Agent skill

Linkfox Amazon Ads Manager

by linkfox-ai in linkfox-ai/linkfox-skills

亚马逊广告（Amazon Ads）管理技能，覆盖 SP/SB/SD 的查询与创建/修改。Sponsored Brands 同时支持 V3 Legacy 与 V4：新活动、多 Ad Group、Ad/Creative Version 默认走 V4，历史 Legacy 可显式走 V3，Keyword/Target 按 Campaign 结构通过版本化脚本调用 Amazon 共享 targeting…

MITAuto-check passedMarketing & SEO

Install Linkfox Amazon Ads Manager

skills CLI

$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-amazon-ads-manager -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install linkfox-ai/linkfox-skills linkfox-amazon-ads-manager --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/linkfox-amazon-ads-manager .claude/skills/linkfox-amazon-ads-manager && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "linkfox-amazon-ads-manager" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-amazon-ads-manager into .claude/skills/linkfox-amazon-ads-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-amazon-ads-manager", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-amazon-ads-manager

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-amazon-ads-manager -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install linkfox-ai/linkfox-skills linkfox-amazon-ads-manager --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/linkfox-amazon-ads-manager .agents/skills/linkfox-amazon-ads-manager && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "linkfox-amazon-ads-manager" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-amazon-ads-manager into .agents/skills/linkfox-amazon-ads-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-amazon-ads-manager", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-amazon-ads-manager -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install linkfox-ai/linkfox-skills linkfox-amazon-ads-manager --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/linkfox-amazon-ads-manager .cursor/skills/linkfox-amazon-ads-manager && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "linkfox-amazon-ads-manager" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-amazon-ads-manager into .cursor/skills/linkfox-amazon-ads-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-amazon-ads-manager", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/linkfox-ai/linkfox-skills.git --path skills/linkfox-amazon-ads-manager

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-amazon-ads-manager -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install linkfox-ai/linkfox-skills linkfox-amazon-ads-manager --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/linkfox-amazon-ads-manager .gemini/skills/linkfox-amazon-ads-manager && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "linkfox-amazon-ads-manager" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-amazon-ads-manager into .gemini/skills/linkfox-amazon-ads-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-amazon-ads-manager", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install linkfox-ai/linkfox-skills linkfox-amazon-ads-manager

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-amazon-ads-manager -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/linkfox-amazon-ads-manager .github/skills/linkfox-amazon-ads-manager && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "linkfox-amazon-ads-manager" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-amazon-ads-manager into .github/skills/linkfox-amazon-ads-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-amazon-ads-manager", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add linkfox-ai/linkfox-skills --skill linkfox-amazon-ads-manager -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install linkfox-ai/linkfox-skills linkfox-amazon-ads-manager --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/linkfox-ai/linkfox-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/linkfox-amazon-ads-manager .opencode/skills/linkfox-amazon-ads-manager && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "linkfox-amazon-ads-manager" agent skill from https://github.com/linkfox-ai/linkfox-skills/tree/main/skills/linkfox-amazon-ads-manager into .opencode/skills/linkfox-amazon-ads-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linkfox-amazon-ads-manager", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: linkfox-amazon-ads-manager
GitHub stars: 107
Token cost: ~3.7k tokens
SKILL.md length: 1,033 words
Files: 108 (incl. scripts, references)
Skills in repo: 177
Repo updated: Sep 14, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Works in 10 steps: 列活跃 SP 广告活动 → 看某 SP campaign 下的广告组 → 按 ASIN 反查 SP 投放（客户端过滤） → …
Tasks that involve Paid advertising
SKILL.md covers Core Concepts, 可用脚本, 调用方式 and 解决认证和算力问题, plus 9 more sections
Runs Python scripts from its folder; calls python; needs LINKFOX_AGENT_API_KEY and LINKFOXAGENT_API_KEY

What it does

Linkfox Amazon Ads Manager is an agent skill from linkfox-ai/linkfox-skills. 亚马逊广告（Amazon Ads）管理技能，覆盖 SP/SB/SD 的查询与创建/修改。Sponsored Brands 同时支持 V3 Legacy 与 V4：新活动、多 Ad Group、Ad/Creative Version 默认走 V4，历史 Legacy 可显式走 V3，Keyword/Target 按 Campaign 结构通过版本化脚本调用 Amazon 共享 targeting 资源；禁止 V4 失败后自动回落 V3，禁止用 V3 静默截断多 Ad Group 数据。适用于查询、创建、调价、改预算、改状态及管理 SP/SB/SD 广告。本技能依赖 linkfox-amazon-ads-auth；不覆盖 Sponsored Television / DSP。

Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 111 other files, including scripts and reference files (for example `references/api.md`, `references/api/sb-coexistence.md` and `references/api/sb-v3.md`).

It sits in Marketing & SEO, covering Paid advertising. The licence is MIT.

When your agent uses it

Tasks that involve Paid advertising

Example prompts

“/linkfox-amazon-ads-manager”

Requirements

Python 3
A credential in LINKFOX_AGENT_API_KEY
A credential in LINKFOXAGENT_API_KEY

Workflow steps

10 steps, taken from the step headings in SKILL.md.

列活跃 SP 广告活动
看某 SP campaign 下的广告组
按 ASIN 反查 SP 投放（客户端过滤）
列 SB V4 广告活动（默认）
列某 SB V4 campaign 下的 adGroups / ads
管理 SB V4 campaign 的关键词（共享 targeting 路径）
查询已确认的 V3 Legacy campaign
列活跃 SD 广告活动
按 ASIN 反查 SD 投放（client-side 过滤，带 campaign 收窄）
与 report 配合分析指标

What it can do on your machine

Read from SKILL.md and the folder at commit 38fef04. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 8 files in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
- python
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- skill.linkfox.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- LINKFOX_AGENT_API_KEY
- LINKFOXAGENT_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Linkfox Amazon Ads Manager loads about 3.7k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 92 tokens; SKILL.md has 1,033 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~92
When it runs · the whole SKILL.md, loaded when a task matches: ~3.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from linkfox-ai/linkfox-skills at commit 38fef04, republished under its MIT licence (© linkfox-ai). 1,033 words, ~3,687 tokens.

Download SKILL.mdSave it as .claude/skills/linkfox-amazon-ads-manager/SKILL.md (or your agent's skills folder). This skill also uses 107 other files; get the full folder from GitHub.

name: linkfox-amazon-ads-manager
description: 亚马逊广告（Amazon Ads）管理技能，覆盖 SP/SB/SD 的查询与创建/修改。Sponsored Brands 同时支持 V3 Legacy 与 V4：新活动、多 Ad Group、Ad/Creative Version 默认走 V4，历史 Legacy 可显式走 V3，Keyword/Target 按 Campaign 结构通过版本化脚本调用 Amazon 共享 targeting 资源；禁止 V4 失败后自动回落 V3，禁止用 V3 静默截断多 Ad Group 数据。适用于查询、创建、调价、改预算、改状态及管理 SP/SB/SD 广告。本技能依赖 linkfox-amazon-ads-auth；不覆盖 Sponsored Television / DSP。

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 Legacy campaigns/keywords/targets；V4 campaigns/adGroups/ads/creative versions；keywords/targets 走 V4 脚本入口但底层是共享 targeting 路径	`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 与 SB V4 主资源 list 使用 nextToken，SB Target/BudgetRule 使用 nextToken（BudgetRule 查询必须带 pageSize），SB Keyword GET、SB V3 GET 与 SD 使用 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 / budgetRule），payload 透传 Amazon 原生格式；SB Creative 仅支持按 adId 查询 Creative Version 与创建新版本，没有通用 update 脚本
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

可用脚本

SP（28 个）

脚本	业务实体	操作
`sp/list_campaigns.py`	广告活动	查询
`sp/create_campaigns.py`	广告活动	创建
`sp/update_campaigns.py`	广告活动	修改（预算/策略/状态/名称等）
`sp/list_ad_groups.py`	广告组	查询
`sp/create_ad_groups.py`	广告组	创建
`sp/update_ad_groups.py`	广告组	修改（默认出价/状态/名称等）
`sp/list_keywords.py`	关键词	查询
`sp/create_keywords.py`	关键词	创建
`sp/update_keywords.py`	关键词	修改（出价/状态等）
`sp/list_negative_keywords.py`	否定关键词	查询
`sp/create_negative_keywords.py`	否定关键词	创建
`sp/update_negative_keywords.py`	否定关键词	修改（状态等）
`sp/list_product_ads.py`	商品广告	查询
`sp/create_product_ads.py`	商品广告	创建
`sp/update_product_ads.py`	商品广告	修改（状态等）
`sp/list_targets.py`	商品定向	查询
`sp/create_targets.py`	商品定向	创建
`sp/update_targets.py`	商品定向	修改（出价/状态等）
`sp/create_campaign_negative_keywords.py`	活动级否定关键词	创建
`sp/update_campaign_negative_keywords.py`	活动级否定关键词	修改（状态等）
`sp/create_campaign_negative_targets.py`	活动级否定定向	创建
`sp/update_campaign_negative_targets.py`	活动级否定定向	修改（状态等）
`sp/create_negative_targets.py`	广告组级否定定向	创建
`sp/update_negative_targets.py`	广告组级否定定向	修改（状态等）
`sp/list_budget_rules.py`	预算规则	查询
`sp/create_budget_rules.py`	预算规则	创建
`sp/update_budget_rules.py`	预算规则	修改
`sp/create_budget_rules_association.py`	预算规则关联	关联规则到活动

SB V3 Legacy（10 个）

脚本组	业务实体	操作
`sb/v3/list/create/update_campaigns.py`	Legacy 广告活动（Creative 内嵌）	查询/创建/修改
`sb/v3/list_ad_groups.py`	Legacy 广告组	查询
`sb/v3/list/create/update_keywords.py`	关键词	查询/创建/修改
`sb/v3/list/create/update_targets.py`	商品定向	查询/创建/修改

V3 仅兼容 Legacy。若参数包含 campaignStructure:"MULTI_AD_GROUP" 或 isMultiAdGroupsEnabled:true，脚本返回 SB_V4_CAMPAIGN_NOT_SUPPORTED。脚本没有本地 Campaign 数据库，因此调用前应先用 V4 Campaign list 确认结构。

SB V4（20 个）

脚本组	业务实体	操作
`sb/v4/list/create/update_campaigns.py`	广告活动	查询/创建/修改
`sb/v4/list/create/update_ad_groups.py`	广告组	查询/创建/修改
`sb/v4/list/create/update_ads.py`	广告	查询/创建/修改
`sb/v4/list/create/update_keywords.py`	关键词（Amazon 共享 targeting 路径 `sb/keywords`）	查询/创建/修改
`sb/v4/list/create/update_targets.py`	商品定向（Amazon 共享 targeting 路径 `sb/targets[/list]`）	查询/创建/修改
`sb/v4/list_creatives.py`、`create_creatives.py`	独立 Creative Version	按 `adId` 查询/创建新版本
`sb/v4/list/create/update_budget_rules.py`	预算规则	查询/创建/修改

原 scripts/sb/*.py 继续作为既有 V4 操作的兼容入口（薄封装转发到 scripts/sb/v4/）；新调用统一使用带版本目录。完整规则见 references/api/sb-coexistence.md。

SD（21 个）

脚本	业务实体	操作
`sd/list_campaigns.py`	广告活动	查询
`sd/create_campaigns.py`	广告活动	创建
`sd/update_campaigns.py`	广告活动	修改（预算/状态/名称等）
`sd/list_ad_groups.py`	广告组	查询
`sd/create_ad_groups.py`	广告组	创建
`sd/update_ad_groups.py`	广告组	修改（出价/状态等）
`sd/list_product_ads.py`	商品广告	查询
`sd/create_product_ads.py`	商品广告	创建
`sd/update_product_ads.py`	商品广告	修改（状态等）
`sd/list_targets.py`	定向子句	查询
`sd/create_targets.py`	定向子句	创建
`sd/update_targets.py`	定向子句	修改（出价/状态等）
`sd/list_negative_targets.py`	否定定向子句	查询
`sd/create_negative_targets.py`	否定定向子句	创建
`sd/update_negative_targets.py`	否定定向子句	修改（状态等）
`sd/list_creatives.py`	创意素材	查询
`sd/create_creatives.py`	创意素材	创建
`sd/update_creatives.py`	创意素材	修改（素材/状态等）
`sd/list_budget_rules.py`	预算规则	查询
`sd/create_budget_rules.py`	预算规则	创建
`sd/update_budget_rules.py`	预算规则	修改
详细过滤器、枚举值、返回字段见 references/api/sp.md / references/api/sb.md / references/api/sd.md。

调用方式

API 端点：POST /amazonAds/developerProxy（不同操作通过请求体区分；完整参数/响应/错误码见 references/api.md）
Python 脚本：python scripts/<脚本名>.py '<JSON 参数>' [--inline]；SB 新调用必须显式使用 scripts/sb/v3/ 或 scripts/sb/v4/
成本约束：本工具会消耗算力；失败/空结果不得自动换关键词、翻页或连续试探；需要继续检索时先向用户说明会产生额外消耗。

输出策略（脚本默认行为）：

始终将完整响应写入 <cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-amazon-ads-manager-<timestamp>.json（<cwd> 为脚本执行时的工作目录，在 Claude Code 里即当前项目目录；<session> 取自环境变量 SESSION_ID，按用户任务自动聚合；禁止写入 /tmp，当前目录不可写则报错）
响应体 ≤ 8 KB：落盘后把完整 JSON 打印到 stdout
响应体 > 8 KB：落盘后 stdout 只输出摘要（顶层字段、常见计数如 total/costToken、最大列表字段的长度 + 前 3 条样本）
加 --inline 强制全量打印到 stdout（同样落盘）

读数据建议：先看摘要判断是否足够；需要具体字段时优先用 jq或ConvertFrom-Json 从保存的 json 文件按需抽取，避免整份 JSON 进入上下文。

解决认证和算力问题

发生以下异常情况时，采用 references/onboarding.md 引导解决问题：

异常情况

未配置API Key：环境变量未配置 LINKFOX_AGENT_API_KEY，也未配置 LINKFOXAGENT_API_KEY。
响应401或402状态码
响应提示算力或余额不足：消息含"算力余额不足/计费不足/余额不足/quota exceeded/insufficient balance/套餐到期/需充值/请充值"，或类似含义的内容。

Financial Safety Guidance

创建和更新操作可能直接影响广告花费，立即生效且无法撤回。

决策规则：

用户状态	Agent 行为
已授权（说过"自动调价"/"按你判断来"/"不用问我"/"确认"等）	直接执行 → 输出操作回执
未授权（首次交互、未明确表态）	先输出确认摘要 → 等用户确认后执行

确认摘要模板（未授权时，执行前输出）：

📋 即将执行：
- 操作：[创建/修改] [N 个] [实体类型]
- 变更：[关键字段变化，如 bid $1.0→$1.5 / budget $50→$100]
- 影响：[花费变化预估，引用日预算作为上限]
确认执行？后续如需自动处理，告诉我即可。

操作回执模板（每次写操作执行后必须输出）：

✅ 已执行：[简短描述]
- 范围：[实体数量、名称或 ID]
- 变化：[具体变更内容]
- 结果：[成功 N 个 / 失败 M 个]

共用参数（SP + SB + SD 均适用）

字段	类型	说明
`profileId`	number	必填，从 ads-auth 获取
`region`	string	必填，`NA` / `EU` / `FE`
`fetchAll`	bool	默认 `true`；SP 与 SB V4 主资源 list 使用 `nextToken`，SB Target/BudgetRule 使用 `nextToken`（BudgetRule 查询必须带 `pageSize`），SB Keyword GET、SB V3 GET 与 SD 使用 `startIndex + count`
`maxResults`	int	1-100，默认 100；对应 Sponsored Display 端 `count`
`includeExtendedDataFields`	bool	返回扩展字段（部分实体）；SD 通过路径切换为 `/sd/<entity>/extended` 实现
`locale`	string	本地化（SP keywords 支持）

Show full SKILL.md (416 more words)Show less

过滤器结构速查（最易错）

结构	示例	适用字段
Object	`{"include":[...]}` / `{"exclude":[...]}`	全部 id/状态类：campaignIdFilter、adGroupIdFilter、keywordIdFilter、stateFilter、portfolioIdFilter、expressionTypeFilter、adIdFilter
Array	`["EXACT","BROAD"]`	matchTypeFilter（SP keywords/negativeKeywords）
Scalar	`"AUTO"`	campaignTargetingTypeFilter（SP adGroups）
Text	`{"queryTermMatchType":"BROAD_MATCH","include":["..."]}`	nameFilter、keywordTextFilter
Client	任意形式，本 skill 本地过滤	asinFilter、skuFilter（SP productAds）

易错点：

SP matchTypeFilter 是裸数组 ["EXACT"]（传错本 skill 自动规范化）
expressionTypeFilter 反而是 Object（与 matchType 不同）
asinFilter / skuFilter 客户端过滤，建议同时传 campaignIdFilter / adGroupIdFilter 收窄

响应格式

json

{
  "success": true,
  "apiVersion": "V3 | V4",
  "amazonResourceVersion": "V4 | V3_SHARED_TARGETING | SHARED_TARGETING | SHARED",
  "<entityKey>": [ /* 实体数组，字段原样 */ ],
  "total": 157,
  "pagesFetched": 2,
  "truncated": false
}

SB 的 apiVersion 表示调用入口/结构意图，amazonResourceVersion 表示实际 Amazon 资源版本；两者不同不代表发生自动回落。SP productAds 客户端过滤时额外带：serverTotalBeforeClientFilter + clientSideFilters。

使用示例

1. 列活跃 SP 广告活动

bash

python scripts/sp/list_campaigns.py '{"profileId":1234567890,"region":"NA",
  "stateFilter":{"include":["ENABLED"]}}'

2. 看某 SP campaign 下的广告组

bash

python scripts/sp/list_ad_groups.py '{"profileId":1234567890,"region":"NA",
  "campaignIdFilter":{"include":["998877665544"]}}'

3. 按 ASIN 反查 SP 投放（客户端过滤）

bash

python scripts/sp/list_product_ads.py '{"profileId":1234567890,"region":"NA",
  "asinFilter":{"include":["B01ABCDEFG"]},
  "campaignIdFilter":{"include":["998877665544"]}}'

4. 列 SB V4 广告活动（默认）

bash

python scripts/sb/v4/list_campaigns.py '{"profileId":1234567890,"region":"NA",
  "stateFilter":{"include":["ENABLED"]}}'

5. 列某 SB V4 campaign 下的 adGroups / ads

bash

python scripts/sb/v4/list_ad_groups.py '{"profileId":1234567890,"region":"NA",
  "campaignIdFilter":{"include":["1122334455"]}}'

python scripts/sb/v4/list_ads.py '{"profileId":1234567890,"region":"NA",
  "adGroupIdFilter":{"include":["5566778899"]}}'

6. 管理 SB V4 campaign 的关键词（共享 targeting 路径）

bash

python scripts/sb/v4/list_keywords.py '{"profileId":1234567890,"region":"NA",
  "campaignIdFilter":["1122334455"],"adGroupIdFilter":["5566778899"]}'

7. 查询已确认的 V3 Legacy campaign

bash

python scripts/sb/v3/list_campaigns.py '{"profileId":1234567890,"region":"NA",
  "campaignStructure":"LEGACY","stateFilter":["enabled","paused"]}'

8. 列活跃 SD 广告活动

bash

python scripts/sd/list_campaigns.py '{"profileId":1234567890,"region":"NA",
  "stateFilter":{"include":["ENABLED"]}}'

9. 按 ASIN 反查 SD 投放（client-side 过滤，带 campaign 收窄）

bash

python scripts/sd/list_product_ads.py '{"profileId":1234567890,"region":"NA",
  "asinFilter":{"include":["B01ABCDEFG"]},
  "campaignIdFilter":{"include":["998877665544"]}}'

10. 与 report 配合分析指标

本 skill 返回实体元数据（id、名称、状态、匹配类型等）；指标（曝光、点击、花费、转化）交给 linkfox-amazon-ads-report（reportTypeId: "spTargeting" / "sbCampaigns" / "sdCampaigns" 等），按 id join。

调用原则

返回字段原样保留；不改名、不翻译、不补算派生指标
非 2xx 不自动重试；保留 httpStatus + body 告知用户
truncated=true 时明确提示数据未取完

常见错误

状态	含义	建议
`HTTP 401`	accessToken 过期	调 ads-auth 的 `refresh_token.py` 后重试
`HTTP 403`	profileId 无权限	核对 profileId 归属
`HTTP 400`	入参结构错	先核对"过滤器结构速查"表
`HTTP 429`	限流	等 2-5s 重试
exit 42	依赖 skill 未安装	先装 `linkfox-amazon-ads-auth`

Not Applicable

删除 / 归档 → 本 skill 不支持 DELETE（可通过 update state 为 ARCHIVED 实现归档，但归档不可逆）
SB 不支持把 V4 Multi-Ad-Group Campaign 降级成 V3；V3 独立 Creative CRUD 不存在，Legacy Creative 通过 Campaign payload 管理
SB negativeKeywords / negativeTargets / themes / recommendations 与 Legacy→V4 Migration 暂不在本次 A+B+C 范围
SD 的按 id 单查 / brandSafety / recommendations / forecasts / optimizationRules / locations 等"非基础实体"接口 → 不在本 skill
DSP / ST 实体 → 不在本 skill
指标报表 → linkfox-amazon-ads-report
授权 / token / profile → linkfox-amazon-ads-auth

Amazon Ads API 接口保护与重试指引

同一广告账号/profile 连续收到 Amazon Ads API 的 400、403、404 或 429 时，网关会返回 450、453、454 或 459 并短暂冷却。这些自定义状态码不是 Amazon 原生状态，也不表示封号；目的是避免持续异常或高频调用扩大广告账号风险。

状态与 message	范围	触发与冷却	处理
`450`：`400，请求异常，请优化您的参数`	广告账号/profile+接口	60 秒内超过 3 次：5 分钟；10 分钟内超过 4 次：20 分钟	停止原参数重试，检查 profileId、region、实体/报告 ID、日期和请求体
`453`：`403，店铺未授权，请先授权`	广告账号/profile 全部接口	60 秒内超过 2 次：5 分钟；10 分钟内超过 4 次：30 分钟	停止该广告账号调用，检查 Ads 授权、应用权限、profile 归属和区域
`454`：`404，资源不存在，请优化您的参数`	广告账号/profile+接口	60 秒内超过 3 次：5 分钟；10 分钟内超过 4 次：30 分钟	确认资源 ID、所属 profile/区域、资源状态和接口路径
`459`：`429限流中，请降低频率`	广告账号/profile+接口	首次：15 秒；2 分钟内超过 2 次：30 秒；3 分钟内超过 4 次：2 分钟	降低并发、分页和轮询频率并逐级退避

立即停止自动或并发重试，不得通过换脚本或重复创建任务绕过保护；优先遵循 retryAfter、blockedUntil，没有时按表中时长说明。
450/453/454 必须先修正参数、授权或资源标识，冷却后最多谨慎重试一次；再次触发则停止调用。453 期间停止该广告账号/profile 全部 Ads API。
保留已有 reportId 等任务 ID；写操作结果不确定时先查询状态，不直接重放。
向用户先说明广告账号保护，再给原因、处理和等待时间。可回复：“为保护您的亚马逊广告账号安全，检测到 Amazon Ads API 连续返回{原因}，当前已进入短暂保护。请先{处理动作}，预计{等待时间}后再试；这不代表封号，也不是套餐或积分限制。”不要只说“LinkFox 限流”或“服务器繁忙”。

算力消耗规则

不消耗算力。

Feedback:

Auto-detect and report feedback via the Feedback API when any of the following apply:

The functionality or purpose described in this skill does not match actual behavior
The skill's results do not match the user's intent
The user expresses dissatisfaction or praise about this skill
Anything you believe could be improved

Call the feedback API as specified in references/api.md. Do not interrupt the user's flow.

For more high-quality, professional cross-border e-commerce skills, visit LinkFox Skills.

Files

SKILL.md and 107 other files (scripts, references) in skills/linkfox-amazon-ads-manager of linkfox-ai/linkfox-skills.

SKILL.md
references/api.md
references/api/sb-coexistence.md
references/api/sb-v3.md
references/api/sb-v4.md
references/api/sb.md
references/api/sd.md
references/api/sp.md
references/onboarding.md
scripts/_common.py
scripts/check_auth_dependency.py
scripts/onboarding.py
scripts/sb/_sb_common.py
scripts/sb/create_ad_groups.py
scripts/sb/create_ads.py
scripts/sb/create_budget_rules.py
scripts/sb/create_campaigns.py
… and 91 more

Open the folder on GitHubat commit 38fef04

Compare with similar skills

Linkfox Amazon Ads Manager next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Linkfox Amazon Ads Manager compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Linkfox Amazon Ads Manager this skilllinkfox-ai/linkfox-skills	107	—	~3.7k	Automated safety check: Pass	MIT	26 days ago
Ad CreativeLeoYeAI/openclaw-marketing-skills	1k	8 repos	~3.4k	Automated safety check: Pass	Custom licence	4 mo ago
Blog GoogleAgriciDaniel/claude-blog	2.3k	1 repos	~3.3k	Automated safety check: Notes	MIT	yesterday
Ad Account Auditoraaron-he-zhu/aaron-marketing-skills	2.9k	2 repos	~2.2k	Automated safety check: Pass	Apache-2.0	today
Ad Creative Builderaaron-he-zhu/aaron-marketing-skills	2.9k	2 repos	~2.2k	Automated safety check: Pass	Apache-2.0	today
Ad Test Designeraaron-he-zhu/aaron-marketing-skills	2.9k	2 repos	~2.8k	Automated safety check: Pass	Apache-2.0	today

Similar skills

Ad Creative
LeoYeAI/openclaw-marketing-skills
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform.
1k GitHub starsUsed in 8 repos~3.4k tokens
Marketing & SEOAuto-check passed
Blog Google
AgriciDaniel/claude-blog
Google API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity…
2.3k GitHub starsUsed in 1 repo~3.3k tokens
Marketing & SEOAuto-check: notes
Ad Account Auditor
aaron-he-zhu/aaron-marketing-skills
A skill your agent uses when auditing a paid ad account for incremental contribution, wasted spend, or measurement integrity before scaling; runs a typed 20-item ROAS profile with verified vetoes…
2.9k GitHub starsUsed in 2 repos~2.2k tokens
Marketing & SEOAuto-check passed
Ad Creative Builder
aaron-he-zhu/aaron-marketing-skills
A skill your agent uses when the user asks to "write ad copy", "generate RSA headlines", or "build ad creative at volume"; produces ad units — RSA headlines/descriptions, hooks, and an angle matrix…
2.9k GitHub starsUsed in 2 repos~2.2k tokens
Marketing & SEOAuto-check passed
Ad Test Designer
aaron-he-zhu/aaron-marketing-skills
A skill your agent uses when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this result statistically and practically material?"…
2.9k GitHub starsUsed in 2 repos~2.8k tokens
Marketing & SEOAuto-check passed
Paid Ads Audit
AgriciDaniel/claude-ads
Runs a source-grounded paid advertising audit across up to 12 ad platforms, with parallel platform workers, deterministic scoring and a versioned JSON bundle.
9.9k GitHub stars~1.5k tokensUpdated 3 days ago
Marketing & SEOAuto-check passed

Questions about Linkfox Amazon Ads Manager

What does Linkfox Amazon Ads Manager do?

When should I use Linkfox Amazon Ads Manager?

Linkfox Amazon Ads Manager fits situations like: tasks that involve Paid advertising.

How do I install Linkfox Amazon Ads Manager in Claude Code?

Run `npx skills add linkfox-ai/linkfox-skills --skill linkfox-amazon-ads-manager -a claude-code`. Or copy the skill folder (skills/linkfox-amazon-ads-manager in linkfox-ai/linkfox-skills) into .claude/skills/linkfox-amazon-ads-manager in your project. Claude Code loads it when a task matches its description.

How do I install Linkfox Amazon Ads Manager in Codex?

Run `npx skills add linkfox-ai/linkfox-skills --skill linkfox-amazon-ads-manager -a codex`. Or copy the skill folder (skills/linkfox-amazon-ads-manager in linkfox-ai/linkfox-skills) into .agents/skills/linkfox-amazon-ads-manager in your project. Codex loads it when a task matches its description.

Can I use Linkfox Amazon Ads Manager in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add linkfox-ai/linkfox-skills --skill linkfox-amazon-ads-manager -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/linkfox-amazon-ads-manager, .gemini/skills/linkfox-amazon-ads-manager, .github/skills/linkfox-amazon-ads-manager and .opencode/skills/linkfox-amazon-ads-manager in your project.

What does Linkfox Amazon Ads Manager need to run?

Going by SKILL.md and its folder, Linkfox Amazon Ads Manager needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named LINKFOX_AGENT_API_KEY and LINKFOXAGENT_API_KEY. Our summary lists: Python 3; A credential in LINKFOX_AGENT_API_KEY; A credential in LINKFOXAGENT_API_KEY.

Does Linkfox Amazon Ads Manager access the network?

SKILL.md names 1 domain. As links in the text: skill.linkfox.com. This is read from the text; nothing was executed.

Is Linkfox Amazon Ads Manager safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Linkfox Amazon Ads Manager use?

Linkfox Amazon Ads Manager is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Linkfox Amazon Ads Manager use?

About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.8k tokens, read only when the agent opens those files.

What are the alternatives to Linkfox Amazon Ads Manager?

Skills that share tags, products or a category with Linkfox Amazon Ads Manager: Ad Creative (LeoYeAI/openclaw-marketing-skills, 1k stars), Blog Google (AgriciDaniel/claude-blog, 2.3k stars), Ad Account Auditor (aaron-he-zhu/aaron-marketing-skills, 2.9k stars) and Ad Creative Builder (aaron-he-zhu/aaron-marketing-skills, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Linkfox Amazon Ads Manager?

linkfox-ai (a GitHub user) maintains it in linkfox-ai/linkfox-skills, which has 107 GitHub stars. The repository holds 177 skills in this directory. The repository was last updated on September 14, 2026.

Source: linkfox-ai/linkfox-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Linkfox Amazon Ads Manager

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Amazon Ads 广告管理

⚠️ 多账号场景：调用前必须解析好 profileId

Core Concepts

可用脚本

SP（28 个）

SB V3 Legacy（10 个）

SB V4（20 个）

SD（21 个）

调用方式

解决认证和算力问题

异常情况

Financial Safety Guidance

共用参数（SP + SB + SD 均适用）

过滤器结构速查（最易错）

响应格式

使用示例

1. 列活跃 SP 广告活动

2. 看某 SP campaign 下的广告组

3. 按 ASIN 反查 SP 投放（客户端过滤）

4. 列 SB V4 广告活动（默认）

5. 列某 SB V4 campaign 下的 adGroups / ads

6. 管理 SB V4 campaign 的关键词（共享 targeting 路径）

7. 查询已确认的 V3 Legacy campaign

8. 列活跃 SD 广告活动

9. 按 ASIN 反查 SD 投放（client-side 过滤，带 campaign 收窄）

10. 与 report 配合分析指标

调用原则

常见错误

Not Applicable

Amazon Ads API 接口保护与重试指引

算力消耗规则

Files

Compare with similar skills

Similar skills

More from linkfox-ai/linkfox-skills

Related

Questions about Linkfox Amazon Ads Manager