agentmods.dev

linkfox-amazon-ads

linkfox-amazon-ads is a skill for Claude Code, Codex from linkfox-ai/linkfox-skills. It costs 0 tokens per session (6,595 once invoked), scanned A, original, MIT.

An Amazon Ads toolkit covering account authorisation, advertising management, and reporting. Amazon Ads is Amazon's platform for running and measuring product and brand advertisements.

In plain words
What is it for?
Use it to authorise accounts, manage Sponsored Products, Sponsored Brands, and Sponsored Display campaigns, or fetch their reports.
Why use it?
It brings the full workflow together, from connecting accounts and finding ad data to changing campaigns and retrieving reports.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

not rated 101repo +6 22d ago A scan SkillSpector: pass 0 tokens original MIT

Good fit Use it to authorise accounts, manage Sponsored Products, Sponsored Brands, and Sponsored Display campaigns, or fetch their reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/linkfox-ai/linkfox-skills/linkfox-amazon-ads
View source ↗ linkfox-ai/linkfox-skills
Install

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.

Any agent
npx skills add linkfox-ai/linkfox-skills --skill linkfox-amazon-ads
Clone the repo
git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for linkfox-amazon-ads

README.md
[![agentmods](https://agentmods.dev/badge/skills/linkfox-ai/linkfox-skills/linkfox-amazon-ads/github.svg)](https://agentmods.dev/skills/linkfox-ai/linkfox-skills/linkfox-amazon-ads)
Your own site
<a href="https://agentmods.dev/skills/linkfox-ai/linkfox-skills/linkfox-amazon-ads"><img src="https://agentmods.dev/badge/skills/linkfox-ai/linkfox-skills/linkfox-amazon-ads/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.

agentmods 80×15 button for linkfox-amazon-ads

Your own site · 80×15
<a href="https://agentmods.dev/skills/linkfox-ai/linkfox-skills/linkfox-amazon-ads"><img src="https://agentmods.dev/badge/skills/linkfox-ai/linkfox-skills/linkfox-amazon-ads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,595 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.06595
Opus 5 $0.00000 $0.03298
Sonnet 5 $0.00000 $0.01319
Haiku 4.5 $0.00000 $0.00660

Measured 12d ago against content hash 5be4efeb0170, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

linkfox-amazon-ads 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 12d ago.

The scan reads SKILL.md. This mod also ships 27 executable files (scripts/auth/_lf_output.py, scripts/auth/authorize_url.py, scripts/auth/authorized_stores.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/linkfox-amazon-ads-<auth|manager|report>.md`（文件内含该子能力 SKILL.md 正文与 api.md 全文）；manager 的 SP/SB/SD 过滤器/枚举/字段见 `references/api/{sp,sb,sd}.md`，report 的报告类型规格见 `references/r
skills/linkfox-amazon-ads/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Linkfox 亚马逊广告（Amazon Ads）

亚马逊广告（Amazon Ads）全链路一站式 AI 工具集，整合 3 项子能力，覆盖授权与令牌、SP/SB/SD 广告查询与写操作、广告报告一站式获取。三条子能力构成「授权 → 管理 → 报表」链路：linkfox-amazon-ads-auth 是前置依赖（产出 profileId + 访问令牌），linkfox-amazon-ads-manager（实体元数据）与 linkfox-amazon-ads-report（指标报表）均依赖它。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/<auth|manager|report>/。

能力边界

✅ 能力范围

  • 授权与令牌管理（子能力 linkfox-amazon-ads-auth，tool_key amazon_ads）：为新账号生成 LWA OAuth 授权链接，一次授权自动发现并绑定同账号下所有可用站点的广告 profile（每站点一个 profileId）；查询已授权账号 × 站点列表与 profile 列表；读取与刷新访问令牌（accessToken 1 小时有效）；为下游解析 profileId。支持 NA（美加墨巴）/ EU（英德法意西荷印等）/ FE（日澳新）三大区域，默认 NA。
  • 广告管理（子能力 linkfox-amazon-ads-manager，tool_key amazon_ads）：查询（list）与创建/修改（create/update）SP/SB/SD 三条产品线的广告活动、广告组、关键词、否定关键词、商品广告、定向、否定定向、创意、预算规则等实体元数据；含出价调整、预算修改、状态变更、Budget Rules；自动分页、过滤器结构规范化、多账号 profileId 解析。写操作遵循财务安全指引（先确认再执行、执行后输出回执）。
  • 广告报告（子能力 linkfox-amazon-ads-report，tool_key amazon_ads）：一站式获取 SP/SB/SD 全量广告报告，脚本内部完成报告创建 → 等待生成 → 下载 → 解压，直接返回结构化数据；支持全链路模式与仅轮询模式（用 reportId 救回上次超时）。每个 reportTypeId 的可用 columns/groupBy/filters/timeUnit/日期约束以 references/report-types/<adProduct-dir>/<reportTypeId>.md 为单一真相源。
  • 链路依赖：manager 与 report 调用前必须先经 auth 拿到 profileId（数字，内部传递不播报）；令牌过期（下游 HTTP 401）时回 auth 用 refresh_token.py 续签。多账号场景按 countryCode/accountName 澄清，严禁让用户直接报 profileId 数字、严禁歧义下挑第一个。

❌ 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）；各子能力独立计费、独立限频。
  • accountName 必填：调 authorize_url.py 前必须先向用户确认一个非空账号名。
  • 令牌时效：accessToken 有效期 1 小时，过期后下游返回 HTTP 401，需用 refresh_token.py 续签。
  • manager 只给元数据，不含指标：返回实体字段（id/名称/状态/匹配类型等）；曝光/点击/花费/转化等指标交给 report，按 id join。
  • manager 不支持 DELETE：可通过 update state=ARCHIVED 归档，但不可逆；SB keywords/targets 等无 list all（Amazon 官方未提供，需按 id 单查，不在本 skill）；SD 非基础实体接口（brandSafety/recommendations/forecasts/optimizationRules/locations 等）不在范围。
  • report 日期约束：多数报告跨度上限 31 天，sbPurchasedProduct 731 天，GrossAndInvalids 系列 365 天（以 frontmatter dateRange.maxSpanDays 为准）；回溯窗口 SP 默认 95 天、SB 60 天、GrossAndInvalids 365 天（以 dateRange.dataRetentionDays 为准）；数据延迟约 12 小时。
  • 未覆盖：Sponsored Television (ST) / Amazon DSP；Brand Analytics / Retail Analytics / Attribution 报告；报告删除/修改/定时任务。
  • 计费约束：同一会话同一参数组合默认只调用一次；失败或空结果不得自动换关键词、翻页或连续试探；需继续检索时先向用户说明会产生额外消耗（各子能力计费规则见 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）、选品调研（用亚马逊选品系列）、1688 找货源、TikTok/沃尔玛等其他平台、与平台或卖家的直接沟通。

Read the full file on GitHub · 217 lines

Files

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.

Changes

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.

  1. 12d ago First seen · 217 lines · 0 tokens per session scan A 5be4efeb0170

Subscribe to this mod's changes

linkfox-amazon-ads is a skill published in the GitHub repository linkfox-ai/linkfox-skills (101 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,595 tokens. 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.

E-commerceMarketing and SEOe-commerce
Related

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.

buluslan/review-analyzer-skill · 340 tokens

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…

spree/spree · 90 tokens

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…

spree/spree · 96 tokens

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.

spree/spree · 35 tokens

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.

saleor/storefront · 68 tokens

paper-migrations

Apply chronological Paper storefront upgrades to a forked shop. Use when the user says upgrade Paper, apply Paper migrations, catch up with upstream caching, or paper-version. Reads migrations/manifest.json and paper-version.json; ports architecture without overwriting custom styling.

saleor/storefront · 55 tokens