Ecommerce Competitor Analyzer

What it does

When your agent uses it

• You need to analyze competitor products
• Extract product insights
• Batch analyze multiple product listings

Example prompts

• “/ecommerce-competitor-analyzer”

Requirements

• Node.js
• A Bash shell
• A credential in OLOSTEP_API_KEY
• A credential in GEMINI_API_KEY

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Extract Product Identifiers
2. 2Batch Scrape Product Data
3. 3Batch AI Analysis
4. 4Generate Dual Format Output

What it can do on your machine

Read from SKILL.md and the folder at commit 331ecd3. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 4 files in scripts/ (JavaScript and Shell, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • gemini

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • amazon.com
  • api.olostep.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • OLOSTEP_API_KEY
  • GEMINI_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ecommerce Competitor Analyzer loads about 2.6k tokens when it runs, and up to ~4.4k if it reads all its reference files. Until then it costs about 109 tokens; SKILL.md has 760 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~109

When it runs · the whole SKILL.md, loaded when a task matches

~2.6k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:60

  lostep API with configured API key from `.env`

• NoteMentions a .env fileSKILL.md:98

  2. Default from `.env` (`GOOGLE_SHEETS_ID`)

• NoteMentions a .env fileSKILL.md:190

  **Critical**: Always check if `.env` file exists and contains required keys before processing.

• NoteMentions a .env fileSKILL.md:264

  | `OLOSTEP_API_KEY not found` | Missing .env file | Check .env exists and contains key |

• NoteMentions a .env fileSKILL.md:344

  5. **ALWAYS validate .env exists** before starting processing

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from aAAaqwq/AGI-Super-Team at commit 331ecd3, republished under its MIT licence (© aAAaqwq). 760 words, ~2,605 tokens.

name

ecommerce-competitor-analyzer

description

Multi-platform e-commerce competitor analysis skill that automatically scrapes product data from Amazon, Temu, Shopee and generates comprehensive analysis reports using AI. Use when you need to analyze competitor products, extract product insights, or batch analyze multiple product listings. Supports bulk processing with structured outputs including title, price, rating, reviews, and strategic analysis.

version

1.0.0

author

Buluslan@新西楼Newest AI

globs

*.md, platforms.yaml, scripts/*.js, prompts/*.md

"Analyze these Amazon products:
B0C4YT8S6H
B08N5WRQ1Y
B0CLFH7CCV"

"Analyze B0C4YT8S6H and https://amazon.com/dp/B08N5WRQ1Y"

// Process all products in parallel
const products = ['B0C4YT8S6H', 'B08N5WRQ1Y', 'B0CLFH7CCV'];
const results = await Promise.allSettled(
  products.map(asin => scrapeAmazon(asin))
);

// Handle failures gracefully
const successful = results.filter(r => r.status === 'fulfilled');
const failed = results.filter(r => r.status === 'rejected');

# Amazon Competitor Analysis Report

## Analysis Overview
- Products analyzed: 3
- Analysis date: 2026-01-29
- Total time: ~5 minutes

---

## Product 1: B0C4YT8S6H

### Basic Information
- Title: [Product title]
- Price: [Price]
- Rating: [Rating]

### Copywriting Strategy & Keyword Analysis
[Full analysis...]

### Visual Asset Design Methodology
[Full analysis...]

### Customer Review Analysis
[Full analysis...]

### Market Positioning & Competitive Intelligence
[Full analysis...]

---

ecommerce-competitor-analyzer.skill/
├── SKILL.md                                # This file (AI instructions)
├── platforms.yaml                          # Platform configurations (URL patterns, regex)
├── .env.example                            # Configuration template (API keys)
├── prompts/                                # AI prompt templates
│   └── analysis-prompt-base.md            # Base analysis framework (from n8n)
├── scripts/                                # Processing scripts
│   ├── detect-platform.js                 # Platform detection utility
│   ├── scrape-amazon.js                   # Amazon scraper (Olostep API)
│   └── batch-processor.js                 # Batch processing engine
└── references/                             # Documentation
    └── n8n-workflow-analysis.md           # n8n workflow insights

platforms:
  amazon:
    url_patterns: ["amazon.com", "amazon.co.uk", ...]
    asin_regex:
      standard: "/dp/([A-Z0-9]{10})"
    scraper:
      provider: "olostep"
      api_endpoint: "https://api.olostep.com/v2/agent/web-agent"

OLOSTEP_API_KEY=your_olostep_api_key_here
GEMINI_API_KEY=your_gemini_api_key_here
GOOGLE_SHEETS_ID=YOUR_GOOGLE_SHEETS_ID_HERE

const items = productIdentifiers;
const results = await Promise.allSettled(
  items.map(async (item, index) => {
    try {
      const data = await scrapeProduct(item);
      const analysis = await analyzeWithAI(data);
      return { success: true, index, data: analysis };
    } catch (error) {
      // Single failure doesn't stop batch
      return { success: false, index, error: error.message };
    }
  })
);

// Report results
const successful = results.filter(r => r.status === 'fulfilled' && r.value.success);
const failed = results.filter(r => r.status === 'rejected' || !r.value.success);

console.log(`Processed: ${successful.length} succeeded, ${failed.length} failed`);

function detectPlatform(urlOrId) {
  // Direct ASIN
  if (/^[A-Z0-9]{10}$/.test(urlOrId)) {
    return { platform: 'amazon', id: urlOrId };
  }

  // Amazon URL patterns
  if (/amazon\.(com|co\.uk|de|es|fr|it|ca|co\.jp)/i.test(urlOrId)) {
    const asinMatch = urlOrId.match(/\/dp\/([A-Z0-9]{10})/i);
    if (asinMatch) {
      return { platform: 'amazon', id: asinMatch[1] };
    }
  }

  // Other platforms (future)
  // if (/temu\.com/i.test(urlOrId)) return { platform: 'temu', id: extractId(urlOrId) };

  return null;
}

© aAAaqwq, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 25 other files (scripts, references) in skills/ecommerce-competitor-analyzer of aAAaqwq/AGI-Super-Team.

• SKILL.md
• .gitignore
• LICENSE
• README.md
• docs/INSTALLATION.md
• docs/SETUP.md
• output/.gitkeep
• platforms.yaml
• prompts/analysis-prompt-base.md
• references/n8n-workflow-analysis.md
• reports/.gitkeep
• scripts/auth-google-sheets-manual.js
• scripts/auth-google-sheets-service-account.js
• scripts/auth-google-sheets.js
• scripts/auth-guide.sh
• … and 11 more

Open the folder on GitHubat commit 331ecd3