attribution-reconciler

Use when platform-reported conversions disagree with GA4/ecommerce, when you suspect Meta and Google are double-counting the same sales, or for a standing (monthly) reconciliation workbook that de-dups stacked credit against an order-ID truth set, normalizes attribution windows and currency, compares attribution models, and reads incrementality from a geo/holdout test. Not for the point-in-time R2 veto or RQS gate — use ad-account-auditor; not for the ROI/ROAS ratio math itself — use roi-calculator; not for organic dark-social share attribution or GA4 direct-traffic decomposition — use dark-social-attributor. 付费广告归因对账/去重/增量

Quality

94%

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

88%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 instruction-only skill with a clear validated workflow and good reference navigation. The main weakness is noticeable restatement of the truth-set and delegation rules across sections, which costs conciseness, and the absence of bundle files limits progressive disclosure.

Suggestions

Consolidate the order-ID truth-set rule and the 'hand ratios to roi-calculator' delegation into a single authoritative statement; reference it from other sections instead of restating it.

Move the inline Skill Contract / Handoff Summary shape detail into a referenced file (or confirm the external skill-contract.md reference) so the body stays a lean overview.

If detailed attribution-model comparison logic or normalization tables exist, split them into a bundle file under references/ and link one level deep rather than keeping everything inline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept filler, but the order-ID truth-set rule and the 'hand ratios to roi-calculator' point are each restated across the intro, Skill Contract, and Instructions, which could be trimmed.	4 / 5
Actionability	Concrete, executable guidance with specific decision rules and formulas (join on order ID or timestamp+value fallback; incremental orders ÷ exposed; convert to one currency at a stated rate) covering the common cases.	5 / 5
Workflow Clarity	A 7-step numbered sequence with an explicit validate/stop checkpoint (Step 1 NEEDS_INPUT, no reconciliation without the truth set) and clear 'Done when' criteria.	5 / 5
Progressive Disclosure	Good overview structure with a clearly signaled one-level-deep Reference Materials section, but no bundle files are present and a couple references point outside the skill, leaving minor organization gaps.	4 / 5
	Total	18 / 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 specific, trigger-rich, complete, and sharply distinguished from sibling skills via explicit negative boundary clauses. It is a strong, concise trigger description that covers the workflow comprehensively.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — de-dups stacked credit against an order-ID truth set, normalizes attribution windows and currency, compares attribution models, reads incrementality from a geo/holdout test — covering the workflow comprehensively.	5 / 5
Completeness	Explicitly answers both what (reconciliation/de-dup/normalize/compare/incrementality workbook) and when via an explicit 'Use when…' trigger clause, plus negative boundary guidance.	5 / 5
Trigger Term Quality	Includes natural user phrases ('platform-reported conversions disagree with GA4/ecommerce', 'double-counting the same sales', 'monthly reconciliation') with concrete platform names and synonyms.	5 / 5
Distinctiveness Conflict Risk	Carves out a clear niche with explicit 'Not for…' routes to ad-account-auditor, roi-calculator, and dark-social-attributor, minimizing conflict risk.	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: 21 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: ad/scale/attribution-reconciler/SKILL.md
Commit: 888dd38

Reviewed: 5 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.