will verify instructions against current platform documentation before deploying to live accounts.
Set up, audit, verify, or fix website conversion tracking.
As a process D 49/100 · Unfinished process — References files that are not bundled: assets/snippets/{tool}.js
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 4
✓ No critical or high findings
Medium and low: 4
-
low Secrets in code
secret-high-entropy-tokenassets/gtm-recipes/detect/detect-cal-com.json:32High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"value": "<script>\n(function () {\n 'use strict';\n if (window.__ctDetectCalcom) return;\n window.__ctDetectCalcom = true;\n window.dataLayer = window.dataLayer || [];\n\n // Cal.com's embed codquoted -
low Secrets in code
secret-high-entropy-tokenassets/gtm-recipes/detect/detect-formidable-forms.json:32High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"value": "<script>\n(function () {\n 'use strict';\n\n // Shared with the recipe snippet so template + recipe installation is one listener.\n if (window.__ctDetectFormidableForms) return;\n windowdetector -
low Secrets in code
secret-high-entropy-tokenassets/snippets/cal-com.js:84High-entropy token-like string (may be an id, hash or a credential)// Only a completed new booking. Reschedules (resc…lV2)
-
low Secrets in code
secret-high-entropy-tokenassets/snippets/formidable-forms.js:13High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)var MARKER_KEY = '__ct…gV2';
detector
Files scanned: 74. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7482 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: assets/snippets/{tool}.js - note
edit-residuethe text marks something as outdated (lines 38): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 49/100
- 0Tools and files. 1 referenced file(s) missing: assets/snippets/{tool}.js
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 30 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 7482 tokens
- 100Steps. 27 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
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 993: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 12 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.