What makes Product Feed Optimizer notable?

1.1K downloads. Trust evidence available

How should Product Feed Optimizer be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

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 grou... Skill: Product Feed Optimizer Owner: aaron-he-zhu Summary: Use when the user asks to "optimize my Shopping feed", "fix product disapprovals", "improve product titles/attributes", or "build feed-driven PMax asset grou... Tags: latest:19.0.0 Version history: v19.0.0 | 2026-07-24T15:04:18.801Z | auto - Bumped version to 19.0.0. - Added distribution-manifest.json for improved distribution and hosting metadata. - Removed

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

19.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 19.0.0release · observed Jul 24, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17e1tg8pjra8dn1dvtq21sahx83hrxj:product-feed-optimizer

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-product-feed-optimizer/snapshot"

Documentation

CLAWHUB

144,034 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: product-feed-optimizer
slug: aaron-product-feed-optimizer
displayName: "Product Feed Optimizer · 商品Feed优化"
summary: "商品Feed优化/购物广告Feed/商品标题优化/商品禁投修复"
description: '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'
version: "19.0.0"
license: Apache-2.0
compatibility: "Claude Code and compatible agent-skill hosts"
homepage: "https://github.com/aaron-he-zhu/aaron-marketing-skills"
when_to_use: "Use when preparing or repairing the product data behind Shopping / Performance Max before or during a paid run: rewriting product titles and descriptions to a front-loaded attribute pattern, filling required/recommended feed attributes (GTIN, brand, condition, product_type, google_product_category), fixing availability/price/identifier mismatches, triaging Merchant Center disapprovals and their causes, and grouping products into feed-driven asset groups / listing-group trees. Distinct from writing text-ad copy and from scoring the account."
argument-hint: "<product-feed export (TSV/CSV/XML) or Merchant Center diagnostics> [goal: DR|prospecting] [platforms]"
metadata: {"author": "aaron-he-zhu", "version": "19.0.0", "discipline": "ad", "phase": "research", "geo-relevance": "low", "hermes": {"tags": ["marketing", "ad", "research"], "category": "ad"}, "openclaw": {"emoji": "🎯", "homepage": "https://github.com/aaron-he-zhu/aaron-marketing-skills"}}
---

# Product Feed Optimizer

Audits and rewrites the Shopping / Performance Max product feed — title and description patterns, required and recommended attributes, GTIN/availability/price hygiene, disapproval triage, and feed-driven asset-group / listing-group structure. This is the research-phase skill that hardens the product data behind the ROAS **O (Offer)** dimension; it does not write text-ad copy (that is `ad-creative-builder`) and does not score the account or compute the RQS (that is `ad-account-auditor`).

## Quick Start

```
Audit my Shopping feed export for disapprovals and missing attributes: [path]. Goal is DR.
```

```
Rewrite these product titles to a front-loaded pattern and fill the missing GTIN/brand/condition attributes. [feed CSV]
```

```
Triage my Merchant Center disapprovals and group the approved products into PMax listing groups. [diagnostics export + feed]
```

## Skill Contract

**Expected output**: a feed remediation package — (1) a **disapproval / diagnostics triage** table (item → cause → fix), (2) **rewritten titles + descriptions** to a front-loaded

_meta.json

{
  "ownerId": "kn73qjxwmbna25qq8q051epqt980sys5",
  "slug": "product-feed-optimizer",
  "version": "19.0.0",
  "publishedAt": 1784905458801
}

references/feed-title-patterns.md

# Feed Title Patterns

Front-loaded product-title formulas by vertical, an attribute-priority checklist, GTIN/availability/disapproval hygiene rules, and one before/after title example. Used by step 4 (rewrite titles) and step 3 (attribute completeness) of [../SKILL.md](../SKILL.md). All numbers below are **Estimated** starter defaults — confirm each against the live feed and the destination landing page before shipping.

## Character limits (Estimated)

| Platform | Title field | Hard max | Front-load budget |
|---|---|---|---|
| Google Shopping / PMax | `title` | ~150 chars | first ~70 chars carry the match |
| Meta Commerce / Advantage+ Catalog | `title` | ~150 chars | first ~65 chars |
| Microsoft Shopping | `title` | ~150 chars | first ~70 chars |

Rule: the buyer decides in the visible prefix. Put brand + product type + top spec in the first ~70 chars; the tail is for secondary variants and long-tail terms. Never pad to the limit — a truthful 60-char title beats a stuffed 150.

## Title formula by vertical

Order = highest-intent attribute first. Drop any slot the item does not have; do not invent one.

| Vertical | Formula (front → back) | Example shape |
|---|---|---|
| Apparel / footwear | Brand + Product type + Key attribute + Color + Material + Size + Gender/Age | `Nike Air Zoom Pegasus 40 Running Shoe Black Mesh Men's US 10` |
| Electronics | Brand + Model + Product type + Key spec + Capacity/Size + Color | `Sony WH-1000XM5 Wireless Headphones Noise-Canceling Black` |
| Home / furniture | Brand + Product type + Key feature + Material + Dimensions + Color | `IKEA Kallax Shelf Unit 4-Cube Particleboard 30x30 White` |
| Health / beauty | Brand + Product type + Key attribute + Quantity/Volume + Skin/Hair type | `CeraVe Moisturizing Cream Fragrance-Free 19 oz Dry Skin` |
| Consumable / grocery | Brand + Product type + Flavor/Variant + Count + Size/Weight | `Nespresso Vertuo Coffee Pods Melozio 30-Count Medium Roast` |
| Auto / parts | Brand + Part type + Fitment (make/model/year) + Spec + OEM/MPN | `Bosch Brake Pads Front Ceramic Fits Honda Civic 2016-2021` |
| Generic default | Brand + Product type + Key attribute + Variant (color/size) | `<Brand> <Product type> <Key spec> <Variant>` |

Attribute-ordering rules:
- Brand first **only if** it drives demand; for unbranded/generic goods lead with product type.
- One key spec, not three — pick the attribute a buyer searches on (capacity, size, fitment).
- Match variant terms (color/size) to the actual `color`/`size` attributes; a title/attribute mismatch is a common disapproval.
- No promo text in the title: no `Free Shipping`, `Sale`, `Best`, `%`, ALL-CAPS words, or emoji. Promotions live in `promotion_id` / `sale_price`, not the title.

## Attribute-priority checklist

Required — a missing one limits or disapproves the item. Flag per item as `[needs source]`; never fabricate.

- [ ] `id` — stable, unique per item
- [ ] `title` — front-loaded per the vertical formula
- [ ] `description` — sec

skill-card.md

## Description:

Audits and improves Shopping and Performance Max product feeds by triaging disapprovals, checking required attributes, rewriting product titles and descriptions, and structuring feed-driven asset or listing groups.

This skill is ready for commercial/non-commercial use.

## Publisher:

[aaron-he-zhu](https://clawhub.ai/user/aaron-he-zhu)

### License/Terms of Use:

MIT-0

## Use Case:

Marketing operators, ecommerce teams, and agent-assisted media buyers use this skill to prepare or repair product feed data before Shopping or Performance Max campaigns. It helps turn feed exports, diagnostics, and landing-page checks into a remediation package for disapprovals, title patterns, attribute gaps, price and availability mismatches, and catalog segmentation.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Product feed exports, diagnostics, landing-page URLs, and claims or offers memory can contain sensitive catalog, pricing, and campaign information.

Mitigation: Share only the fields needed for the feed audit and review the generated remediation package before applying changes.

Risk: Incorrect price, availability, identifier, or claim wording can lead to disapprovals or misleading feed updates.

Mitigation: Validate proposed fixes against landing pages, Merchant Center diagnostics, and approved claims or offer records before publishing.

## Reference(s):

- [Product Feed Optimizer on ClawHub](https://clawhub.ai/aaron-he-zhu/skills/product-feed-optimizer)
- [Metadata homepage](https://github.com/aaron-he-zhu/aaron-marketing-skills)
- [Feed Title Patterns](references/feed-title-patterns.md)

## Skill Output:

**Output Type(s):** [text, markdown, configuration, guidance]

**Output Format:** [Markdown remediation package with tables, rewritten feed fields, and handoff notes]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May include per-item diagnostics, missing-attribute flags, title and description rewrites, price and availability checks, and feed segment recommendations.]

## Skill Version(s):

19.0.0 (source: server release evidence and skill frontmatter)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

distribution-manifest.json

{
  "capabilities": [
    "inline-delivery",
    "canonical-state-read"
  ],
  "capability_ceiling": "lite",
  "catalog_sha256": "6f0256cf52710f2916ecebaea0f3110c9313099ec4a69a11cac72ba9b2f3b940",
  "files": [
    {
      "bytes": 12684,
      "mode": "0644",
      "path": "SKILL.md",
      "sha256": "5634f06092093a39f2777b0d6505eac59450dcede50c6ceb95cdabfe81574521"
    },
    {
      "bytes": 7887,
      "mode": "0644",
      "path": "references/feed-title-patterns.md",
      "sha256": "6cf6691d2cbc00f1cd7488dcd4066cac5bf83d989d523709754e32ab837c166e"
    }
  ],
  "files_sha256": "b435890912826476734315c46fad616c44d6276e8b8a82dee7e0bb182fa67a9e",
  "hash_algorithm": "sha256",
  "kind": "standalone-skill",
  "manifest_excludes": [
    "distribution-manifest.json"
  ],
  "manifest_path": "distribution-manifest.json",
  "package_ceiling": {
    "max_bytes": 1000000,
    "max_files": 64
  },
  "profile": "lite",
  "profile_definition_sha256": "4598e1f7bba667ef928ea2a60a6252ad9348086e9eecab29437db442df2a568e",
  "schema_version": "1.1",
  "source": {
    "commit": "f552620c278afddcb25d09637a0cfcc1ce48faf4",
    "repository": "aaron-he-zhu/aaron-marketing-skills"
  }
}

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.