mbfinotti/advertising-skills / skills/ad-conversion-tracking
ad-conversion-tracking
VerifiedVerify that conversion events are correctly configured, firing once, and deduplicated before a paid campaign launches, then turn the evidence into a GO / NO-GO decision. Covers tag debugging, test conversion tracing, browser/server event deduplication (including Conversions API setups), value and currency checks, conversion action status, consent handling, and test-data exclusion. Use whenever the user asks if their tracking works, mentions a pixel or tag check, conversions not showing up, duplicate conversions, or a pre-launch checklist - even if they never say 'conversion tracking'. Covers B2B lead gen and B2C ecommerce on any ad platform. Do NOT use to reconcile platform vs CRM numbers after launch - use mbfinotti/advertising-skills@ad-attribution-gap instead.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 29.1 KB |
| evals/evals.json | config | 20.9 KB |
| references/output-report-example.md | markdown | 2.0 KB |
references/output-report-example.md
View on GitHub# Output report - worked example
A full worked pre-launch tracking verification report, showing a NO-GO decision blocked on a deduplication defect.
```
PRE-LAUNCH TRACKING VERIFICATION - <campaign>, <date>
platform(s): <...> | funnel: B2B | B2C | both | server-side: yes/no
launch: <date> | budget at risk: <amount>
check result impact fix effort evidence
1 settings & designation pass - - 1 primary action = purchase; count-once n/a
2 tag debug pass - - tag fired once, on confirmation only
3 test conversion pass - - order #QA-1042, click ID present end to end
4 payload inspection pass - - value 4.90, currency EUR, event ID = order ID
5 platform UI + status pass - - event visible; status: recording
6 deduplication fail critical a few days (dev) server event ID differs; 2 conversions counted
7 test-data exclusion pass - - filter ACTIVE; QA order refunded, conv. retracted
8 soak unknown - - starts after fix
9 sign-off - - - blocked by check 6
dedup rate : 0% (target ≥ ~90%)
gaps : platform vs analytics n/a | analytics vs backend n/a | server vs browser n/a
DECISION: NO-GO
fix order : shared event ID (only blocker at or above the default rung)
blockers : shared event ID missing server-side (fix owner: dev team)
deferred : click-identifier chain across the checkout domain - risk-accepted by <name>,
hard launch date, revisit post-launch
deleted : consent path - no consent-regulated traffic in scope (not applicable)
re-verify : full sequence from step 3 after fix ships, then GO decision
approver : <name> date: <date>
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |