AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Sealeap Amazon Creative Ai

skill-xjli360-sealeap-amazon-skills-sealeap-amazon-creative-ai · by xjli360

Turn verified Amazon product and audience evidence into reviewable AI-assisted advertising concepts, copy, image/video briefs, variants, and controlled creative tests. Use for 对话式AI广告素材, Creative Agent, Creative Studio, AI爆款素材, AI视频脚本, 商品广告创意, prompt共创, 素材A/B测试, POE/ABA insight-to-creative, or converting the authorized conversational-AI seller case into a repeatable workflow. Verify current tool…

— No reviews yet
0 installs
31 views
0.0% view→install

Install

$ agentstack add skill-xjli360-sealeap-amazon-skills-sealeap-amazon-creative-ai

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-xjli360-sealeap-amazon-skills-sealeap-amazon-creative-ai)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 16d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Sealeap Amazon Creative Ai? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Amazon 广告 AI 创意工作流

目标

把“让 AI 做一条爆款素材”改成可复核的创意实验:用真实商品、受众和目标约束模型,生成相互有意义差异的概念,逐条做事实/品牌/政策审查,再用预注册指标比较,而不是把一次好结果归因于 AI。

开始前读 [references/source-and-guardrails.md](references/source-and-guardrails.md)。生成概念和 prompt 读 [references/creative-workflow.md](references/creative-workflow.md),审核与实验读 [references/review-and-testing.md](references/review-and-testing.md)。

工作流

1. 确认模式

  • IDEATE:只生成方向;
  • BRIEF:输出可交付给设计/视频团队的 brief;
  • GENERATE_PREP:准备给当前可用 AI 工具的 prompt,不提交;
  • TEST_PREP:做审核、版本管理和 A/B 草案;
  • APPROVED_PUBLISH:仅在用户明确批准具体素材与投放对象后执行。

默认 BRIEF,不把工具入口存在等同于当前账户可用。

2. 建立事实包

至少需要 marketplace、ASIN、目标人群、使用场景、广告目标、允许的商品事实、禁用声明、品牌语气、格式/时长、PDP 证据和现有表现。可用 Product Opportunity Explorer、Brand Analytics、搜索词、评论主题和账户报告提供洞察,但必须保留来源、日期与作用域。

缺少商品事实时不让模型猜图中属性、材质、尺寸、兼容性或功效。

3. 写清创意命题

用一句话固定:为[人群]在[场景]展示[经验证的单一价值],目标是[行为]。每个版本只改变一个创意假设,例如痛点、演示方式、开场钩子或叙事视角。

4. 人机共创

按 [references/creative-workflow.md](references/creative-workflow.md) 先发散 5–10 个概念,再按相关性、可证明性、差异化、无声/移动端可懂性和制作可行性筛到 2–4 个。将被拒概念与原因保留,避免下次重复。

5. 生成并版本化

每个产物记录 asset_id / concept_id / prompt_version / model_or_tool / seed_if_available / source_assets / generated_at / editor / status。AI 产物先标 DRAFT_AI;人工修订后标 REVIEWED_DRAFT,不能直接称“官方素材”或“已合规”。

6. 三层审核

  1. FACT:所有文字与画面是否由商品档案支持;
  2. BRAND:语气、视觉、Logo、目标人群和差异化是否一致;
  3. POLICY:当前 Amazon 广告政策、类目限制、IP/肖像/商标、生成式内容要求和技术规格。

任一层 HOLD 就不进入测试。

7. 控制实验

固定人群、投放、预算、ASIN、PDP、时间逻辑和其它主要变量,只比较一个创意维度。预注册主指标、护栏、样本门槛、最大花费、停止线、归因成熟日和回退。

8. 复盘

分别报告素材生产效率与媒体效果。节省制作时间/成本不等于广告表现更好;CTR 上升不等于利润或增量销售上升。

必须交付

  • 事实包、缺口与禁止猜测项;
  • 创意命题、候选矩阵和筛选理由;
  • 每个入选概念的 brief/prompt 与版本信息;
  • FACT/BRAND/POLICY 审核表;
  • 单变量测试卡和审批状态。

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.