Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/linkfox-ai/linkfox-skillsnpx agentmods add skills/linkfox-ai/linkfox-skills/linkfox-amazon-ads-managerWrote 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-ads-manager)<a href="https://agentmods.dev/skills/linkfox-ai/linkfox-skills/linkfox-amazon-ads-manager"><img src="https://agentmods.dev/badge/skills/linkfox-ai/linkfox-skills/linkfox-amazon-ads-manager/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-ads-manager"><img src="https://agentmods.dev/badge/skills/linkfox-ai/linkfox-skills/linkfox-amazon-ads-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00156 | $0.05259 |
| Opus 5 | $0.00078 | $0.02629 |
| Sonnet 5 | $0.00031 | $0.01052 |
| Haiku 4.5 | $0.00016 | $0.00526 |
Grade A, and why
linkfox-amazon-ads-manager 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 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.
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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amazon Ads 广告管理
Amazon Ads 广告管理 skill，支持 list（查询）和 create / update（创建与修改）操作；经 developerProxy 传 profileId，由服务端解析 token（勿先 storeTokens 取 raw token）。自动处理分页、过滤字段规范化。
| 广告产品 | 覆盖实体 | 脚本子目录 | 详细参数 |
|---|---|---|---|
| SP (Sponsored Products) v3 | campaigns / adGroups / keywords / negativeKeywords / productAds / targets | scripts/sp/ |
references/api/sp.md |
| SB V3 Legacy + V4 | V3 campaigns/keywords/targets；V4 campaigns/adGroups/ads/keywords/targets/creatives | scripts/sb/v3/、scripts/sb/v4/ |
references/api/sb.md |
| SD (Sponsored Display) v3 | campaigns / adGroups / productAds / targets / negativeTargets / creatives | scripts/sd/ |
references/api/sd.md |
依赖 linkfox-amazon-ads-auth（脚本启动时自动检查；未安装时 exit 42，stderr 打 DEPENDENCY_MISSING）。
⚠️ 多账号场景：调用前必须解析好 profileId
用户经常只说自然语言（"美国站"、"日本站"、"我的店铺"），本 skill 的所有脚本都必须拿到数字 profileId 才能调。按下列顺序处理，不要跳过：
- 先调
linkfox-amazon-ads-auth的authorized_stores.py拉出用户已授权的账号 × 站点清单。 - 根据用户提到的站点（映射到
countryCode，如 美国→US）匹配候选 profile：- 只有 1 个候选 → 静默取对应 profileId，继续调用；不要把 profileId 数字播报给用户。
- ≥ 2 个候选（同站点下多个授权账号） → 必须向用户澄清，用
accountName问："你在美国站授权了 A 和 B 两个账号，这次用哪个？" - 0 个候选 → 告知用户该站点未授权，引导去
linkfox-amazon-ads-auth做授权。
- 严禁让用户直接报 profileId 数字。
- 严禁在歧义下"挑第一个"或"选默认"绕过澄清。
完整决策表见 linkfox-amazon-ads-auth SKILL.md 的 Usage Scenarios 第 4 节。
Core Concepts
- 自动分页：
fetchAll=true（默认）跟随分页到结束或maxPages=50兜底；SP/SB V4/Target 用nextToken，SB V3 GET 与 SD 用startIndex + count - 过滤器结构不统一：不同字段需要不同写法（详见下方"过滤器结构速查"）；本 skill 已对常见写错格式做自动兜底规范化，但仍建议按速查表准确传入
- 只给 metadata，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 等指标要调
linkfox-amazon-ads-report，按 id join - 支持 create / update：各模块下
create_*.py/update_*.py脚本创建或修改实体（campaign / adGroup / keyword / target / productAd / creative / budgetRule），payload 透传 Amazon 原生格式 - SB V3/V4 共存：默认使用
scripts/sb/v4/；只有确认是 Legacy 或用户明确要求 V3 时使用scripts/sb/v3/。不自动执行 V4→V3 回落；已知 Multi-Ad-Group Campaign 必须拒绝 V3 - SB 共享 Targeting：Amazon 的 Keyword/Target 仍使用
sb/keywords、sb/targets[/list]，没有伪造的/sb/v4/keywords；V3/V4 脚本入口隔离，但底层共享官方 targeting 资源 - SD 接口形态：Sponsored Display 是 v3 REST endpoint，
GET /sd/<entity>+ querystring，分页用startIndex + count；state / id 类过滤为逗号分隔字符串；includeExtendedDataFields:true时请求/sd/<entity>/extended路径。所有过滤字段统一支持{"include":[...]}入参
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/api.md 3.5 KB
- references/api/sb-coexistence.md 2.9 KB
- references/api/sb-v3.md 3.3 KB
- references/api/sb-v4.md 3.0 KB
- references/api/sb.md 1.1 KB
- references/api/sd.md 7.5 KB
- references/api/sp.md 5.2 KB
- references/onboarding.md 2.0 KB
- scripts/_common.py 30 KB runs code
- scripts/check_auth_dependency.py 6.4 KB runs code
- scripts/onboarding.py 24 KB runs code
- scripts/sb/_sb_common.py 16 KB runs code
- scripts/sb/create_ad_groups.py 250 B runs code
- scripts/sb/create_ads.py 238 B runs code
- scripts/sb/create_budget_rules.py 256 B runs code
- scripts/sb/create_campaigns.py 250 B runs code
- scripts/sb/list_ad_groups.py 246 B runs code
- scripts/sb/list_ads.py 234 B runs code
- scripts/sb/list_budget_rules.py 252 B runs code
- scripts/sb/list_campaigns.py 246 B runs code
- scripts/sb/update_ad_groups.py 250 B runs code
- scripts/sb/update_ads.py 238 B runs code
- scripts/sb/update_budget_rules.py 256 B runs code
- scripts/sb/update_campaigns.py 250 B runs code
- scripts/sb/v3/create_campaigns.py 574 B runs code
- scripts/sb/v3/create_keywords.py 596 B runs code
- scripts/sb/v3/create_targets.py 596 B runs code
- scripts/sb/v3/list_ad_groups.py 670 B runs code
- scripts/sb/v3/list_campaigns.py 674 B runs code
- scripts/sb/v3/list_keywords.py 742 B runs code
- scripts/sb/v3/list_targets.py 691 B runs code
- scripts/sb/v3/update_campaigns.py 573 B runs code
- scripts/sb/v3/update_keywords.py 595 B runs code
- scripts/sb/v3/update_targets.py 595 B runs code
- scripts/sb/v4/create_ad_groups.py 459 B runs code
- scripts/sb/v4/create_ads.py 1.1 KB runs code
- scripts/sb/v4/create_budget_rules.py 467 B runs code
- scripts/sb/v4/create_campaigns.py 461 B runs code
- scripts/sb/v4/create_creatives.py 1.2 KB runs code
- scripts/sb/v4/create_keywords.py 596 B runs code
- scripts/sb/v4/create_targets.py 596 B runs code
- scripts/sb/v4/list_ad_groups.py 766 B runs code
- scripts/sb/v4/list_ads.py 750 B runs code
- scripts/sb/v4/list_budget_rules.py 449 B runs code
- scripts/sb/v4/list_campaigns.py 770 B runs code
- scripts/sb/v4/list_creatives.py 597 B runs code
- scripts/sb/v4/list_keywords.py 843 B runs code
- scripts/sb/v4/list_targets.py 684 B runs code
- scripts/sb/v4/update_ad_groups.py 457 B runs code
- scripts/sb/v4/update_ads.py 447 B runs code
- scripts/sb/v4/update_budget_rules.py 466 B runs code
- scripts/sb/v4/update_campaigns.py 459 B runs code
- scripts/sb/v4/update_keywords.py 595 B runs code
- scripts/sb/v4/update_targets.py 595 B runs code
- scripts/sd/create_ad_groups.py 1.7 KB runs code
- scripts/sd/create_budget_rules.py 1.7 KB runs code
- scripts/sd/create_campaigns.py 1.7 KB runs code
- scripts/sd/create_creatives.py 1.7 KB runs code
- scripts/sd/create_negative_targets.py 1.7 KB runs code
- scripts/sd/create_product_ads.py 1.7 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 · 324 lines · 156 tokens per session scan A 07c2e047f088
linkfox-amazon-ads-manager is a skill published in the GitHub repository linkfox-ai/linkfox-skills (101 stars, last pushed 20d ago), licensed MIT. It adds 156 tokens to every session and 5,259 once invoked, about $0.0008 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…