New: Earn 20% as an AgentAlley affiliate. Share your link and earn on every sale you refer. Join now New: Earn 20% as an affiliate. Join now

Generate and optimize SEO-rich

Product description optimizer

by writer · Apache-2.0 license · ★ 7 on GitHub

Product description optimizer cover

Generate and optimize SEO-rich, conversion-focused product detail page (PDP) copy for CPG and retail e-commerce, leveraging keyword strategy, benefit-driven messaging, and structured content best practices.

---
name: Product Description Optimizer
description: Generate and optimize SEO-rich, conversion-focused product detail page (PDP) copy for CPG and retail e-commerce, leveraging keyword strategy, benefit-driven messaging, and structured content best practices.

metadata:
  display_name: "Product Description Optimizer"
  short_description: "Optimize product detail page copy for SEO and conversion"
  default_prompt: "Optimize my product description and suggest the best next steps"
  version: "1.0.1"
  tags:
    - cpg-retail
  icon_path: "assets/icon.png"
---

# Product Description Optimizer

## Overview

Overview

This skill produces high-converting product detail page copy that balances search engine visibility with persuasive consumer messaging. It applies CPG-specific SEO frameworks, benefit-ladder copywriting, and structured data alignment to maximize both organic traffic and on-page conversion rate.

Manual install (npx, ZIP)
Claude Codenpx skills add writer/skills --skill Product Description Optimizer -g -a claude-code
Claude Code (degit)npx degit writer/skills/skills/content-brand/product-description-optimizer#main ~/.claude/skills/product-description-optimizer
Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md7.7 KB
Read SKILL.md here
writer/main1 file shown
SKILL.md
Show the full text156 lines

Product Description Optimizer

Overview

This skill produces high-converting product detail page copy that balances search engine visibility with persuasive consumer messaging. It applies CPG-specific SEO frameworks, benefit-ladder copywriting, and structured data alignment to maximize both organic traffic and on-page conversion rate.

The optimizer treats every PDP as a micro-landing page — each element (title, bullets, enhanced content) has a distinct job in the discovery-to-purchase funnel.

When to Use

  • Launching new SKUs on DTC or marketplace channels (Amazon, Walmart, Target+, Instacart).
  • Refreshing existing listings that underperform on CTR (< 0.4%) or CVR (< 8% category avg).
  • Expanding to new keywords or search verticals (e.g., "clean label," "keto-friendly").
  • Migrating content across retailers with different character-limit and formatting rules.
  • Preparing A+ / Enhanced Brand Content modules.

Required Inputs

Input Description Example
product_name Full SKU name including variant "BrightClean Dish Soap, Lemon Zest, 28 oz"
product_attributes Key specs: size, scent, flavor, form factor, count JSON or table
target_keywords Primary (1-2) and secondary (3-7) keywords with search volume { "primary": ["natural dish soap"], "secondary": ["plant-based dish soap", "eco dish soap"] }
category Retail taxonomy / browse node "Health & Household > Cleaning Supplies > Dish Soap"
brand_voice_guide Link or summary of tone, banned words, mandatory claims Brand style guide excerpt
channel Target retailer or DTC platform "Amazon US", "Walmart.com", "Shopify DTC"
competitive_set Top 3-5 competitor ASINs/URLs for gap analysis List of URLs
regulatory_claims Approved on-pack claims and certifications "USDA Organic", "EPA Safer Choice"

Methodology

Step 1 — Keyword & Search Intent Mapping
  1. Classify each keyword by intent: navigational (brand search), informational (how-to), transactional (buy/best).
  2. Map primary keyword to the product title; secondary keywords distributed across bullets and description.
  3. Identify long-tail modifiers from auto-suggest, "Customers also searched," and Related Search terms.
  4. Calculate a Keyword Coverage Score: (matched keywords / total target keywords) × 100. Target ≥ 85%.
Step 2 — Title Construction

Apply the CPG Title Formula:

[Brand] + [Product Line] + [Key Differentiator] + [Primary Keyword] + [Size/Count] + [Variant]
  • Amazon: ≤ 200 characters (80 chars mobile-visible).
  • Walmart: ≤ 75 characters for title; extended title ≤ 250.
  • Keep the first 60 characters front-loaded with primary keyword and core benefit.
Step 3 — Benefit-Ladder Bullet Points

Use the Feature → Advantage → Benefit (FAB) framework for each bullet:

  1. Feature: What it is (ingredient, technology, format).
  2. Advantage: What it does better than alternatives.
  3. Benefit: What the consumer gains (time saved, peace of mind, sensory delight).

Write 5 bullets (Amazon) or 3-4 key features (Walmart). Each bullet ≤ 250 characters. Lead with the benefit, not the feature. Naturally embed one secondary keyword per bullet without stuffing.

Step 4 — Product Description / A+ Content
  • Above the fold: 50-80 word paragraph restating the core value proposition with primary keyword in the first sentence.
  • Storytelling module: Brand origin or use-case scenario (150-200 words).
  • Comparison chart: Feature matrix vs. own portfolio (not competitors, per Amazon TOS).
  • Lifestyle imagery alt text: Keyword-enriched, descriptive alt text ≤ 125 characters.
Step 5 — Structured Data & Backend Optimization
  • Populate search terms / backend keywords with synonyms, abbreviations, and Spanish-language equivalents where relevant.
  • Ensure itemType, material, scent, and custom attributes align with browse node expectations.
  • Add schema.org Product markup for DTC (name, brand, sku, gtin, offers, aggregateRating).
Step 6 — Readability & Conversion Audit
Metric Target
Flesch-Kincaid Grade Level 6-8 (general CPG)
Avg sentence length ≤ 20 words
Power words per bullet ≥ 1 ("effortless," "clinically proven," "dermatologist tested")
CTA presence At least 1 implicit CTA ("Try," "Discover," "Experience")
Scannability No paragraph > 3 lines on mobile

Output Specification

output:
  title: string              # Optimized product title
  bullets: list[string]      # 3-5 benefit-driven bullet points
  description_html: string   # Rich product description with HTML
  backend_keywords: string   # Space-separated, ≤ 250 bytes
  seo_score: float           # 0-100 composite score
  readability_grade: float   # Flesch-Kincaid grade level
  keyword_coverage: float    # Percentage of target keywords used
  warnings: list[string]     # Policy violations or optimization gaps

Analysis Framework

Score each listing across five dimensions (20 points each, total 100):

  1. Keyword Relevance (20): Primary keyword in title & first bullet; secondary keywords distributed; no cannibalization.
  2. Persuasion Quality (20): FAB framework applied; emotional triggers present; objection handling (e.g., "no artificial dyes").
  3. Compliance (20): No banned claims; certifications substantiated; retailer policy adherence.
  4. Readability (20): Grade level, sentence length, scannable formatting.
  5. Technical SEO (20): Backend keywords populated; structured data complete; image alt text present.

Examples

Input snippet:

  • Product: "PureGlow Vitamin C Serum, 1 fl oz"
  • Primary keyword: "vitamin c serum for face"
  • Channel: Amazon US

Optimized Title: "PureGlow Vitamin C Serum for Face — 20% L-Ascorbic Acid, Hyaluronic Acid & Vitamin E — Brightening & Anti-Aging Face Serum, 1 fl oz"

Bullet 1 (FAB): "VISIBLY BRIGHTER SKIN IN 14 DAYS — Our stabilized 20% L-Ascorbic Acid formula penetrates deeply to reduce dark spots and even skin tone, so you wake up to a radiant, lit-from-within glow."

Guidelines

  • Never make unsubstantiated health or efficacy claims; always tie claims to approved language from regulatory/legal.
  • Avoid keyword stuffing — a keyword density > 3% in any content block triggers a warning.
  • Do not reference competitors by name on Amazon or Walmart.
  • Use sentence case for bullets on Amazon; title case for titles.
  • Always run final copy through the Claims Compliance Checker skill before publishing.
  • Preserve brand voice parameters: if the guide says "playful," do not write clinical copy.

Validation Checklist

  • Primary keyword appears in title, first bullet, and description opening.
  • All bullets follow the FAB framework.
  • Title length within channel-specific character limit.
  • Backend keywords contain no duplicates of title/bullet words.
  • Flesch-Kincaid grade level ≤ 8.
  • No banned or unsubstantiated claims present.
  • Structured data / schema markup is complete (DTC).
  • Content passes retailer-specific style guide checks.
  • Keyword coverage score ≥ 85%.
  • At least one implicit CTA is present in the description.
1---
2name: Product Description Optimizer
3description: Generate and optimize SEO-rich, conversion-focused product detail page (PDP) copy for CPG and retail e-commerce, leveraging keyword strategy, benefit-driven messaging, and structured content best practices.
4 
5metadata:
6 display_name: "Product Description Optimizer"
7 short_description: "Optimize product detail page copy for SEO and conversion"
8 default_prompt: "Optimize my product description and suggest the best next steps"
9 version: "1.0.1"
10 tags:
11 - cpg-retail
12 icon_path: "assets/icon.png"
13---
14 
15# Product Description Optimizer
16 
17## Overview
18 
19This skill produces high-converting product detail page copy that balances search engine visibility with persuasive consumer messaging. It applies CPG-specific SEO frameworks, benefit-ladder copywriting, and structured data alignment to maximize both organic traffic and on-page conversion rate.
20 
21The optimizer treats every PDP as a micro-landing page — each element (title, bullets, enhanced content) has a distinct job in the discovery-to-purchase funnel.
22 
23## When to Use
24 
25- Launching new SKUs on DTC or marketplace channels (Amazon, Walmart, Target+, Instacart).
26- Refreshing existing listings that underperform on CTR (< 0.4%) or CVR (< 8% category avg).
27- Expanding to new keywords or search verticals (e.g., "clean label," "keto-friendly").
28- Migrating content across retailers with different character-limit and formatting rules.
29- Preparing A+ / Enhanced Brand Content modules.
30 
31## Required Inputs
32 
33| Input | Description | Example |
34|---|---|---|
35| `product_name` | Full SKU name including variant | "BrightClean Dish Soap, Lemon Zest, 28 oz" |
36| `product_attributes` | Key specs: size, scent, flavor, form factor, count | JSON or table |
37| `target_keywords` | Primary (1-2) and secondary (3-7) keywords with search volume | `{ "primary": ["natural dish soap"], "secondary": ["plant-based dish soap", "eco dish soap"] }` |
38| `category` | Retail taxonomy / browse node | "Health & Household > Cleaning Supplies > Dish Soap" |
39| `brand_voice_guide` | Link or summary of tone, banned words, mandatory claims | Brand style guide excerpt |
40| `channel` | Target retailer or DTC platform | "Amazon US", "Walmart.com", "Shopify DTC" |
41| `competitive_set` | Top 3-5 competitor ASINs/URLs for gap analysis | List of URLs |
42| `regulatory_claims` | Approved on-pack claims and certifications | "USDA Organic", "EPA Safer Choice" |
43 
44## Methodology
45 
46### Step 1 — Keyword & Search Intent Mapping
47 
481. Classify each keyword by intent: **navigational** (brand search), **informational** (how-to), **transactional** (buy/best).
492. Map primary keyword to the product title; secondary keywords distributed across bullets and description.
503. Identify long-tail modifiers from auto-suggest, "Customers also searched," and Related Search terms.
514. Calculate a **Keyword Coverage Score**: (matched keywords / total target keywords) × 100. Target ≥ 85%.
52 
53### Step 2 — Title Construction
54 
55Apply the **CPG Title Formula**:
56 
57```
58[Brand] + [Product Line] + [Key Differentiator] + [Primary Keyword] + [Size/Count] + [Variant]
59```
60 
61- Amazon: ≤ 200 characters (80 chars mobile-visible).
62- Walmart: ≤ 75 characters for title; extended title ≤ 250.
63- Keep the first 60 characters front-loaded with primary keyword and core benefit.
64 
65### Step 3 — Benefit-Ladder Bullet Points
66 
67Use the **Feature → Advantage → Benefit (FAB)** framework for each bullet:
68 
691. **Feature**: What it is (ingredient, technology, format).
702. **Advantage**: What it does better than alternatives.
713. **Benefit**: What the consumer gains (time saved, peace of mind, sensory delight).
72 
73Write 5 bullets (Amazon) or 3-4 key features (Walmart). Each bullet ≤ 250 characters. Lead with the benefit, not the feature. Naturally embed one secondary keyword per bullet without stuffing.
74 
75### Step 4 — Product Description / A+ Content
76 
77- **Above the fold**: 50-80 word paragraph restating the core value proposition with primary keyword in the first sentence.
78- **Storytelling module**: Brand origin or use-case scenario (150-200 words).
79- **Comparison chart**: Feature matrix vs. own portfolio (not competitors, per Amazon TOS).
80- **Lifestyle imagery alt text**: Keyword-enriched, descriptive alt text ≤ 125 characters.
81 
82### Step 5 — Structured Data & Backend Optimization
83 
84- Populate search terms / backend keywords with synonyms, abbreviations, and Spanish-language equivalents where relevant.
85- Ensure `itemType`, `material`, `scent`, and custom attributes align with browse node expectations.
86- Add schema.org Product markup for DTC (name, brand, sku, gtin, offers, aggregateRating).
87 
88### Step 6 — Readability & Conversion Audit
89 
90| Metric | Target |
91|---|---|
92| Flesch-Kincaid Grade Level | 6-8 (general CPG) |
93| Avg sentence length | ≤ 20 words |
94| Power words per bullet | ≥ 1 ("effortless," "clinically proven," "dermatologist tested") |
95| CTA presence | At least 1 implicit CTA ("Try," "Discover," "Experience") |
96| Scannability | No paragraph > 3 lines on mobile |
97 
98## Output Specification
99 
100```yaml
101output:
102 title: string # Optimized product title
103 bullets: list[string] # 3-5 benefit-driven bullet points
104 description_html: string # Rich product description with HTML
105 backend_keywords: string # Space-separated, ≤ 250 bytes
106 seo_score: float # 0-100 composite score
107 readability_grade: float # Flesch-Kincaid grade level
108 keyword_coverage: float # Percentage of target keywords used
109 warnings: list[string] # Policy violations or optimization gaps
110```
111 
112## Analysis Framework
113 
114Score each listing across five dimensions (20 points each, total 100):
115 
1161. **Keyword Relevance (20)**: Primary keyword in title & first bullet; secondary keywords distributed; no cannibalization.
1172. **Persuasion Quality (20)**: FAB framework applied; emotional triggers present; objection handling (e.g., "no artificial dyes").
1183. **Compliance (20)**: No banned claims; certifications substantiated; retailer policy adherence.
1194. **Readability (20)**: Grade level, sentence length, scannable formatting.
1205. **Technical SEO (20)**: Backend keywords populated; structured data complete; image alt text present.
121 
122## Examples
123 
124**Input snippet**:
125- Product: "PureGlow Vitamin C Serum, 1 fl oz"
126- Primary keyword: "vitamin c serum for face"
127- Channel: Amazon US
128 
129**Optimized Title**:
130"PureGlow Vitamin C Serum for Face — 20% L-Ascorbic Acid, Hyaluronic Acid & Vitamin E — Brightening & Anti-Aging Face Serum, 1 fl oz"
131 
132**Bullet 1 (FAB)**:
133"VISIBLY BRIGHTER SKIN IN 14 DAYS — Our stabilized 20% L-Ascorbic Acid formula penetrates deeply to reduce dark spots and even skin tone, so you wake up to a radiant, lit-from-within glow."
134 
135## Guidelines
136 
137- Never make unsubstantiated health or efficacy claims; always tie claims to approved language from regulatory/legal.
138- Avoid keyword stuffing — a keyword density > 3% in any content block triggers a warning.
139- Do not reference competitors by name on Amazon or Walmart.
140- Use sentence case for bullets on Amazon; title case for titles.
141- Always run final copy through the **Claims Compliance Checker** skill before publishing.
142- Preserve brand voice parameters: if the guide says "playful," do not write clinical copy.
143 
144## Validation Checklist
145 
146- [ ] Primary keyword appears in title, first bullet, and description opening.
147- [ ] All bullets follow the FAB framework.
148- [ ] Title length within channel-specific character limit.
149- [ ] Backend keywords contain no duplicates of title/bullet words.
150- [ ] Flesch-Kincaid grade level ≤ 8.
151- [ ] No banned or unsubstantiated claims present.
152- [ ] Structured data / schema markup is complete (DTC).
153- [ ] Content passes retailer-specific style guide checks.
154- [ ] Keyword coverage score ≥ 85%.
155- [ ] At least one implicit CTA is present in the description.
156 
View all files on GitHub →

Details

License
Apache-2.0
Stars on the repo
★ 7
Checked
Source
writer/skills ↗
Creator
writer · 5 listings
View creator

Similar skills

See all →
SkillAnalyze active ads from Meta/Facebook, GoogleAd library teardownScrapeCreators/social-media-research-skills · by ScrapeCreatorsUse when the user wants to analyze active ads from Meta/Facebook, Google, or LinkedIn ad libraries; tear down a competitor's messaging; extract hooks, offers, CTAs, video transcripts, landing page claims, and test ideas from public ads.★ 2.6k GitHub starsSkillTurn product materials into listing visuals for Taobao, JDEcommerce visual copywritingfeichanggege/ecommerce-visual-copywriting-skill · by feichanggegeTurn product materials into listing visuals for Taobao, JD, Douyin, Amazon, Shopify and TikTok Shop: main-image and detail-page storyboards, in-image copy, image prompts, plus an evidence and ad-compliance check.★ 985 GitHub starsSkillTell us about your plans and pricesPricing Page (High‑Conversion) — Web Design Skillboraoztunc/skills · by Meng ToTell us about your plans and prices, and get back a ready-to-build pricing page: plan layout, what each tier includes, buttons, and answers to common buyer questions.★ 361 GitHub starsSkillWrites opening hooks and post titles for long-form articlesCopywriting hookssamber/cc-skills · by samberWrites opening hooks and post titles for long-form articles in EN or FR — blog posts, Substack/Medium/dev.to, LinkedIn long-form, newsletters, essays. Trigger whenever the user asks for a hook, opening, lede, intro, first sentence/paragraph, opener, accroche, attaque, phrase d'accroche, or première phrase — including punching up a flat intro or draft opening — or for a post title, titre d'article, or headline. Do NOT trigger for social posts (LinkedIn feed, Twitter/X, TikTok, Bluesky), READMEs, taglines, email subjects, ad copy, landing-page headlines, press releases, SEO meta, or body rewrites. Do NOT use for end-of-article CTAs — use samber/cc-skills@copywriting-cta instead.★ 222 GitHub starsSkillSomeone wants landing page ideas, conceptsEcom landing pageskgelster/awesome-ecom-skills · by kgelsterUse when someone wants landing page ideas, concepts, or angles for a store: give me landing page concepts", "LP ideas", "landing page angles", a campaign or ad landing page, pages for a new audience/segment, a seasonal/event/promo page, or a geo/local page. Also use when a chosen concept gets picked and needs building out into an actual page (section-by-section blueprint), or when auditing an existing landing page against best practice. The core insight: one product becomes dozens of pages by varying the ANGLE, not the product. Not for full-site information architecture, product detail pages, collection pages, or blog/SEO content (a landing page has ONE goal, no site chrome). Use an SEO/content skill. Not for the ad or email creative itself, though message match with the page matters.★ 49 GitHub starsSkillWrite sales pages, email sequencesEW Skill — Sales CopyDeupaxx/EveryDay-Writer · by DeupaxxWrite sales pages, email sequences, and direct-response copy that converts through clarity and specificity rather than manipulation. Use for launches, offers, and conversion-focused email. Enforces the EW anti-AI rules, proof standards, and the writer's voice profile.★ 32 GitHub stars

More from writer

SkillGenerates systematic ad creative variants across copyAd creative variant generatorwriter/skills · by writerGenerates systematic ad creative variants across copy, visual direction, format, and audience angle for CPG and retail e-commerce campaigns. Use when a user needs multiple ad variations for testing, creative diversification, or multi-platform adaptation. Triggers on requests for ad copy, creative variants, A/B test assets, ad matrix generation, or platform-specific ad content.★ 7 GitHub starsSkillAnalyze and rewrite content to strict brand voice guidelinesBrand voice enforcerwriter/skills · by writerAnalyze and rewrite content to strict brand voice guidelines, scoring adherence across tone, vocabulary, syntax patterns, and persona alignment for CPG and retail brands.★ 7 GitHub starsSkillScores and ranks influencers for brand partnership fitInfluencer fit scoringwriter/skills · by writerScores and ranks influencers for brand partnership fit using a multi-dimensional framework covering audience alignment, engagement quality, brand safety, content relevance, and commercial viability for CPG and retail e-commerce campaigns. Use when evaluating potential influencer partners, building shortlists, or comparing candidates. Triggers on requests for influencer evaluation, creator partnerships, influencer scoring, KOL assessment, or ambassador selection.★ 7 GitHub starsSkillSimulate CPG pricing strategies including cost pass-throughPricing strategy simulatorwriter/skills · by writerSimulate CPG pricing strategies including cost pass-through, promotional pricing, EDLP/Hi-Lo analysis, and price pack architecture optimization with elasticity modeling and competitive response scenarios. Use when evaluating price changes, building price pack architecture, analyzing price gaps, or modeling price elasticity impacts.★ 7 GitHub stars