AF 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
audits and rewrites the Shopping/Performance Max product feed — title/description patterns, required and recommended attributes, GTIN/availability/price…
As a process F 45/100 · Will not run — References files that are not bundled: ../../../protocol/offer-claims-registry/SKILL.md, ../../activate/ad-account-auditor/SKILL.md, ../../../references/skill-contract.md
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
low Concealment
en-hide-from-userSKILL.md:61Instruction to hide actions from the user (negated — the text forbids it)6. **Pre-check claims and policy** — flag any superlative/guarantee/health-or-finance claim in a title or description that needs substantiation (O1) and any prohibited-category, trademark, or restrict
negated
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 584 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
missing-refreference to a missing file: ../../../protocol/offer-claims-registry/SKILL.md - warning
missing-refreference to a missing file: ../../activate/ad-account-auditor/SKILL.md - warning
missing-refreference to a missing file: ../../../references/skill-contract.md - warning
missing-refreference to a missing file: ../../../CONNECTORS.md - warning
missing-refreference to a missing file: ../../../SECURITY.md - warning
missing-refreference to a missing file: ../../../references/humanizer-slop.md - warning
missing-refreference to a missing file: ../../orchestrate/ad-creative-builder/SKILL.md - warning
missing-refreference to a missing file: ../../../influencer/report/landing-optimizer/SKILL.md - warning
missing-refreference to a missing file: ../../../references/roas-benchmark.md - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "summary" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 45/100
- 0Tools and files. 9 referenced file(s) missing: ../../../protocol/offer-claims-registry/SKILL.md, ../../activate/ad-account-auditor/SKILL.md, ../../../references/skill-contract.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Consistency. The Hermes dialect needs category and tags
- 100Steps. 23 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 2654 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 584: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.