conversion-signal-qa

Use when the user asks to "QA my conversion tracking before launch", "check my UTMs / pixel / event firing", "set up a tracking pre-flight", or "set the dedup rule so Meta and Google stop double-counting"; builds and fixes the measurement plumbing — conversion-event firing, UTM hygiene, cross-platform dedup rules, attribution-window alignment, and offline/iOS-ATT modeled-gap flags — as a pre-flight checklist plus a UTM/event-spec builder. Not for scoring R1/R2 — that is a scored veto in ad-account-auditor; not for account structure — use campaign-architect. 付费广告转化追踪QA/UTM规范/跨平台去重

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable QA process with a clear validated workflow and clean one-level-deep bundle references. The only weakness is repeated restatement of the R1/R2 scope boundary across multiple sections, which adds tokens without adding clarity.

Suggestions

State the R1/R2-vs-ad-account-auditor scope boundary once in the opening scope line and link out; remove the restatements in steps 1, 5, and 8 to recover tokens.

Drop the duplicate scope sentence from the Skill Contract section since the opening paragraph and the Next Best Skill section already cover it.

Consider trimming the three Quick Start example prompts to two — the third largely restates the first two's intent.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept-padding, but the R1/R2 scope boundary is restated ~4–5 times (opening scope line, Skill Contract, step 1, step 5, step 8, Next Best Skill), which is verbosity that could be tightened.	2 / 3
Actionability	Concrete, executable guidance throughout — e.g. "have the user complete one real conversion and confirm it appears in the GA4 Conversions export with the right event name, value, and source/medium" and "compare landing-page UTMs against the Traffic-acquisition source/medium rows; flag missing, inconsistent-case, or auto-tagging-vs-manual collisions" — with explicit pass/fail/needs-input decision rules.	3 / 3
Workflow Clarity	A clear 8-step numbered sequence with explicit validation checkpoints (step 3: no test conversion = needs-input; step 5: yes/no/needs-input gate, not a recount; step 6: modeled gap is a flag, not a fail) plus a "Done when" completion checklist and a routing feedback loop for non-reconciling numbers.	3 / 3
Progressive Disclosure	SKILL.md is an overview pointing one-level-deep to real, well-signaled bundle files — references/preflight-checklist.md ("the full tracking pre-flight checklist") and references/utm-event-spec.md ("UTM naming convention + conversion-event spec builder") — with detail appropriately split out and a Reference Materials index.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description with explicit "Use when…" triggers, concrete capabilities, and explicit boundary carve-outs against sibling skills. The trailing bilingual summary is slightly redundant but does not weaken any dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "conversion-event firing, UTM hygiene, cross-platform dedup rules, attribution-window alignment, and offline/iOS-ATT modeled-gap flags" — plus concrete deliverables ("a pre-flight checklist plus a UTM/event-spec builder"), matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both what ("builds and fixes the measurement plumbing … as a pre-flight checklist plus a UTM/event-spec builder") and when ("Use when the user asks to …") with explicit triggers; not missing either half.	3 / 3
Trigger Term Quality	Quotes natural user phrasings — "QA my conversion tracking before launch", "check my UTMs / pixel / event firing", "set up a tracking pre-flight", "set the dedup rule so Meta and Google stop double-counting" — exactly what a user would say; good coverage.	3 / 3
Distinctiveness Conflict Risk	Actively carves out its niche — "Not for scoring R1/R2 — that is a scored veto in ad-account-auditor; not for account structure — use campaign-architect" — giving it a clear, non-conflicting trigger space.	3 / 3
	Total	12 / 12 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 12 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: ad/activate/conversion-signal-qa/SKILL.md
Commit: 4a77c48

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.