sealeap-amazon-acos-diagnostics SKILL.md skillA
sealeap-amazon-acos-diagnostics from xjli360/sealeap-amazon-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add xjli360/sealeap-amazon-skills/sealeap-amazon-acos-diagnostics@git:20261016.1283764Pins git:20261016.1283764 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- xjli360/sealeap-amazon-skills
- Path
amazon-skills/amazon-official/sealeap-amazon-acos-diagnostics/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261016.1283764, committed Oct 16, 2026
- First version recorded
- Sep 6, 2026
- Size
- 9,133 bytes
- Repository stars
- 324
- License
- MIT
Diagnose Amazon Ads ACOS with reconciled CTR, CPC, CVR, AOV, ROAS, TACOS, placement, search-term, benchmark, attribution, and contribution-margin evidence, then produce a single-variable optimization experiment. Use for ACOS 高低判断, 广告亏损, CTR/CVR/CPC 异常, 盈亏平衡 ACOS, 广告报告诊断, Benchmark 基准, placement 浪费, 搜索词不精准, Listing 转化问题, 广告利润优化, or converting the authorized Amazon Ads metrics course into an account-specific plan. Default to read-only diagnosis and draft; never change live campaigns without…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Amazon Ads ACOS 核心指标诊断 ## 目标 把“ACOS 高不高”改写成一条可复核的问题链：先确认策略目标和经济性，再统一数据口径，重算 ACOS 及其驱动项，定位 CPC、CVR、客单价或流量结构断点，最后只提出一个可归因的实验。 先读 [references/source-and-guardrails.md](references/source-and-guardrails.md)。需要公式与指标口径时读 [references/metric-system.md](references/metric-system.md)，需要完整诊断树时读 [references/diagnostic-tree.md](references/diagnostic-tree.md)。课程案例只能结合 [references/case-study-and-caveats.md](references/case-study-and-caveats.md) 使用；需要 Benchmark 算法与误读防护时读 [references/benchmark-methodology.md](references/benchmark-methodology.md)。 ## 核心原则 - `ACOS = 广告花费 ÷ 广告归因销售额 × 100%`，也可在同一口径下拆为 `CPC ÷ (CVR × 广告订单客单价) × 100%`。 - ACOS 是结果指标，不是所有广告目标的唯一评价标准。测试、守位、品牌获客、推排名和成熟品利润的主目标不同。 - 盈亏判断使用“扣除商品成本、平台费用、履约、折扣、退货等广告外可变成本后的贡献毛利率”。缺少完整成本时不得把普通毛利率写成精确盈亏线。 - 广告归因销售额与总销售额不得混用；ACOS、TACOS、ROAS 必须分别命名。 - 不跨 marketplace、profile、币种、广告类型、归因窗口、日期或层级直接拼接。 - Benchmark 是同业参照，不是目标或因果解释。当前可用性、同业组、分位数与指标定义必须在控制台/API 重新确认。 - 默认只读。任何 bid、budget、placement、target、否定词、状态或结构变更均需逐对象人工批准。 ## 先声明模式 1. `DIAGNOSE`：重算和定位，不生成变更；默认； 2. `DRAFT`：生成单变量实验草案； 3. `RELEASE_PREP`：生成审批卡、旧值/新值、停止线和回退； 4. `APPROVED_WRITE`：只执行用户本轮明确批准的一个动作，写后复读。 ## 核心工作流 ### 1. 先问“这轮广告要完成什么” 只选一个主目标： | 目标 | 首要判断 | ACOS 的位置 | |---|---|---| …
Read the whole file at its exact version.
How to install
mdr add xjli360/sealeap-amazon-skills/sealeap-amazon-acos-diagnostics@sha256:a0a20d0124cb0816The line at the top of this page pins the label git:20261016.1283764, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ottnx7ctwhx43h5v)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 6, 2026 and Oct 16, 2026, about one every 40 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261016.1283764 latest | 2026-10-16 | 1283764 | 9,133 B | A | view · diff |
| git:20260906.d30e1bd | 2026-09-06 | d30e1bd | 8,904 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9133 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
xjli360/sealeap-amazon-skills · 324 stars · license MIT · pushed 2026-10-16 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ottnx7ctwhx43h5v GET https://markdownregistry.com/api/v1/resolve?ref=xjli360/sealeap-amazon-skills/sealeap-amazon-acos-diagnostics GET https://markdownregistry.com/api/v1/blob/a0a20d0124cb0816ab261f95b78b89d53fdc80af6c18558d1c498b72ed621c8e
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.