A free keyword research tool for Amazon sellers. No API key required — ready to use out of the box.
Features
- Long-tail keyword mining: Extract 100-200 real search terms from Amazon's autocomplete engine
- Competitive landscape analysis: Product count, price range, average rating, review distribution, top brands
- Seasonal trend detection: 12 months of Google Trends data to identify peak seasons and demand changes
- Market opportunity score: 1-10 points, combining competition density, price headroom, and demand signals
- Multi-marketplace support: United States, United Kingdom, Germany, France, Italy, Spain, Japan, Canada, Australia, India, Mexico, Brazil
- Keyword comparison: Side-by-side analysis of multiple keywords
Usage Examples
Users can ask questions naturally. For example:
研究亚马逊美国的关键词"portable blender"
为"yoga mat"查找亚马逊长尾关键词
我想卖阻力带。亚马逊关键词格局如何？
比较亚马逊美国的"laptop stand"和"monitor stand" — 哪个机会更大？
分析亚马逊德国的"Küchenmesser"
研究亚马逊美国、英国和德国的"water bottle"
Workflow
Step 1: Collect autocomplete data
Run the bundled script to collect Amazon autocomplete suggestions:
<skill>/scripts/research.sh "<关键词>" [市场]
Parameters:
关键词(required): The seed keyword to research市场(optional):us(default),uk、de、fr、it、es、jp、ca、au、in、mx、br
Script features:
- Query the Amazon autocomplete API using the seed keyword
- Use prefix expansion: "best [keyword]", "cheap [keyword]", "top [keyword]"
- Use a-z suffix expansion: "[keyword] a", "[keyword] b", ... "[keyword] z"
- Return a deduplicated, sorted list of real search suggestions — one per line
Why it matters: Amazon autocomplete reflects what real shoppers actually type. These are not guesses — they are direct demand signals from Amazon's search engine. Prefix and letter expansion capture long-tail terms that basic autocomplete misses, and these terms are often less competitive and higher intent.
Example:
<skill>/scripts/research.sh "portable blender" us
# 返回100-200个长尾关键词
For multi-marketplace research, run the script once per marketplace.
Step 2: Analyze competition
Use web_search to gather competitor intelligence:
- Search
"<关键词>" site:amazon.com— note the approximate result count to understand competition density - Search
"<关键词>" amazon best sellers price review— extract price patterns, average ratings, dominant brands - Summarize: total competitor count, price range (lowest/average/highest), average star rating, top 5 brands with the highest visibility
Why it matters: Raw keyword volume without competitive context is meaningless. A keyword with 10,000 searches but dominated by 3 established brands with 10,000+ reviews is a completely different opportunity from a keyword with the same search volume but fragmented sellers. Price range reveals profit potential — if all products are under $10, margins after FBA fees will be very thin.
Step 3: Check seasonality
Use on Google Trends web_fetch：
https://trends.google.com/trends/explore?q=<关键词>&geo=US
If Google Trends returns a 429 error, fall back to web_search to get seasonal data:
"<关键词>" seasonal trends demand peak months
Identify: trend direction (rising/falling/stable), seasonal peaks (which months), year-over-year change.
Why it matters: Seasonality determines cash flow risk. A product with 80% of sales concentrated in Q4 means you need to prepare inventory funds months in advance, and may face unsold inventory the rest of the year. An upward trend means demand growth and room for new entrants; a downward trend means you are competing for a shrinking market share. This context turns keywords from numbers into business decisions.
Step 4: Comprehensive Report
Combine all data into the output format below.
Why structure matters: Grouping keywords by intent (commercial intent vs informational intent vs niche intent) helps sellers understand not only what people search for, but also why they search. The opportunity score condenses multiple signals into one actionable number, but the breakdown behind it is what truly informs decisions — so always show the reasoning process.
Output Format
Present the final report using the following structure:
## 关键词研究报告：[关键词]
**市场：** 亚马逊 [美国/英国/德国/...]
**日期：** [当前日期]
### 1. 长尾关键词（找到[数量]个）
**高商业意图：**
- [包含"buy"、"best"、"vs"、"for"等的关键词]
- ...
**信息性/研究性：**
- [包含"how to"、"what is"、"review"等的关键词]
- ...
**利基/特定：**
- [表明明确购买意图的长而具体的关键词]
- ...
### 2. 竞争格局
| 指标 | 值 |
|--------|-------|
| 估计竞争对手数 | [数量] |
| 价格范围 | $[最低] - $[最高] |
| 平均价格 | $[平均] |
| 平均评分 | [星级] |
| 顶级品牌 | [品牌1、品牌2、品牌3...] |
### 3. 季节性趋势
[描述12个月趋势：高峰、低谷、稳定期]
[注意与关键词相关的即将到来的高峰季节]
### 4. 市场机会评分：[X/10]
**评分细分：**
- 竞争密度：[低/中/高] — [原因]
- 价格空间：[低/中/高] — [原因]
- 需求趋势：[增长/稳定/下降] — [原因]
- 利基潜力：[低/中/高] — [原因]
**建议：** [1-2句可操作的建议]
Multi-Keyword Comparison
When the user asks to compare two or more keywords, run the complete workflow (Step 1 to Step 4) for each keyword separately, then present the results in a side-by-side comparison table.
Example user input:
比较亚马逊美国的"laptop stand"、"monitor stand"和"tablet stand" — 我应该卖哪个？
How to execute: Run the script 3 times:
<skill>/scripts/research.sh "laptop stand" us
<skill>/scripts/research.sh "monitor stand" us
<skill>/scripts/research.sh "tablet stand" us
Then complete Step 2 and Step 3 for each keyword, and output the comparison table:
| Metric | laptop stand | monitor stand | tablet stand |
|---|---|---|---|
| Number of long-tail keywords | — | — | — |
| Average price | — | — | — |
| Top brand dominance | — | — | — |
| Trend direction | — | — | — |
| Opportunity score | — | — | — |
End withRecommendation, explaining which keyword has the greatest opportunity and why.
Limitations
- Keyword counts are based on autocomplete returns and may be incomplete
- Competition data comes from web searches and is estimated
- Trend data comes from Google Trends and may be delayed
- Recommendations are for reference only — do your own research before making business decisions