CtrlK
BlogDocsLog inGet started
Tessl Logo

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

69

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

81%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-structured, actionable workflow with strong validation checkpoints and a real one-level reference file. Slight gains available from deduplicating the scope/quality statements and tightening a few high-level verbs.

Suggestions

Consolidate the repeated scope/distinctiveness statements (intro, Skill Contract, Scope guard, Next Best Skill) into one canonical block to remove redundancy and save tokens.

Merge the 'Done when' and 'Quality bar' sections into a single handoff checklist so the acceptance criteria are stated once.

Tighten high-level verbs ('profile', 'triage') into explicit sub-steps or reference the concrete triage table format already implied by the contract.

DimensionReasoningScore

Conciseness

Dense and assumes Claude's competence (no primer on what a Shopping feed is), but the scope/distinctiveness is restated across the intro, Skill Contract, Scope guard, and Next Best Skill, and the Quality bar mirrors the 'Done when' criteria — minor redundancy that could be trimmed.

4 / 5

Actionability

Concrete, specific guidance throughout — exact required/recommended attribute lists, the front-load pattern, named memory paths, and a real patterns reference — though a few directives ('profile', 'triage') remain high-level rather than step-executable.

4 / 5

Workflow Clarity

An 8-step numbered sequence with explicit validation checkpoints — NEEDS_INPUT branch, per-item '[needs source]' flagging, 'Done when' criteria, and a 'Quality bar' checklist that acts as a feedback loop before handoff.

5 / 5

Progressive Disclosure

Clean sectioned overview that signals the one in-bundle reference (references/feed-title-patterns.md, which exists) at one level deep, but many body links point to out-of-bundle files (../../../references/roas-benchmark.md, CONNECTORS.md, etc.) whose presence cannot be verified here.

4 / 5

Total

17

/

20

Passed

Description

92%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.

A strong, third-person description with concrete capabilities, explicit trigger phrases, and clear boundaries against sibling skills. Minor scope to add file-extension synonyms for fuller trigger coverage.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'audits and rewrites', 'title/description patterns', 'GTIN/availability/price hygiene', 'disapproval triage', 'asset-group / listing-group structure' — covering the domain comprehensively.

5 / 5

Completeness

Explicitly answers both 'what' (audits and rewrites the feed across the listed dimensions) and 'when' (Use when the user asks to…) with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural quoted phrases users would say ('optimize my Shopping feed', 'fix product disapprovals', 'improve product titles/attributes', 'build feed-driven PMax asset groups') but omits file-extension/synonym terms (TSV/CSV/XML) that live only in other frontmatter fields.

4 / 5

Distinctiveness Conflict Risk

States a clear niche and explicitly excludes adjacent skills ('Not for text ad copy — use ad-creative-builder; not for scoring the account or the RQS — use ad-account-auditor'), minimizing mis-trigger risk.

5 / 5

Total

19

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.