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 xjli360/sealeap-amazon-ad-skills --skill sealeap-pixiu-amazon-policy-monitoringgit clone --depth 1 https://github.com/xjli360/sealeap-amazon-ad-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/xjli360/sealeap-amazon-ad-skills/sealeap-pixiu-amazon-policy-monitoring)<a href="https://agentmods.dev/skills/xjli360/sealeap-amazon-ad-skills/sealeap-pixiu-amazon-policy-monitoring"><img src="https://agentmods.dev/badge/skills/xjli360/sealeap-amazon-ad-skills/sealeap-pixiu-amazon-policy-monitoring/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/xjli360/sealeap-amazon-ad-skills/sealeap-pixiu-amazon-policy-monitoring"><img src="https://agentmods.dev/badge/skills/xjli360/sealeap-amazon-ad-skills/sealeap-pixiu-amazon-policy-monitoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00074 | $0.01077 |
| Opus 5 | $0.00037 | $0.00539 |
| Sonnet 5 | $0.00015 | $0.00215 |
| Haiku 4.5 | $0.00007 | $0.00108 |
Grade A, and why
sealeap-pixiu-amazon-policy-monitoring 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 5d 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.
This is a copy
84% identical to sealeap-pixiu-amazon-account-compliance — 58 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Amazon 平台政策与异常监控：政策变化、利润模型、季节性
目标
围绕政策变化、利润模型、季节性，核对官方规则、时间和适用范围，形成影响清单、应对动作与复核节点。
使用范围
- 优先处理平台政策与异常监控任务；从专项证据卡选择与当前对象和问题直接相关的主题。
- 集合名称用于维护文件归属，不限制用户要求的交叉验证。其他来源与业务域的证据须分别标注，再按同口径比较。
- 本 Skill 可独立使用，不依赖仓库中的私有语义稿。保留去标识化边界，不恢复原素材身份或逐条映射。
适用任务
- 变更摘要
- 影响矩阵
- 应对检查表
开始前要拿到
- 官方公告或后台通知。
- 站点、账户、类目和生效日期。
- 受影响 SKU/ASIN、费用、库存或流程。
- 执行前后证据。
缺少字段时明确标为 UNKNOWN 或 NEEDS_EVIDENCE，不要补造数据。
不可妥协的边界
- 本 Skill 来自去标识化语义转译，不保留或推断素材来源身份，也不把素材观点冒充 Amazon 当前政策。
- 产品事实、账户事实和 Amazon 一方报告优先；第三方数据必须标明 Provider、站点、日期、样本和估算口径。
- 不捏造销量、搜索量、成本、合规状态、产品属性、评论、平台通知或执行结果。
- 默认提供诊断或草案。写入前展示对象、旧值、新值、影响、停止线与回退，核对用户已有授权是否覆盖对象、动作与预算；范围已明确授权时继续执行并回读核验，只有未覆盖或扩大的范围才请求批准。
- 平台规则、费率、界面和资格会变化；执行前复核当前官方文档与后台状态。
工作流
- 保存官方原文、发布时间、生效日期和适用范围。
- 将明确事实与卖家解读、媒体报道和待验证假设分开。
- 建立受影响对象清单并量化费用、库存、流量和合规风险。
- 设计最小应对、回滚和监控指标，避免提前过度调整。
- 生效后复核后台实际表现并更新结论。
专项路由
- 政策变化：保存官方原文、适用站点、生效日期、受影响对象和待验证解释。
- 利润模型：统一收入、平台费、广告、退货、物流、税费和资金成本口径。
- 季节性：将需求窗口、备货、排名和广告节奏对齐，并区分事件效应。
- 客服与工单：建立问题、证据、请求动作、时限和升级路径，避免无差别重复开案。
- 转化率：把转化问题拆成流量意图、详情页说服力、价格评价、库存配送和购买障碍。
- 运营工具：先核对工具的数据来源、权限、费用和导出字段，再决定是否接入。
完整的 6 张主题证据卡见 references/topic-cards.md；2 种原有组合见 references/scenario-patterns.md。
第三方数据（可选）
只有在用户数据或 Amazon 一方报告不足时，才按 references/mcp-data-plan.md 发现实时 schema、执行 dry-run，并在可能计费的调用前核对具体请求与预算授权；已有授权覆盖时不重复索取。凭证通过环境变量注入，结果保存到 Skill 包之外的任务私有目录。
必须交付的结果
- 变更摘要
- 影响矩阵
- 应对检查表
- 监控阈值
- 复核记录
结尾列出站点、时间窗、数据口径、证据、假设、缺口、风险、下一步和所有待批准动作。证据不足时写 HOLD，不得包装成可直接执行。
执行细节、证据字段和质量检查见 references/playbook.md。
What ships with it
6 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.
- 5d ago First seen · 75 lines · 74 tokens per session scan A 899e4739c85e
sealeap-pixiu-amazon-policy-monitoring is a skill published in the GitHub repository xjli360/sealeap-amazon-ad-skills (86 stars, last pushed 6d ago), licensed MIT. It adds 74 tokens to every session and 1,077 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 84% identical to sealeap-pixiu-amazon-account-compliance, differing in 58 lines, and is treated as a copy.
Other skills, from other repositories
ecom-compliance
Check product compliance, HS codes, IP risks, and platform requirements. Use for category approval, FDA/FCC/CE documentation, IP infringement screening, or dangerous goods classification.
ai-gaochao-cn-migration-ai-hive
A migration-review workflow for moving AI API workloads between providers. It examines data retention, training use, data location, deletion, contracts and operational tests before any traffic is moved.
ai-content-disclosure-check-ai-hive
A review workflow for deciding what AI-generated images, videos or text should disclose before publication. It considers how content was made, who appears in it, where it will be published and which region’s rules apply.
einbeziehung-online-clickwrap-browsewrap
Für Einbeziehung Online Clickwrap Browsewrap: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
plattform-online-gate-rollout-rangfolge
Für Plattform und Online Checkout: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: plattform-online-gate-rollout-rangfolge.
zach-search-term-analyzer
An analyzer for Amazon Brand Analytics Top Search Terms reports, which show popular searches across Amazon and how clicks and conversions are distributed among products.