conversion-value-mapper

Use when the user asks to "set up conversion values so tROAS optimizes profit not orders", "map margin onto my purchase value", "build value rules for lead / phone / signup conversions", or "stop bidding to revenue when I care about profit"; defines and QAs the conversion VALUE model — per-conversion values, margin/net-value adjustment, static-vs-dynamic value rules, proxy values for non-revenue actions, and a value-vs-count sanity check — as a value-model spec plus a pre-launch value QA sheet. Not for whether the tag fires or UTMs are clean — use conversion-signal-qa; not for cross-platform double-count de-dup — use attribution-reconciler; not for scoring R1/R2 — that is a scored veto in ad-account-auditor. 付费广告转化价值建模/利润出价/价值规则QA

Quality

83%

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

67%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.

A well-organized, actionable instruction skill with explicit formulas, decision rules, and a clear 8-step workflow with validation gates. It is held back from the top band mainly by repetitive scope restatements and the lack of a concrete worked example or QA-sheet template.

Suggestions

Consolidate the scope line (tag-fires vs value vs R1/R2 routing) to a single statement instead of restating it in the intro, step 1, step 7, and the termination section.

Add a short worked numeric example for net_value and proxy_value derivation, or ship a value-model spec template as a bundled reference file the body links to.

Make the value-vs-count reconciliation step a validate→fix→retry loop (e.g., on mismatch, name the gap and re-run after the margin/proxy fix) to reach the top workflow-clarity band.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the scope line is restated multiple times (body intro, step 1, step 7, termination) and the Skill Contract/Instructions overlap noticeably, adding tokens that could be tightened.	3 / 5
Actionability	Concrete formulas (net_value = revenue × margin, proxy_value = avg_order_net_value × lead→sale close_rate), explicit value labels (Measured/User-provided/Estimated), and named decision rules give mostly executable guidance; minor gaps are the absence of worked numeric examples and a sample spec/QA-sheet template.	4 / 5
Workflow Clarity	An 8-step numbered sequence with explicit validation/reconciliation gates (needs-input flags, value-vs-count reconciliation, launch-readiness verdict) and clear handoff; just short of a 5 because reconciliation and launch-readiness lack explicit fix-and-retry feedback loops.	4 / 5
Progressive Disclosure	Good structure with well-signaled one-level-deep references (CONNECTORS.md, SECURITY.md, skill-contract.md, sibling skills); however the body has no bundle files (no references/scripts/assets dirs) and inlines some content that could live in a template file, leaving minor organization gaps.	4 / 5
	Total	15 / 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.

An exceptionally well-constructed description: it answers what and when concretely, uses natural user trigger phrasings, and draws sharp boundaries against three sibling skills. Verbosity and the appended Chinese summary are the only minor costs.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: per-conversion values, margin/net-value adjustment, static-vs-dynamic value rules, proxy values for non-revenue actions, and a value-vs-count sanity check — comprehensive coverage of the value-model domain.	5 / 5
Completeness	Explicitly answers both what (defines and QAs the conversion VALUE model, enumerated components) and when (a leading 'Use when the user asks to...' clause with concrete trigger phrases).	5 / 5
Trigger Term Quality	Quotes natural user phrasings verbatim ('set up conversion values so tROAS optimizes profit not orders', 'map margin onto my purchase value', 'stop bidding to revenue when I care about profit') plus domain terms (tROAS, max-conversion-value, GA4), giving comprehensive natural-language coverage.	5 / 5
Distinctiveness Conflict Risk	Clear niche (conversion VALUE model) with explicit negative scope lines routing sibling concerns to conversion-signal-qa, attribution-reconciler, and ad-account-auditor, minimizing 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: 18 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: ad/activate/conversion-value-mapper/SKILL.md
Commit: 888dd38

Reviewed: 6 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.