sealeap-amazon-apparel-lifecycle-ads

REVIEW · 61
Registry indexed

Diagnose and plan Amazon US apparel advertising with an ASIN lifecycle playbook covering long-lifecycle, short-lifecycle, and seasonal products. Use for 美国站服饰广告投放, 女装/内衣/泳装/西装/配饰广告打法, ASIN 生命周期判断, 服饰非标品找词, 广告预算结构, 旺季预热与淡季保温, 主身份/标签/流量池诊断, ACOS 高, 点击高不转化, 大词首页不转化, 断货后重启, SB/SBV/SP

Verified installs0
Stars16
Version1.0.0
Quality59/100 · Promising
Trust61/100 · Sandbox only
Audit75/100 · Needs review

Supply asset profile

Coding and developer agents

Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.

Browse track

Scenario

GitHub automation

I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Agent fit

Claude Code + CLI + Codex

Codex, Claude Code, Cursor, CLI, or custom agents.

Install

Ready

npx skills add xjli360/sealeap-amazon-ad-skills --skill sealeap-amazon-apparel-lifecycle-ads

Maintenance

fresh

Pushed today

Risk

Needs review

The skill mixes Chinese and English extensively, which may reduce clarity for non-bilingual users, though it's consistent with the target audience.

GitHub quality

16

59/100 Quality · 69/100 Trust

Coverage tags

CodingGitHub automationautomationagent-skill

Review notes

The skill mixes Chinese and English extensively, which may reduce clarity for non-bilingual users, though it's consistent with the target audience. · The benchmark data is from a 2026 course and explicitly marked as descriptive, not prescriptive; users must verify current console data, but this is already stated in the documentation.

Agent adoption scorecard

Trust, audit, and install readiness at a glance

These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.

Quality

Promising
59

Useful candidate, but compare it with alternatives before adopting.

Trust

Sandbox only
61

Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.

Audit

Needs review
75

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

OpenAgentSkill Trust Score v5

Human review before install

Run only in a sandbox and compare close alternatives before using it for real work.

CodexClaude CodeCursorOpenAgentSkill CLI

Stars

16 GitHub stars

Repo activity

16 stars, 1 forks

Maintenance

Pushed today

License

MIT

Install

npx skills add xjli360/sealeap-amazon-ad-skills --skill sealeap-amazon-apparel-lifecycle-ads

Install safety

standard package or runtime install path

Permission surface

no high-risk permission surface in public metadata

Agent outcomes

No agent outcome data yet

Docs

Usable metadata, review docs

Risk summary

Review before production

  • The skill mixes Chinese and English extensively, which may reduce clarity for non-bilingual users, though it's consistent with the target audience.
  • Low GitHub adoption signal
  • Quality score needs review
  • GitHub adoption: 16 GitHub stars

Install readiness

Install path available

  • Install path is available
  • Repository evidence is available
  • License is declared
  • No Agent Proven outcome evidence yet

Agent-readable metadata

Machine-readable decision data for this skill.

Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.

Open JSON

Suited tasks

  • Research agents workflows
  • Claude Code teams
  • builders willing to evaluate younger projects
  • Search sources

Suited agents

CodexClaude CodeCursorOpenAgentSkill CLICLI

Install decision

Command
npx skills add xjli360/sealeap-amazon-ad-skills --skill sealeap-amazon-apparel-lifecycle-ads
Policy
review
Human review
yes

Trust and risk

Trust
61/100
Audit
75/100
Risk level
Needs review

Outcome loop

Endpoint
/api/agent/outcome
Event ID
resolve
Outcomes
5

Install command

npx skills add xjli360/sealeap-amazon-ad-skills --skill sealeap-amazon-apparel-lifecycle-ads

Do not use when

  • teams that need a vendor-supported SLA
  • production agents without a repository review
  • Low GitHub adoption signal
  • The skill mixes Chinese and English extensively, which may reduce clarity for non-bilingual users, though it's consistent with the target audience.
  • No OpenAgentSkill engagement data yet

Agent safety v2

63/100 · Review before install

Reviewed with permission notesreview

Usable candidate, but the agent should surface permission and audit notes before installation.

Require human approval before installing into a real workspace.

Resolve via API

medium

Network access

Skill likely fetches remote pages, APIs, repositories, or external services.

  • The skill mixes Chinese and English extensively, which may reduce clarity for non-bilingual users, though it's consistent with the target audience.

Install targets

Install this skill in your agent workflow

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

skill install

OpenAgentSkill CLI

Resolve policy, run the source installer safely, and report a verified install receipt.

$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install xjli360-sealeap-amazon-apparel-lifecycle-ads

Agent resolve plan

Let an agent verify fit before installing.

The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.

Open text plan

Agent should check

  • Task fit and alternatives from Resolve API.
  • Audit score, trust score, and safety policy warnings.
  • Install target compatibility for Codex, Claude Code, Cursor, or CLI.

Copy prompt

Task: Use sealeap-amazon-apparel-lifecycle-ads in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20sealeap-amazon-apparel-lifecycle-ads%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/xjli360-sealeap-amazon-apparel-lifecycle-ads/install
Install command: npx skills add xjli360/sealeap-amazon-ad-skills --skill sealeap-amazon-apparel-lifecycle-ads
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent handoff

Give an agent the install path, not another directory page.

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

Open install API

Agent prompt

Use sealeap-amazon-apparel-lifecycle-ads for this task. Review https://www.openagentskill.com/api/skills/xjli360-sealeap-amazon-apparel-lifecycle-ads/install, then install with: npx skills add xjli360/sealeap-amazon-ad-skills --skill sealeap-amazon-apparel-lifecycle-ads

Registry metadata

Agent-readable profile for automatic skill selection.

This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.

Open manifest

Agent fit

58/100

Research agents

Platforms

Claude Code

Audit report

Needs review · 75/100

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

View audit reportView eval report

Agent decision cockpit

Fallback candidate for Research agents

Prototype with this skill first; keep a fallback candidate ready.

58
Readiness
Prototype
Stage

Role in stack

Fallback candidate

Primary fit

Research agents

Trust label

Prototype first

Install path

Command ready

Use when

  • Research agents workflows
  • Claude Code teams
  • builders willing to evaluate younger projects

Evidence

  • recent repository activity
  • install command or GitHub repo available
  • 59/100 quality profile

review first

  • Low GitHub adoption signal
  • The skill mixes Chinese and English extensively, which may reduce clarity for non-bilingual users, though it's consistent with the target audience.
  • No OpenAgentSkill engagement data yet

Implementation path

  1. 1Install it in a sandbox agent and run one Research agents task end to end.
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

Trust profile

Sandbox only

Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.

61
OpenAgentSkill Trust Score

GitHub adoption

FIX

16 GitHub stars

Stars/forks activity

FIX

16 stars, 1 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

Pushed today

License clarity

PASS

MIT

Good signals

  • AI review approved
  • Install path is available
  • Repository evidence is available
  • Recently maintained repository
  • Install command has no obvious high-risk pattern
  • Outcome loop is ready but needs first real agent run

Review before install

  • The skill mixes Chinese and English extensively, which may reduce clarity for non-bilingual users, though it's consistent with the target audience.
  • Low GitHub adoption signal
  • Quality score needs review
  • GitHub adoption: 16 GitHub stars
  • Stars/forks activity: 16 stars, 1 forks; issue activity unavailable in current metadata
  • No real agent outcome reports yet
  • Human review required before unattended installation

Recommended action

Run only in a sandbox and compare close alternatives before using it for real work.

Quality profile

Promising candidate for agent workflows

Useful candidate, but compare it with alternatives before adopting.

59
GitHub stars
16
Freshness
Today
Install ready
Yes
License
MIT
Review before install: Low GitHub adoption signal · The skill mixes Chinese and English extensively, which may reduce clarity for non-bilingual users, though it's consistent with the target audience.

Workflow fit

Use this skill in these scenarios

Workflow fit

Add it to a complete workflow

Alternative shortlist

Compare before you install

Similar skills that may fit this task.

Compare all

Overview

--- name: sealeap-amazon-apparel-lifecycle-ads description: "Diagnose and plan Amazon US apparel advertising with an ASIN lifecycle playbook covering long-lifecycle, short-lifecycle, and seasonal products. Use for 美国站服饰广告投放, 女装/内衣/泳装/西装/配饰广告打法, ASIN 生命周期判断, 服饰非标品找词, 广告预算结构, 旺季预热与淡季保温, 主身份/标签/流量池诊断, ACOS 高, 点击高不转化, 大词首页不转化, 断货后重启, SB/SBV/SPV/SD/商品投放组合, 否词与复盘. Default to analysis and draft; do not mutate live campaigns without explicit human approval." ---

# 亚马逊美国站服饰品类 · 生命周期广告投放法则

> 来源:亚马逊广告官方系列直播课《ASIN 决金局 · 亚马逊美国站服饰广告系列课》的长生命周期(两个视频版本)、短生命周期与季节性内容(本地共 4 个视频文件,2026 年 4 月) > 讲师:亚马逊广告 楚言(主持/官方数据)、大鹏(盛阳跨境,长生命周期)、二喵(Moses,短生命周期 + 季节性) > 倍数型数据通常为「头部 25% ASIN ÷ 尾部 25% ASIN」的相对值,非绝对值;Costume Outfit 的源画面存在头尾 20% / 25% 分位冲突,未复核前不得用作账户目标。

先读 [references/source-and-guardrails.md](references/source-and-guardrails.md) 理解四段视频、逐字稿覆盖、证据等级与执行边界。课程中的广告产品能力、资格和规则是 2026 年课程时点信息;涉及真实执行时必须核对当前美国站控制台。

## 0. 这个 skill 解决什么

服饰是**非标品**:同一个关键词背后可能对应完全不同的消费者画像,流量更容易泛化。 课程认为,照搬标品打法(先铺满入口 → 再筛选 → 加价上首页)在服饰品类**容易失焦**;是否失效必须用具体账户数据验证。

本 skill 提供的决策链条:

``` 判断周期类型 → 判断细分产品类型 → 确定广告锚点 → 判断当前所处阶段 → 套用该阶段的广告架构与预算配比 → 按触发条件调优 → 运营动作补位 ```

**使用顺序:先做第 1-4 步的诊断,再进入第 5 步的打法章节。不要跳过诊断直接给架构建议。**

---

## 1. 第一步:判断产品属于哪个生命周期类型

### 1.1 三个阶段的课程基础定义

以下月龄定义用于长、短生命周期产品的初始判断;季节性产品必须按细分类型改用旺季窗口:纯季节型为“第一个旺季前 / 第一个旺季 / 第二个旺季及以后”,周期型课程案例为“第一轮促销周期 / 第二轮 / 第三轮及以后”,见 [references/seasonal.md](references/seasonal.md)。

| 阶段 | 定义 | 特征 | |---|---|---| | 新品期 | 上架开售当天起 0–3 个月 | 缺曝光、缺流量、缺市场认知,评论少 | | 成长期 | 上架第 3 个月 → 销售额达到历史峰值 | 销售快速上升,评论/流量由少变多 | | 成熟期 | 从销售峰值 → 跌至峰值 50% 以下之前 | 销售自峰值回落但有反复,自然流量开始进来 | | 衰退期 | 跌破峰值 50% 之后 | 非广告投放的关键阶段 |

### 1.2 三大周期类型的判定

| 类型 | 趋势图特征 | 销售期 | 典型品类 | |---|---|---|---| | **长生命周期** | 稳定爬坡后长期高位,36 个月后仍在峰值 50% 以上 | > 3 年 | 西装 Suit、连衣裙(基础款)、紧身衣、打底裤/塑身衣、太阳镜、领带、配饰 | | **短生命周期** | 快速上升 + 快速下跌,窗口极短 | < 3 年 | 文胸 Bra、内裤 Underpants、睡衣睡裙、浴袍、束腰带、身体束带、腰带、钥匙扣 Keychain | | **季节性** | 高峰低谷规律可预测,旺季窗口集中 2–4 个月 | 多轮周期 | 泳装 Swimwear、女裙 Dress、外套、手套、毛衣、靴子、角色扮演服 Costume Outfit |

### 1.3 ⚠️ 关键补充:日历时间是明线,“标签语义”是课程诊断模型

**不能只按上架天数判断阶段。** 课程用“标签建立/强化/稳定/漂移”解释 ASIN 流量语义的变化,但它不是 Amazon 后台可直接读取的状态字段。使用时标记为 `COURSE_MODEL`,并从搜索词相关性、类目/商品定向流量、点击与转化、自然词覆盖和买家行为中推断:

| 课程模型 | 运营含义 | 大致对应 | |---|---|---| | 标签建立期 | 相关流量与转化语义仍在形成 | 新品期 | | 标签强化期 | 已出现可重复的相关流量与成交信号 | 成长期 | | 标签稳定期 | 主流量池和成交属性较稳定 | 成熟期 | | 标签漂移期 | 流量、页面承诺与成交人群可能出现偏移 | 需先诊断再决定是否放量 |

课程中的判断示例(不是平台硬阈值): - 上架约 3 个月但相关流量仍分散、主场景未形成 → 可按“实质仍在新品期”诊断;先收敛定位与流量,再小步验证放量。 - 上架约 1–2 周已出现清晰主场景和可重复成交 → 可能开始进入成长期;仍需满足利润、库存和样本护栏后再放大。

---

## 2. 第二步:判断细分产品类型与广告锚点

八个课程案例/细分象限,**锚点决定后续动作**:

| 周期类型 | 细分类型 | 代表品类 | 消费者核心疑问 | 广告锚点 | |---|---|---|---|---| | 长生命周期 | 功能基础型(高客单/长决策) | 西装 Suit | 合不合身 / 质量好不好 / 值不值这个价 | **建立信任** | | 长生命周期 | 功能基础型(低客单/短决策) | 女士打底裤、塑身衣 | 同上,但决策周期短 | **建立信任 + 冲动转化** | | 长生命周期 | 功能配饰型(季节性) | 太阳镜 Sunglasses | 款式是不是我喜欢的 | **及时转化 / 超越期望的性价比** | | 长生命周期 | 功能配饰型(无季节性) | 领带 Necktie | 同上 + 搭配场景 | **及时转化 + 关联流量** | | 短生命周期 | 高信任壁垒型 | Bra、Underpants | 舒适度 / 尺码准确度 / 质量柔软度 | **先信任,再规模** | | 短生命周期 | 低门槛快销型 | Keychain、腰带、围裙 | 质量过关吗 / 所见即所得吗 / 值这个钱吗 | **先转化,后留存** | | 季节性 | 纯季节性(季节+趋势双驱动) | Dress、Swimwear | 合身显身材吗 / 款式颜色好看吗 / 图物一致吗 | **旺季窗口 + 视觉驱动转化** | | 季节性 | 周期性(节庆/促销驱动) | Costume Outfit、Pants | 买得值吗 / 用得久吗 / 体验好吗 | **跨周期积累 + 促销节点集中转化** |

同一品类名可能落在不同象限,例如基础款 Dress 可呈长生命周期,强趋势款 Dress 可呈纯季节性。必须看真实销售曲线、需求驱动和旺季窗口,不能只按品类名分类。

**如何判断消费者关注点**(课程推荐方法): 1. 卖家后台 → 商机探测器 → 洞察与趋势 → 买家评论见解(过去 6 个月) 2. 把买家评价全量导出,用 AI 汇总出该细分类目的真实需求与焦虑点 3. 重点看「好评点提及率」和「差评点提及率」最高的原因,在上架前就做改进

---

## 3. 第三步:投放前的两个必要前提

### 前提 1:确定 ASIN 的主身份(课程运营模型)

主身份 = **真实定位 × 成功变量 × 流量池** 三者共同收敛的结果。

| 底座 | 含义 | 常见错误 | |---|---|---| | **真实定位** | 基于产品客观物理属性,你到底是什么产品;同样重要的是**你不是什么** | 今天打约会裙、明天打度假裙、后天打婚礼嘉宾裙 → 流量语义可能分散 | | **成功变量** | 买家到底为什么下单(服饰常见:风格感、显瘦/显身材效果、舒适度、面料质感、场景匹配、价格值不值) | 卖点过多且不一致 → 页面与流量的匹配更难判断 | | **流量池** | 哪一类流量最符合当前定位与变量 | 先问"我能投什么词",而不是先问"什么词什么场景才适合我" |

**建议动作**:前期把卖点压缩到 **2–3 个**集中放大,先让系统和买家记住最关键的一件事。 (课程案例:同一款产品采用两个不同场景的 Listing 后,流量结构与转化率表现不同;这是描述性案例,不单独证明平台归因。)

### 前提 2:理解四大标签来源与三大动态阶段

课程把以下 4 类信号概括为“标签来源”;它们用于运营诊断,不代表可直接读取的平台内部标签:

| 标签来源 | 作用 | |---|---| | 关键词标签 | 系统理解产品语义的入口(身份词/人群词/场景词/属性词) | | 类目标签 | 系统归类、产品身份的入口 | | ASIN 标签 | 系统建立关联认知的入口(ASIN 本身就是关键词合集) | | 买家行为 | 用点击、来源、加购、成交等可观测结果检验流量假设 |

三大动态阶段:**识别期 → 稳定期 → 漂移期**,是动态循环而非一次性过程。发生污染或漂移后,需重新进入下一轮识别。

**课程对广告作用的解释**: 1. 用相关流量帮助验证产品定位与受众假设 2. 放大已经被账户数据验证的流量入口

⚠️ 课程推论:身份与流量尚未收敛时盲目扩量,可能引入更多低相关点击;已有稳定证据后,广告才更适合承担放大角色。该因果需用账户实验验证。

---

## 4. 第四步:查阅头部 ASIN 数据基准

用于判断当前投放是否偏离头部路径 → 见 [references/benchmark-data.md](references/benchmark-data.md)

一句话速查:

| 品类(案例) | 生命周期倍数 | 头部核心策略 | |---|---|---| | Suit(长·高客单) | 5× | 稳扎稳打,逐步拉开差距 | | 打底裤/塑身衣(长·低客单) | 10× | 激进投入,快速建立优势 | | Sunglasses(长·配饰季节性) | 3× | 激进曝光抢占旺季 | | Necktie(长·配饰无季节性) | 1.2× | 精准高效突围 + 中后期借关联品类 | | Bra(短·高信任壁垒) | 10× | 新品期强跑 → 成长期品牌化 → 成熟期规模换利润 | | Keychain(短·低门槛快销) | ~20× | 快速验证 → 品牌突围 → 规模防御 + 以老带新 | | Dress(季节性·纯季节) | 5× | ROAS 优势从第一天建立,三轮旺季稳步放大 | | Costume Outfit(季节性·周期性) | 4–7×(分位口径待复核) | 高转化效率贯穿全程,第三轮用利润换护城河 |

---

## 5. 第五步:套用对应的广告架构

按诊断结果打开对应文档,**逐阶段执行**:

| 场景 | 文档 | |---|---| | 长生命周期(西装/打底裤/太阳镜/领带四类打法) | [references/long-lifecycle.md](references/long-lifecycle.md) | | 短生命周期(Bra 高信任壁垒 / Keychain 低门槛快销) | [references/short-lifecycle.md](references/short-lifecycle.md) | | 季节性(Dress 纯季节 / Costume 周期性 + 站外联动) | [references/seasonal.md](references/seasonal.md) | | 找词方法论(商机探测器订单效率算法、流量层级分层) | [references/keyword-research.md](references/keyword-research.md) | | 运营配合(消除顾虑、降退货、老带新、工具) | [references/operations.md](references/operations.md) | | 常见问题速答(16 条直播现场答疑) | [references/faq.md](references/faq.md) |

---

## 6. 服饰品类的九条铁律

无论哪个周期类型,以下判断在所有 4 讲中被反复强调:

1. **流量入口要多元,不要把预算压在少数几个词上。** 课程数据集显示:热门搜索词里点击份额最高的前三名 ASIN,在单个具体词上的转化份额也有限。它是课程样本中的描述性基准,不是当前账户的保证;应结合账户搜索词与增量结果决定入口数量。

2. **匹配方式按产品象限、阶段和已验证信号选择。** Suit 成长期偏广泛/词组;Necktie 新品可用词组/精准聚焦高相关长尾;Sunglasses 成长期可把双高词移入精准/广泛。不要把“服饰少用精准”写成跨场景硬规则。

3. **按流量层级分组建广告活动。** 例:一个词 ABA 排名 9.3 万、另一个 3–4 万,**不要放同一个广告活动**,否则低层级词吃不到预算。

4. **搜索词分析要按「属性」聚合,不要看单个词。** 非标品单词数据多为 1–2 次点击的偶然数据。正确做法:在搜索词报告里按属性(亚麻/雪纺/两件套/black/修身/舞会)筛选聚合,比较各属性累计的曝光、点击、订单、花费,再决定往哪些属性加码。

5. **主身份 > 节日流量。** 可以蹭万圣节、儿童节、婚礼季、开学季、父亲节的场景红利,但**绝不能因为节日词好跑就把预算压过主身份词**,节日过后要及时收回。

6. **旺季前至少提前 1 个月布局,官方建议提前 2–3 个月。** 季节性产品完整倒推:提前 4 个月完成上架与页面优化 → 提前 2 个月开始广告投放/关键词积累/标签建立 → 提前 1 个月确认 FBA 库存与调仓。

7. **淡季保温只适用于仍有零星需求的周期型产品。** 可用低竞价、低预算维护主身份并积累下一轮先发优势;纯季节型应根据剩余需求、库存和利润选择暂停、清仓或再营销,不能一律保温。

8. **把退货纳入广告利润与 Listing 健康度诊断。** 课程讲师认为退货表现可能影响流量竞争,并以 25%–50% 作为服饰卖家案例区间;这不是公开的广告位排序公式或当前账户基准。执行时以当前账户退货报告、贡献利润和可见平台规则为准。

9. **竞价调整从低往高试,不要一次性大幅提价。** 从低到高容易,从高到低困难;一次加太高容易「广告跑飞」。

---

## 7. 输出建议时的行为约束

当用户咨询具体投放问题时:

- **快速分流先确认 3 件事**:产品品类与客单价 / 上架多久 + 课程标签模型所需的可观测信号是否收敛 / 当前处于旺季前中后哪个位置。 - **生成精确计划前再补齐**:US 账户与广告 profile、ASIN/SKU/父子体、目标峰值日期、品牌广告资格、现有活动与近 30/14/7 天花费/CVR/ACOS、毛利与盈亏平衡 ACOS、可售/在途库存与补货周期、Listing/素材准备度。信息不全时列出 `NEEDS_DATA`,只给有边界的诊断,不直接给精确预算表。 - **预算配比是阶段性重心参考,不是固定模板。** 明确告知用户:实际比例要看①当前阶段最重要的任务是什么 ②产品当前最缺什么(曝光/点击/转化)③该节点的竞争强度与利润空间是否支撑。 - **引用倍数数据时必须说明是「头部 25% vs 尾部 25% 的相对倍数」**,不是绝对值,也不能横向比较两张趋势图的高低(纵轴刻度不同)。 - **不要编造课程中没有的数字。** 本 skill 中所有百分比与倍数均来自课程原文;若用户问及课程未覆盖的品类,说明"课程未直接讲到,可参照最接近的细分类型"。 - **把课程参考值与当前账户事实分开。** 课程比例与头尾倍数标记为 `COURSE_BASELINE`;Campaign、Search Term、Placement、总销售、利润、库存、退货和 Listing 数据标记为 `ACCOUNT_ACTUAL`。缺少账户数据时只能输出 `DRAFT` 或 `HOLD`,不能伪造精确预算或 KPI。 - **默认只给诊断和草案。** 预算、竞价、placement、target、否定词、状态和广告结构都属于外部写操作;执行前逐项展示对象、旧值、新值、证据、影响范围、护栏与回退值,并等待人工确认。 - **每轮只改变一个可归因主变量。** 不要在同一实验里同时改 Listing、价格、优惠、预算、竞价和定向后声称因果。

---

## 8. 交付格式与结论状态

按 [references/output-contract.md](references/output-contract.md) 输出。至少包含:

1. Marketplace、广告 profile、ASIN/SKU、父子体、数据窗口与授权范围; 2. 生命周期类型、阶段、主身份、广告锚点及判定证据; 3. 可售性、流量相关性、点击、转化/退货、利润/增量五层诊断; 4. Campaign/Ad Group 结构、关键词与商品定向、匹配方式、预算重心、创意和运营补位; 5. 单变量实验卡、成功/停止/回退条件、待确认动作; 6. `DRAFT`、`READY_FOR_REVIEW`、`APPROVED` 或 `HOLD` 之一。

只在证据和回退信息完整时使用 `READY_FOR_REVIEW`;只有明确的人工作用域与动作确认后才使用 `APPROVED`。

Technical details

Version
1.0.0
License
MIT
Last updated
Aug 23, 2026
Published
Aug 23, 2026

Decision snapshot

Fallback candidate

58
Ready
Prototype
Stage

recent repository activity

Audit

Install review

Install and adoption review

75
Needs review
Security
81/100
Maintenance
100/100
Install
92/100
Open full auditView eval report

Agent-proven evidence

Agent-proven evidence

Outcome reports after resolve, review, install, and one narrow run.

0
Proven
Needs first agent runAuto-install: review firstLast: Unknown
Success rate
Recent failure
Outcomes
0
Output quality
Failed
0
Not relevant
0
Installs
0
Risk blocked
0
Setup needed
0
Production
0

No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.

Install

Add to agent workflow

Free and open source. Review the report before installing into production agents.

Growth loop

Share kit

X

Scenario-led draft for sealeap-amazon-apparel-lifecycle-ads, ready for a manual X post.

Curator note
sealeap-amazon-apparel-lifecycle-ads: Diagnose and plan Amazon US apparel advertising with an ASIN lifecycle playbook covering long...

16 stars

https://www.openagentskill.com/skills/xjli360-sealeap-amazon-apparel-lifecycle-ads?ref=x
Open X draft
Optional reply with install command
Listing + install path for sealeap-amazon-apparel-lifecycle-ads:
https://www.openagentskill.com/skills/xjli360-sealeap-amazon-apparel-lifecycle-ads?ref=x

Install: npx skills add xjli360/sealeap-amazon-ad-skills --skill sealeap-amazon-apparel-li...

Listing source

Registry indexed

Claimable

This listing was indexed from public sources and is not marked official until a maintainer claim is approved.

Creator
xjli360
Indexed by
OpenAgentSkill community index

Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.

Claim this skill

Owner claim

Claim this skill listing

This Registry indexed listing is attributed to xjli360 but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.

Creator backlink kit

Add the evidence badges to your README

Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/xjli360-sealeap-amazon-apparel-lifecycle-ads?metric=listed&label=Listed)](https://www.openagentskill.com/skills/xjli360-sealeap-amazon-apparel-lifecycle-ads)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/xjli360-sealeap-amazon-apparel-lifecycle-ads?metric=trust&label=Trust)](https://www.openagentskill.com/skills/xjli360-sealeap-amazon-apparel-lifecycle-ads)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/xjli360-sealeap-amazon-apparel-lifecycle-ads?metric=audit&label=Audit)](https://www.openagentskill.com/skills/xjli360-sealeap-amazon-apparel-lifecycle-ads/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/xjli360-sealeap-amazon-apparel-lifecycle-ads?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/xjli360-sealeap-amazon-apparel-lifecycle-ads)

Author

X

xjli360

@xjli360

Platform fit

Health signals

GitHub stars
16
Quality score
32/100
Last GitHub push
Aug 23, 2026
Framework hints
Unknown
OpenAgentSkill views
0
Install copies
0
Outbound clicks
0

Community signal

Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.

Trust & safety

Sandbox only

61
  • GitHub adoption16 GitHub starsFIX
  • Stars/forks activity16 stars, 1 forks; issue activity unavailable in current metadataFIX
  • Recent maintenancePushed todayPASS
  • License clarityMITPASS
  • README/SKILL.md completenessPublic metadata needs stronger README/SKILL.md contextINFO
  • Dependency/runtime riskno major dependency risk hints in public metadataPASS