product-feed-optimizer

Use when the user asks to "optimize my Shopping feed", "fix product disapprovals", "improve product titles/attributes", or "build feed-driven PMax asset groups"; audits and rewrites the Shopping/Performance Max product feed — title/description patterns, required and recommended attributes, GTIN/availability/price hygiene, disapproval triage, and feed-driven asset-group / listing-group structure — informing the ROAS O (Offer) dimension. Not for text ad copy — use ad-creative-builder; not for scoring the account or the RQS — use ad-account-auditor. 商品Feed优化/购物广告Feed/商品标题优化/商品禁投修复

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, highly actionable instruction skill with clear sequencing, validation gates, and clean one-level progressive disclosure. The only weakness is moderate redundancy across the scope-boundary statements.

Suggestions

Collapse the repeated scope/negative-scope statements: keep the 'Scope guard' block and trim the duplicate 'does not write text-ad copy / does not score the account' wording from the intro paragraph and 'Next Best Skill' section.

Merge the 'Done when' criteria and the 'Quality bar before handoff' checklist into a single checklist to remove near-identical restatement of the same five conditions.

Move the long inline reads/writes/promotes enumeration in 'Skill Contract' into a compact bulleted form or a short reference to reduce wall-of-text density.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with no beginner-concept padding, but scope/negative-scope boundaries are restated three times (intro paragraph, the dedicated 'Scope guard' block, and 'Next Best Skill'), which could be consolidated.	2 / 3
Actionability	Eight numbered steps name exact required/recommended attributes, give concrete hygiene rules (check-digit, price-vs-landing-page), specify real save paths, and point to a concrete patterns file — fully actionable rather than descriptive.	3 / 3
Workflow Clarity	Clear sequenced workflow with explicit validation checkpoints: a 'Done when' gate, a 'Quality bar before handoff' checklist, and a defined NEEDS_INPUT fallback path for missing feed/diagnostics.	3 / 3
Progressive Disclosure	Body is an overview that signals one-level-deep references cleanly, including the real bundle file references/feed-title-patterns.md (verified present) plus well-organized external refs (skill-contract, roas-benchmark, humanizer-slop, SECURITY, CONNECTORS).	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 that pairs concrete capability breadth with explicit natural-language triggers and clear disambiguation from sibling skills. It hits all four dimensions at the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'audits and rewrites the Shopping/Performance Max product feed — title/description patterns, required and recommended attributes, GTIN/availability/price hygiene, disapproval triage, and feed-driven asset-group / listing-group structure' — rather than vague language.	3 / 3
Completeness	Explicitly answers both 'what' (audits/rewrites the feed across named dimensions) and 'when' via a clear 'Use when the user asks to...' trigger clause.	3 / 3
Trigger Term Quality	Embeds natural phrasings a user would actually say — 'optimize my Shopping feed', 'fix product disapprovals', 'improve product titles/attributes', 'build feed-driven PMax asset groups' — plus mirrored Chinese keywords.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche and draws explicit negative boundaries — 'Not for text ad copy — use ad-creative-builder; not for scoring the account or the RQS — use ad-account-auditor' — making mis-routing unlikely.	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: 20 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: ad/research/product-feed-optimizer/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.