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

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%Weight 40%Scale 1-5

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

The body is a well-structured, actionable QA workflow with strong progressive disclosure and validation checkpoints, held back only by repetitive restatements of the scope line across multiple sections.

Suggestions

State the 'BUILDS/FIXES vs. does NOT score R1/R2' scope line once in the intro and once at handoff; remove the repeats in steps 1, 5, and 8 to reduce token overhead.

Collapse the 'Reference Materials' list and the inline cross-skill links (CONNECTORS.md, SECURITY.md, skill-contract.md) so each external reference appears in one place rather than being re-introduced per step.

Tighten step 5 and step 8, which re-explain the attribution-reconciler routing already covered in step 5's gate description.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (no basic-concept padding), but the scope line ('BUILDS/FIXES the signal, does NOT score R1/R2') is restated in the intro, steps 1, 5, 8, and Next Best Skill, which is repetitive padding that could be tightened.	3 / 5
Actionability	Eight numbered steps give concrete, executable guidance tied to specific bundled artifacts ('walk every item in references/preflight-checklist.md', 'compare landing-page UTMs against the Traffic-acquisition source/medium rows'), with only minor gaps; as an instruction-only skill, code absence is not penalized.	4 / 5
Workflow Clarity	A clearly sequenced 8-step pre-flight process with explicit validation checkpoints (pass/fail/needs-input, 'never pass-by-default', no-test-conversion = needs-input), a referenced checklist, and feedback routing (flag and route to attribution-reconciler) matching the top anchor.	5 / 5
Progressive Disclosure	SKILL.md is a lean overview that delegates detail to two real, one-level-deep, clearly linked bundled references (preflight-checklist.md, utm-event-spec.md) listed in a Reference Materials section, with the bulk content appropriately split out and easy to navigate.	5 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

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

The description is a strong, third-person statement that covers concrete capabilities, natural trigger phrases, both the what and the when, and explicit conflict-avoidance boundaries against sibling skills.

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 'a pre-flight checklist plus a UTM/event-spec builder' — giving comprehensive, domain-specific coverage rather than vague language.	5 / 5
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 concrete trigger phrases, satisfying the top anchor.	5 / 5
Trigger Term Quality	Embeds natural phrases a user would actually say — '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' — covering synonyms and platform names comprehensively.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche and adds explicit negative boundaries — 'Not for scoring R1/R2 ... in ad-account-auditor; not for account structure — use campaign-architect' — minimizing overlap and wrong-skill triggering.	5 / 5
	Total	20 / 20 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: 14 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: ad/activate/conversion-signal-qa/SKILL.md
Commit: 5cd4a80

Reviewed: 3 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.