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 linkfox-ai/linkfox-skills --skill linkfox-amazon-product-selectiongit clone --depth 1 https://github.com/linkfox-ai/linkfox-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/linkfox-ai/linkfox-skills/linkfox-amazon-product-selection)<a href="https://agentmods.dev/skills/linkfox-ai/linkfox-skills/linkfox-amazon-product-selection"><img src="https://agentmods.dev/badge/skills/linkfox-ai/linkfox-skills/linkfox-amazon-product-selection/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/linkfox-ai/linkfox-skills/linkfox-amazon-product-selection"><img src="https://agentmods.dev/badge/skills/linkfox-ai/linkfox-skills/linkfox-amazon-product-selection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high YARA Match · line 5 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00081 | $0.06623 |
| Opus 5 | $0.00041 | $0.03312 |
| Sonnet 5 | $0.00016 | $0.01325 |
| Haiku 4.5 | $0.00008 | $0.00662 |
Grade A, and why
linkfox-amazon-product-selection scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **完整参数**：每个子能力的请求参数、响应字段、错误码、curl 示例见 `references/<源skill>.md`（文件内含该子能力 SKILL.md 正文与 api.md 全文）。 How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linkfox 亚马逊选品（Amazon Product Selection）
亚马逊选品一站式 AI 工具集，整合 12 类底层工具、33 项子能力，覆盖前台实时、历史时序、关键词与流量、利基市场、商业洞察与评论挖掘。各子能力完整参数、响应字段与错误码见 references/ 下对应文件，可执行脚本见 scripts/。
能力边界
✅ 能力范围
- 前台实时数据：关键词搜索排名与 SERP、以图搜图（
amazon_search）、商品详情/五点/A+/变体（amazon_product_detail）、按星级筛选评论（amazon_reviews）、Alexa 自然语言导购（amazon_alexa_assistant）。 - 竞品搜索：卖家精灵竞品查询（按关键词/ASIN/卖家/品牌/类目反查竞品，含销量、BSR、定价、评分与增长趋势，
sellersprite竞品查询）、极目按 ASIN 挖同细分市场竞品并按转化率/销量/价格/利润多维筛选（jiimorepage-asins-by-asin）。 - 历史时序与趋势：Keepa 商品详情/搜索/历史曲线（
keepa，价格/BSR/月销/卖家数）、Sorftime 详情/搜索与趋势回看（sorftime，含 FBA 利润、Deal 历史、历史快照）。 - 关键词与流量分析：ABA 搜索词挖掘（
amazon_aba_search_term）、Jungle Scout 反查/拓展/历史/声量份额（jungle_scout）、SIF ASIN 关键词反查/ASIN 流量结构/关键词竞争概览/关键词下竞品流量来源拆解（sif_search_intelligence）、卖家精灵流量词反查（sellersprite流量关键词）。 - 利基与市场分析：极目细分市场指标/评论/竞品/潜力爆品（
jiimore）、卖家精灵商品搜索选品、选市场列表与统计看板（sellersprite）、Jungle Scout 商品库与销量预估（jungle_scout）。 - 商业洞察与反向选品：按关键词生成市场潜力/产品特征/评论/客户画像/搜索趋势/定价六维 AI 报告，按 30+ 商业维度反向筛选蓝海赛道（
amazon_business_insight）。 - 覆盖美国、英国、德国、法国、日本、加拿大、意大利、西班牙、印度、墨西哥、巴西等 15+ 站点（站点集合随工具略有差异，详见各 references）。
❌ 边界与限制
- API Key 必需：所有工具均需环境变量
LINKFOX_AGENT_API_KEY（或LINKFOXAGENT_API_KEY）；各工具独立计费、独立限频，数据时效与站点覆盖随数据源而异。 - 计费约束：同一会话同一参数组合默认只调用一次（脚本带 24h 本地缓存）；失败或空结果不得自动换关键词、翻页或改邮编连续试探；需继续检索时先向用户说明会产生额外消耗（各工具计费规则见
skills-version.json对应条目与 references 内 api.md 的costToken字段）。 - 不在范围内：店铺运营（Listing 刊登/订单/库存，用 SP-API 系列）、广告投放与管理（用 Amazon Ads 系列）、物流与供应链规划、1688 找货源、TikTok/沃尔玛等其他平台选品、非电商任务、与平台或卖家的直接沟通、实时库存与订单处理。
- 数据时效：前台类工具为实时抓取（含 SERP 排名、评论、Alexa）；历史类（Keepa/Sorftime/ABA）为各自数据源的更新周期，
lastUpdate/costToken等字段标识刷新与消耗。
工具选择指南
按需求在下表定到子能力，再跳到【业务需求路由速查】查端点/脚本/references 取参执行。
| 需求 / 用户说 | 默认推荐（子能力） | 何时换用其他 |
|---|---|---|
| ASIN 商品数据 / 价格销量趋势（"这个 ASIN 卖得怎么样"） | linkfox-keepa-product-request（字段最全） |
要 FBA 利润+趋势回看用 linkfox-sorftime-amazon-product-detail；要 A+/变体/实时价用 linkfox-amazon-product-detail |
| ASIN 流量词反查（"ASIN 的流量词有哪些"） | linkfox-sif-asin-keywords（流量词+排名+搜索量） |
要 PPC 竞价+排名难度用 linkfox-junglescout-keyword-by-asin；要转化类型+历史月份用 linkfox-sellersprite-traffic-keyword |
| 关键词拓展 / 相关流量词（"这个词有哪些相关词/长尾词"） | linkfox-junglescout-keyword-by-keyword（种子词拓展，含搜索量/趋势/PPC 竞价） |
要按 ASIN 反查其流量词用 linkfox-sif-asin-keywords；要官方搜索词排名（非拓展）用 linkfox-aba-intelligent-query |
| 关键词搜索量趋势（"这个词的搜索量/排名"） | linkfox-junglescout-keyword-history（精确搜索量） |
要官方搜索排名（非搜索量）用 linkfox-aba-intelligent-query |
| 商品搜索 / 选品筛选（"帮我选品 / 什么好卖"） | linkfox-keepa-product-search（多维+历史） |
要历史快照回看用 linkfox-sorftime-amazon-product-query；要毛利筛选用 linkfox-sellersprite-product-search；要实时 SERP 用 linkfox-amazon-search |
| 关键词竞争度（"这个词竞争大不大"） | linkfox-sif-keyword-overview（供需比+搜索量） |
要品牌声量份额用 linkfox-junglescout-keyword-share-of-voice |
| 利基 / 细分市场评估（"细分市场能不能进"） | linkfox-jiimore-get-niche-info-by-keyword（垄断/品牌/新品成功率） |
要类目维度看板用 linkfox-sellersprite-market-research / -market-statistics；要多条件筛选商品库用 linkfox-junglescout-product-database |
| ASIN 销量预估 | linkfox-junglescout-sales-estimates（日维度） |
要 12 月月销趋势用 linkfox-keepa-product-request |
| 利基评论 / 痛点（"评论痛点 / 差评"） | linkfox-jiimore-get-niche-review-from-keyword（细分市场级） |
要单 ASIN 评论用 linkfox-amazon-reviews-list |
| ASIN 流量结构 / 竞品分析 | linkfox-sif-asin-summary（ASIN 流量构成） |
要关键词下竞品流量拆解用 linkfox-sif-keyword-summary |
| 竞品反查（关键词/ASIN/卖家/品牌） | linkfox-sellersprite-competitor-lookup |
要按 ASIN 挖同细分竞品用 linkfox-jiimore-page-asins-by-asin |
| 六维 AI 市场报告（"AI 市场报告"） | linkfox-amazon-opportunity-report-by-keyword |
— |
| 反向按指标找赛道（"按条件反找赛道"） | linkfox-amazon-opportunity-search-by-metrics |
— |
| 前台实时搜索 / 以图搜图（"前台搜一下这个词"） | linkfox-amazon-search / linkfox-amazon-search-by-image |
— |
| 自然语言导购（"用自然语言问亚马逊推荐"） | linkfox-amazon-alexa-search |
— |
What ships with it
60 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.
- references/linkfox-aba-intelligent-query.md 12 KB
- references/linkfox-amazon-alexa-search.md 13 KB
- references/linkfox-amazon-opportunity-report-by-keyword.md 8.2 KB
- references/linkfox-amazon-opportunity-search-by-metrics.md 21 KB
- references/linkfox-amazon-product-detail.md 15 KB
- references/linkfox-amazon-reviews-list.md 11 KB
- references/linkfox-amazon-search-by-image.md 15 KB
- references/linkfox-amazon-search.md 14 KB
- references/linkfox-jiimore-get-niche-info-by-keyword.md 18 KB
- references/linkfox-jiimore-get-niche-info.md 20 KB
- references/linkfox-jiimore-get-niche-review-from-keyword.md 16 KB
- references/linkfox-jiimore-page-asins-by-asin.md 17 KB
- references/linkfox-jiimore-product-discovery.md 14 KB
- references/linkfox-junglescout-keyword-by-asin.md 16 KB
- references/linkfox-junglescout-keyword-by-keyword.md 14 KB
- references/linkfox-junglescout-keyword-history.md 10 KB
- references/linkfox-junglescout-keyword-share-of-voice.md 13 KB
- references/linkfox-junglescout-product-database.md 16 KB
- references/linkfox-junglescout-sales-estimates.md 12 KB
- references/linkfox-keepa-product-request.md 14 KB
- references/linkfox-keepa-product-search.md 18 KB
- references/linkfox-keepa-product-series.md 12 KB
- references/linkfox-sellersprite-competitor-lookup.md 16 KB
- references/linkfox-sellersprite-market-research.md 16 KB
- references/linkfox-sellersprite-market-statistics.md 9.8 KB
- references/linkfox-sellersprite-product-search.md 23 KB
- references/linkfox-sellersprite-traffic-keyword.md 12 KB
- references/linkfox-sif-asin-keywords.md 17 KB
- references/linkfox-sif-asin-summary.md 18 KB
- references/linkfox-sif-keyword-overview.md 14 KB
- references/linkfox-sif-keyword-summary.md 19 KB
- references/linkfox-sorftime-amazon-product-detail.md 16 KB
- references/linkfox-sorftime-amazon-product-query.md 18 KB
- references/onboarding.md 2.0 KB
- scripts/aba_query.py 12 KB runs code
- scripts/amazon_alexa_search.py 12 KB runs code
- scripts/amazon_opportunity_report.py 12 KB runs code
- scripts/amazon_opportunity_screener.py 12 KB runs code
- scripts/amazon_product_detail.py 12 KB runs code
- scripts/amazon_reviews.py 12 KB runs code
- scripts/amazon_search_by_image.py 12 KB runs code
- scripts/amazon_search.py 12 KB runs code
- scripts/jiimore_get_niche_info_by_keyword.py 13 KB runs code
- scripts/jiimore_get_niche_info.py 13 KB runs code
- scripts/jiimore_get_niche_review.py 13 KB runs code
- scripts/jiimore_page_asins_by_asin.py 13 KB runs code
- scripts/jiimore_product_discovery.py 13 KB runs code
- scripts/junglescout_keyword_by_asin.py 13 KB runs code
- scripts/junglescout_keyword_by_keyword.py 13 KB runs code
- scripts/junglescout_keyword_history.py 13 KB runs code
- scripts/junglescout_keyword_sov.py 13 KB runs code
- scripts/junglescout_product_database.py 13 KB runs code
- scripts/junglescout_sales_estimates.py 13 KB runs code
- scripts/keepa_product_detail.py 13 KB runs code
- scripts/keepa_product_history.py 13 KB runs code
- scripts/keepa_product_search.py 12 KB runs code
- scripts/onboarding.py 24 KB runs code
- scripts/sellersprite_competitor_lookup.py 13 KB runs code
- scripts/sellersprite_market_research.py 13 KB runs code
- scripts/sellersprite_market_statistics.py 13 KB runs code
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.
- 11d ago First seen · 269 lines · 81 tokens per session scan A 6df9b35de76f
linkfox-amazon-product-selection is a skill published in the GitHub repository linkfox-ai/linkfox-skills (101 stars, last pushed 21d ago), licensed MIT. It adds 81 tokens to every session and 6,623 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
review-analyzer-skill
A review-analysis tool for studying product reviews, also called voice-of-the-customer analysis. It turns review data into labelled customer patterns, findings, reports, and visual dashboards.
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…
animate
Build an animation from scratch, making the decisions in the order that determines whether it feels right — should it animate at all, what purpose, which tool, which properties, which curve and duration, how it interrupts, how it exits. Writes the implementation. Use when asked to animate something, add motion, make a…
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…
saleor-paper-storefront
Project-specific patterns for the Saleor Paper storefront built with Next.js 16, TypeScript, and Tailwind CSS. Use when working with product pages, checkout flow, caching, variant selection, filtering, SEO, or UI components. For universal Saleor API patterns, see the saleor-storefront dependency.