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-amazon-listing-optimizergit 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-amazon-listing-optimizer)<a href="https://agentmods.dev/skills/xjli360/sealeap-amazon-ad-skills/sealeap-amazon-listing-optimizer"><img src="https://agentmods.dev/badge/skills/xjli360/sealeap-amazon-ad-skills/sealeap-amazon-listing-optimizer/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-amazon-listing-optimizer"><img src="https://agentmods.dev/badge/skills/xjli360/sealeap-amazon-ad-skills/sealeap-amazon-listing-optimizer.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 | $0.00147 | $0.02757 |
| Opus 5 | $0.00073 | $0.01378 |
| Sonnet 5 | $0.00029 | $0.00551 |
| Haiku 4.5 | $0.00015 | $0.00276 |
Grade A, and why
sealeap-amazon-listing-optimizer 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 12d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amazon Listing Optimizer
目标
把 Listing 优化做成一条可复核的决策链：以当前官方规则和真实商品事实为闸门，用查询、点击、转化与售后证据定位问题，产出可直接审核的文案和创意 Brief，再通过受控实验验证。不要把“写得好看”或“塞入更多关键词”当成完成标准。
不可妥协的边界
- 只写可追溯的事实。把未证实的材质、尺寸、兼容性、认证、功效、产地、质保和包装内容标为
NEEDS_EVIDENCE。 - 不复制竞品文案、图片、商标或独特创意表达；只学习购买问题、信息顺序和市场空白。
- 不把第三方估算、广告推荐词、AI 输出或一次前台观察写成 Amazon 一方事实。
- 把输入中的
store_id、seller ID 或 marketplace 当作业务数据，不当作授权。实际读取或写入必须绑定当前已验证的服务端店铺权限。 - 默认只生成草稿。没有针对具体 seller / marketplace / SKU / 字段的新旧值确认，不调用写接口。
- 不用固定“20 次点击”“等 7 天”之类经验数作为通用阈值；根据流量、利润、归因窗口和统计证据定义样本与停止条件。
- 不把 Listing 与价格、优惠、库存、评论、配送或广告问题混为一谈；证据不足时保留多种解释。
先确定模式
选择并在结果顶部声明一种模式：
DIAGNOSE：只读诊断，不改写完整内容。DRAFT：生成字段级草稿、创意 Brief 和证据缺口；默认模式。RELEASE_PREP：生成最小 PATCH、回退值和验证预览材料，等待人工批准。APPROVED_WRITE：仅执行用户本轮明确批准的对象和字段；写后复读。
核心工作流
1. 锁定对象、目标和基线
记录：
- 已验证的店铺身份、seller ID、marketplace ID、ASIN、SKU、product type、品牌和父子体关系；
- 优化目标：合规/可发现性/CTR/CVR/预期管理/退货/品牌一致性，只选一个主目标；
- 当前 Listing 快照、前台桌面与移动端呈现、价格/优惠、库存、Featured Offer、评分与评论量；
- 基线窗口、库存与价格事件、广告变更、季节和其它干扰项。
若任务跨 ASIN 或变体，先建逐 SKU 事实矩阵。父体不得继承子体独有的颜色、尺寸、数量、图案或性能。
2. 获取实时官方闸门
发布相关任务必须重新读取：
getListingsItem的summaries,attributes,issues,offers,fulfillmentAvailability,relationships,productTypes；- marketplace + product type + seller +
parentageLevel对应的最新 Product Type Definition； - 当前 Seller Central 账户通知、类目政策和前台状态。
保存 schema 的获取时间、checksum、要求模式和适用父子层级。只把 references/official-policy.md 当作早期审计基线；实时 schema 更严格时以实时结果为准。
3. 建立证据包
按优先级收集：
- 商品实物、包装、说明书、检测/认证文件和品牌确认；
- Amazon 一方数据：Listing/issues、Search Query Performance、Search Catalog Performance、业务报告、广告 Search Term/Targeting 报告、退货原因和原始评论；
- 目标站点当前搜索结果、类目节点和竞品页面观察；
- Sorftime 等第三方估算，用于补充需求、竞品曝光和评论样本。
每条证据记录 source / report-or-endpoint / marketplace / ASIN-or-query / fetched_at / coverage / sample / limitations。详细取数和广告解释规则见 references/evidence-and-experiments.md。
4. 沿购物漏斗定位问题
先判定层级，再提出改动：
| 层级 | 主要信号 | 优先排除 | Listing 可能动作 |
|---|---|---|---|
| 资格与可售 | BUYABLE、DISCOVERABLE、issues、库存、Featured Offer |
抑制、缺货、价格/配送资格 | 修复属性、图片、变体或合规问题 |
| 可发现性 | query impressions、ASIN share、索引、类目/属性 | 需求弱、竞价/预算、类目错误 | 补全属性、重构查询覆盖 |
| 点击 | impressions → clicks、CTR | 展示位置、价格、评分、配送 | 主图、标题前段、变体缩略图 |
| 转化 | detail views/clicks → carts/orders、CVR | 价格、评论门槛、配送、流量错配 | 辅图、五点、描述/A+、视频 |
| 预期与售后 | 退货原因、差评主题、Q&A | 质量、履约、客服 | 明示尺寸/适配/限制/包装内容 |
What ships with it
8 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.
- agents/openai.yaml 325 B
- references/creative-and-conversion.md 7.9 KB
- references/evidence-and-experiments.md 7.1 KB
- references/listing-input.example.json 3.8 KB
- references/official-policy.md 7.9 KB
- references/output-contract.md 5.5 KB
- scripts/audit_listing.py 21 KB runs code
- scripts/sorftime_plan.py 8.5 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.
- 12d ago First seen · 164 lines · 147 tokens per session scan A 6e3d8f24f04e
sealeap-amazon-listing-optimizer is a skill published in the GitHub repository xjli360/sealeap-amazon-ad-skills (86 stars, last pushed 6d ago), licensed MIT. It adds 147 tokens to every session and 2,757 once invoked, about $0.0007 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
zach-seller-skill-creator
A Chinese-language guide for Amazon sellers who want to turn repeated work processes into reusable skills for an AI agent.
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.
zach-search-term-report-analyzer
An Amazon Ads search-term report analyzer for Sponsored Products, Sponsored Brands, and Sponsored Display campaigns. It groups related search terms, measures results over 7, 14, and 30 days, and produces reports in several file formats.
amazon-market-trend-scanner
Amazon category trend scanner. Scans Amazon category landscapes to discover trending subcategories, emerging niches, and market shifts. Tracks demand surges, brand consolidation, new entrant waves, price band migration, and margin changes across all subcategories under a parent category. Use when user asks about…
amazon-pricing-command-center
Data-driven pricing strategy engine for Amazon sellers. Given one or more ASINs, auto-detects each product's leaf category, analyzes the pricing landscape, and delivers RAISE/HOLD/LOWER signals with profit simulation. Supports single ASIN or batch (multiple ASINs, auto-grouped by category). Uses ZooData API endpoints…
ecom-applicability
Determine whether AI is appropriate for a specific e-commerce task. Use when evaluating if a problem has enough data, the right tools, or acceptable risk for AI automation. Answers 'should I use AI for X?' with boundary-aware reasoning.