$npx -y skills add nexscope-ai/Amazon-Skills --skill amazon-keyword-researchAmazon keyword research and market opportunity analysis for sellers. Retrieve autocomplete suggestions (long-tail keywords), analyze competitor landscape, and assess market opportunity for any keyword on 12 Amazon marketplaces (US/UK/DE/FR/IT/ES/JP/CA/AU/IN/MX/BR). No API key req
| 1 | # Amazon Keyword Research 🔍 |
| 2 | |
| 3 | Free keyword research for Amazon sellers. No API key — works out of the box. |
| 4 | |
| 5 | ## Installation |
| 6 | |
| 7 | ```bash |
| 8 | npx skills add nexscope-ai/Amazon-Skills --skill amazon-keyword-research -g |
| 9 | ``` |
| 10 | |
| 11 | ## Capabilities |
| 12 | |
| 13 | - **Long-tail keyword mining**: Extract 100-200 real search terms from Amazon's autocomplete engine |
| 14 | - **Competitor landscape analysis**: Product count, price range, average rating, review distribution, top brands |
| 15 | - **Seasonal trend detection**: 12-month Google Trends data to identify peak seasons and demand shifts |
| 16 | - **Market opportunity scoring**: 1-10 score combining competition density, price room, and demand signals |
| 17 | - **Multi-marketplace support**: US, UK, DE, FR, IT, ES, JP, CA, AU, IN, MX, BR |
| 18 | - **Keyword comparison**: Side-by-side analysis of multiple keywords |
| 19 | |
| 20 | ## Usage Examples |
| 21 | |
| 22 | Users can ask naturally. Examples: |
| 23 | |
| 24 | ``` |
| 25 | Research the keyword "portable blender" on Amazon US |
| 26 | ``` |
| 27 | |
| 28 | ``` |
| 29 | Find long-tail keywords for "yoga mat" on Amazon |
| 30 | ``` |
| 31 | |
| 32 | ``` |
| 33 | I want to sell resistance bands. What does the Amazon keyword landscape look like? |
| 34 | ``` |
| 35 | |
| 36 | ``` |
| 37 | Compare "laptop stand" vs "monitor stand" on Amazon US — which has more opportunity? |
| 38 | ``` |
| 39 | |
| 40 | ``` |
| 41 | Analyze "Küchenmesser" on Amazon Germany |
| 42 | ``` |
| 43 | |
| 44 | ``` |
| 45 | Research "water bottle" across Amazon US, UK, and DE |
| 46 | ``` |
| 47 | |
| 48 | ## Workflow |
| 49 | |
| 50 | ### Step 1: Gather Autocomplete Data |
| 51 | |
| 52 | Run the bundled script to collect Amazon autocomplete suggestions: |
| 53 | |
| 54 | ```bash |
| 55 | <skill>/scripts/research.sh "<keyword>" [marketplace] |
| 56 | ``` |
| 57 | |
| 58 | **Parameters:** |
| 59 | - `keyword` (required): The seed keyword to research |
| 60 | - `marketplace` (optional): `us` (default), `uk`, `de`, `fr`, `it`, `es`, `jp`, `ca`, `au`, `in`, `mx`, `br` |
| 61 | |
| 62 | **What the script does:** |
| 63 | - Queries Amazon's autocomplete API with the seed keyword |
| 64 | - Expands with prefixes: "best [keyword]", "cheap [keyword]", "top [keyword]" |
| 65 | - Expands with a-z suffixes: "[keyword] a", "[keyword] b", ... "[keyword] z" |
| 66 | - Returns deduplicated, sorted list of real search suggestions — one per line |
| 67 | |
| 68 | **Why this matters:** Amazon autocomplete reflects what real shoppers are actually typing. These aren't guesses — they're demand signals directly from Amazon's search engine. The prefix and alphabet expansion catches long-tail terms that basic autocomplete misses, which are often lower competition and higher intent. |
| 69 | |
| 70 | Example: |
| 71 | ```bash |
| 72 | <skill>/scripts/research.sh "portable blender" us |
| 73 | # Returns 100-200 long-tail keywords |
| 74 | ``` |
| 75 | |
| 76 | For multi-marketplace research, run the script once per marketplace. |
| 77 | |
| 78 | ### Step 2: Analyze Competition |
| 79 | |
| 80 | Use `web_search` to gather competitor intelligence: |
| 81 | |
| 82 | 1. Search `"<keyword>" site:amazon.com` — note approximate result count for competition density |
| 83 | 2. Search `"<keyword>" amazon best sellers price review` — extract price patterns, rating averages, dominant brands |
| 84 | 3. Summarize: total competitors, price range (min/avg/max), average star rating, top 5 brands by visibility |
| 85 | |
| 86 | **Why this matters:** Raw keyword volume means nothing without competition context. A keyword with 10,000 searches but dominated by 3 entrenched brands with 10,000+ reviews each is a very different opportunity than one with the same volume but fragmented sellers. The price range reveals margin potential — if everything is under $10, margins will be razor-thin after FBA fees. |
| 87 | |
| 88 | ### Step 3: Check Seasonality |
| 89 | |
| 90 | Use `web_fetch` on Google Trends: |
| 91 | |
| 92 | ``` |
| 93 | https://trends.google.com/trends/explore?q=<keyword>&geo=US |
| 94 | ``` |
| 95 | |
| 96 | If Google Trends returns a 429 error, fall back to `web_search` for seasonal data: |
| 97 | ``` |
| 98 | "<keyword>" seasonal trends demand peak months |
| 99 | ``` |
| 100 | |
| 101 | Identify: trend direction (rising/declining/stable), seasonal peaks (which months), year-over-year change. |
| 102 | |
| 103 | **Why this matters:** Seasonality determines cash flow risk. A product that sells 80% of its volume in Q4 means you need capital for inventory months in advance and may sit on dead stock the rest of the year. Rising trends mean growing demand and more room for new entrants; declining trends mean yo |