Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nexscope-ai/Amazon-Skills --skill amazon-keyword-researchgit clone --depth 1 https://github.com/nexscope-ai/Amazon-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nexscope-ai/amazon-skills/amazon-keyword-research)<a href="https://agentmods.dev/skills/nexscope-ai/amazon-skills/amazon-keyword-research"><img src="https://agentmods.dev/badge/skills/nexscope-ai/amazon-skills/amazon-keyword-research/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nexscope-ai/amazon-skills/amazon-keyword-research"><img src="https://agentmods.dev/badge/skills/nexscope-ai/amazon-skills/amazon-keyword-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 14 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00199 | $0.01910 |
| Opus 5 | $0.00100 | $0.00955 |
| Sonnet 5 | $0.00040 | $0.00382 |
| Haiku 4.5 | $0.00020 | $0.00191 |
Grade A, and why
amazon-keyword-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amazon Keyword Research 🔍
Free keyword research for Amazon sellers. No API key — works out of the box.
Installation
npx skills add nexscope-ai/Amazon-Skills --skill amazon-keyword-research -g
Capabilities
- Long-tail keyword mining: Extract 100-200 real search terms from Amazon's autocomplete engine
- Competitor landscape analysis: Product count, price range, average rating, review distribution, top brands
- Seasonal trend detection: 12-month Google Trends data to identify peak seasons and demand shifts
- Market opportunity scoring: 1-10 score combining competition density, price room, and demand signals
- Multi-marketplace support: US, UK, DE, FR, IT, ES, JP, CA, AU, IN, MX, BR
- Keyword comparison: Side-by-side analysis of multiple keywords
Usage Examples
Users can ask naturally. Examples:
Research the keyword "portable blender" on Amazon US
Find long-tail keywords for "yoga mat" on Amazon
I want to sell resistance bands. What does the Amazon keyword landscape look like?
Compare "laptop stand" vs "monitor stand" on Amazon US — which has more opportunity?
Analyze "Küchenmesser" on Amazon Germany
Research "water bottle" across Amazon US, UK, and DE
Workflow
Step 1: Gather Autocomplete Data
Run the bundled script to collect Amazon autocomplete suggestions:
<skill>/scripts/research.sh "<keyword>" [marketplace]
Parameters:
keyword(required): The seed keyword to researchmarketplace(optional):us(default),uk,de,fr,it,es,jp,ca,au,in,mx,br
What the script does:
- Queries Amazon's autocomplete API with the seed keyword
- Expands with prefixes: "best [keyword]", "cheap [keyword]", "top [keyword]"
- Expands with a-z suffixes: "[keyword] a", "[keyword] b", ... "[keyword] z"
- Returns deduplicated, sorted list of real search suggestions — one per line
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.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 201 lines · 199 tokens per session scan A 30dc7de84471
amazon-keyword-research is a skill published in the GitHub repository nexscope-ai/Amazon-Skills (661 stars, last pushed 17d ago), licensed MIT. It adds 199 tokens to every session and 1,910 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
1800flowers-checkout
Buy products from 1-800-Flowers (1800flowers.com) and manage those orders via the Zinc API (zinc.com). Use when the user wants to purchase, order, or check out an item from 1-800-Flowers, check 1-800-Flowers order status or tracking, cancel a 1-800-Flowers order, or return a 1-800-Flowers item. One API also covers…
send-donuts
Send a box of Krispy Kreme donuts (doughnuts) to someone by mail, paid with your own credit card via Stripe Link — driven entirely from the terminal. Use when the user wants to send donuts, doughnuts, treats, or a thank-you gift to a lead, prospect, customer, colleague, or friend — e.g. "send donuts to Jane at Acme"…
universal-checkout
Discover, buy, track, and return products across Amazon, Walmart, Target, Best Buy, eBay, and 50+ other US retailers via the Zinc API (zinc.com). Use when the user wants to search for or buy a product, check out, check order status or tracking, cancel an order, or return an item programmatically. Supports API key auth…
homedepot-checkout
Buy products from The Home Depot (homedepot.com) and manage those orders via the Zinc API (zinc.com). Use when the user wants to purchase, order, or check out an item from The Home Depot, check The Home Depot order status or tracking, cancel a The Home Depot order, or return a The Home Depot item. One API also covers…
bestbuy-checkout
Buy products from Best Buy (bestbuy.com) and manage those orders via the Zinc API (zinc.com). Use when the user wants to purchase, order, or check out an item from Best Buy, check Best Buy order status or tracking, cancel a Best Buy order, or return a Best Buy item. One API also covers Amazon, Walmart, Target, Best…
lowes-checkout
Buy products from Lowe's (lowes.com) and manage those orders via the Zinc API (zinc.com). Use when the user wants to purchase, order, or check out an item from Lowe's, check Lowe's order status or tracking, cancel a Lowe's order, or return a Lowe's item. One API also covers Amazon, Walmart, Target, Best Buy and 50+…