Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
DeepSeek
Muse+22 moreClaude CodeCursorCodex CLIDeepSeekMuse
Dots
Manus
Grok
Grok Bot+18 agentsBrand+Type+Attr Title Optimizer
Turn basic product-feed titles into structured Brand + Product Type + Material + Color titles, validate Merchant Center rules, and export AI-aware structured_title candidates with a row-level audit.
Free
Brand+Type+Attr Title Optimizer
Example session with this skill installed
Optimize the product titles in spring-catalog.csv for our Google Shopping feed.
Use the strict structure Brand + Product Type + Material + Color.
Rules
- only use values already present in the catalog;
- never invent materials, colors, keywords, claims, or promotions;
- preserve exact variant colors;
- keep generated titles within 150 characters;
- put the most important identifying information early;
- flag products missing product type or other important attributes;
- generate AI-aware Merchant Center structured_title values;
- do not overwrite the original titles.
Give me an optimized-title file, a Merchant Center structured-title patch candidate, a row-level audit, and a summary.
- Read your context and instructions
- Compiled the brand+type+attr title optimizer
- Generated the data export
Product-title optimization complete
Products processed: 2,486
Titles generated: 2,431
Rows requiring review: 55
Missing material values: 128
Missing color values: 41
Average original title length: 27.6 characters
Average generated title length: 54.2 characters
No product attributes were invented.
Example transformations
| ID | Original | Generated |
|---|---|---|
| BP-104 | Classic Backpack | NorthPeak Hiking Backpack Recycled Nylon Black |
| TS-221 | Essential Tee | Alder Essential T-Shirt Organic Cotton Navy Blue |
| MG-019 | Coffee Mug | Hearthline Coffee Mug Stoneware White |
Review queue
55 products were flagged because at least one core requirement could not be safely satisfied.
Examples
- SH-442 — missing product type
- BP-317 — core title exceeded the safe character limit
- TS-981 — color field missing for a variant-specific item
Missing attributes were not guessed.
Merchant Center output
Each AI-generated title is represented as a structured_title candidate using:
trained_algorithmic_media:"..."
Files generated
- optimized_titles.csv
- merchant_center_structured_title_patch.csv
- title_audit.csv
- summary.json
Important publishing note
The structured-title patch is a preparation artifact.
Google states that if both title and structured_title are supplied for a product, title is used. Review your Merchant Center data-source configuration before publishing.
These titles are feed-optimization candidates, not a guarantee of Google Ads performance.
optimized_titles.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Many ecommerce catalogs use weak titles like “Classic Backpack” or “Cotton Tee.” Valuable product attributes remain buried in separate feed columns instead of helping identify the product clearly.
Rewriting hundreds or thousands of titles manually is slow—and one-shot AI rewriting can invent materials, colors, claims, or promotional language that does not belong in the feed.
What it does
Brand+Type+Attr Title Optimizer transforms verified catalog attributes into structured product titles using a strict, repeatable format.
Brand + Product Type + Material + Color
- Reads CSV and XLSX product catalogs
- Uses only attributes already present in the feed
- Supports category-specific title templates
- Removes duplicate attribute phrases
- Preserves exact variant values such as color
- Enforces the 150-character Merchant Center title limit
- Shows a first-70-character preview for prominence review
- Flags missing attributes instead of inventing them
- Generates AI-aware structured_title values
- Produces a row-level audit and review queue
Why this beats prompting it yourself
A generic prompt can rewrite titles, but it can silently invent descriptors, use inconsistent attribute order, forget variants, or exceed feed limits.
This skill separates AI generation from deterministic validation. Every row records the original title, generated title, attributes used, missing attributes, character count, first-70 preview, and validation status.
Built for current Merchant Center rules
AI-generated title candidates are represented as structured_title values using trained_algorithmic_media.
The skill also warns when an existing title could take precedence, so teams can review their actual Merchant Center data-source setup before publishing.
No performance guarantees
Better product data can improve relevance and feed quality, but this skill does not promise additional impressions, clicks, conversions, or ROAS.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for E-commerce.
Requires source attributes to exist in the input; will not invent missing data. Large Excel files require openpyxl. Does not directly push to Google Merchant Center API.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
4 uses
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 1 month ago
- Free with an Agensi account
- Software
Python