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-baize-amazon-inventory-profit-balancegit 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-baize-amazon-inventory-profit-balance)<a href="https://agentmods.dev/skills/xjli360/sealeap-amazon-ad-skills/sealeap-baize-amazon-inventory-profit-balance"><img src="https://agentmods.dev/badge/skills/xjli360/sealeap-amazon-ad-skills/sealeap-baize-amazon-inventory-profit-balance/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-baize-amazon-inventory-profit-balance"><img src="https://agentmods.dev/badge/skills/xjli360/sealeap-amazon-ad-skills/sealeap-baize-amazon-inventory-profit-balance.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 | $0.00069 | $0.01088 |
| Opus 5 | $0.00034 | $0.00544 |
| Sonnet 5 | $0.00014 | $0.00218 |
| Haiku 4.5 | $0.00007 | $0.00109 |
Grade A, and why
sealeap-baize-amazon-inventory-profit-balance 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 4d 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.
What it actually says
Amazon 库存与利润平衡
目标
Set Amazon per-SKU inventory and advertising boundaries from realistic sales capacity, cash turnover, conversion, break-even acquisition cost, and portfolio risk.
不可妥协的边界
- 当前 Amazon 官方政策、账户资格、站点字段和一方数据优先于本 Skill 的经验框架。
- 第三方数据一律标为估算或前台观测，不得写成 Amazon 一方事实。
- 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。
- 一次实验只改变一个主要变量，并记录基线、样本、成功、停止和回退条件。
- 不得复制来源材料或竞品表达；输出必须按当前任务重新组织并可由现有证据支撑。
- 不存在可验证的固定店铺订单上限时，不用该假设限制组合。
- 固定广告占比是经验值，应按产品毛利、退货和目标利润重算。
先判断任务模式
- 诊断：读取现状、证据和缺口，不生成线上写入动作。
- 方案草案：输出可审核的结构、参数范围、实验和回退值。
- 执行准备：只生成待批准变更表或 API/控制台操作草案。
- 已批准执行：仅对用户在当前会话明确批准的对象和字段执行，并立即回读核验。
用户未指定时采用“诊断”。
开始前要拿到
- marketplace、ASIN/SKU、库存阶段、补货与到仓时间
- 断货或备货前后的销量、流量、广告、自然位置和转化基线
- COGS、头程、仓储、平台费、退货和清仓成本
- 可比产品的成熟度、销量区间和需求趋势
缺失项必须标为 NEEDS_EVIDENCE；不得猜数字、补属性或把不同站点、ASIN、变体、币种和时间窗混在一起。
工作流
先读取 references/playbook.md，确认该方法适用于当前对象。按以下顺序执行：
- 用低成熟度可比产品估算销量区间，而不是直接采用头部销量。
- 计算不同备货量下的现金占用、仓储、广告和清仓损失。
- 用单位贡献利润反推最大广告获客成本。
- 在单 SKU 和组合层分别设置补货、减投和退出触发器。
- 滚动更新实际销量与转化，逐批增加而非一次压货。
最后做数据充分性检查，并把结论分成 FACT / ESTIMATE / HYPOTHESIS / UNKNOWN。若关键证据不足，状态写 HOLD。
第三方 MCP 数据
仅在自有数据不足且当前任务确实需要外部证据时，读取 references/mcp-data-plan.md，再使用 scripts/mcp_research.py。本 Skill 的外部取数目的：获取历史趋势、可比销量、评论成熟度和关键词需求代理数据。
- 先
doctor，再search-tools和describe；工具名及参数以实时tools/list与inputSchema为准。 - Token 只从环境变量读取。不得写入命令参数、URL、Skill、报告、日志或 Git。
tools/call或 Actor 可能计费；先展示 Provider、工具、无密钥业务参数、预计成本与输出位置，核对已有授权覆盖后才加--allow-cost；该标志不是费用上限。
必须交付的结果
- 销量区间
- 库存情景表
- 获客成本上限
- 组合风险与触发器
- 数据范围、来源、采集时间、样本与限制。
- 关键假设、待补证据、风险和不可确定项。
- 若有动作：对象、旧值、新值、预期、停止条件、回退值与审批状态。
方案状态使用 READY FOR REVIEW / DRAFT / HOLD / STOP；如已执行，另行记录实际结果及回读证据。未得到明确批准时，不得声称已修改线上对象。
What ships with it
4 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.
- 4d ago First seen · 72 lines · 69 tokens per session scan A 726cfc31a75b
sealeap-baize-amazon-inventory-profit-balance is a skill published in the GitHub repository xjli360/sealeap-amazon-ad-skills (86 stars, last pushed 6d ago), licensed MIT. It adds 69 tokens to every session and 1,088 once invoked, about $0.0003 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 2026-09-07.
Other skills, from other repositories
ecom-pricing
Set competitive prices and model profitability. Use for Buy Box pricing analysis, profit margin calculation, breakeven analysis, or multi-marketplace pricing strategy.
ai-api-alternative-ai-hive
A billing-comparison guide for moving between AI API providers, which are services that let software send requests to AI models.
ai-api-live-price-snapshot-ai-hive
A guide for recording current AI model prices and setting spending limits before submitting generation jobs.
ai-hive-boss-coupon-cost
A coupon-cost analysis workflow that examines discount rules, redemption, stacking, profit margin, and purchases that might have happened without the coupon.
asc-ppp-pricing
Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands. Use when adjusting prices by country or implementing localized PPP strategies.
ai-slop
Operational rubric that turns "don't make AI slop" into observable properties, severity levels, evidence requirements, and repair actions for interface design. Use as the reference rubric when building or reviewing marketing sites, product interfaces, dashboards, portfolios, or e-commerce pages, especially alongside…