Agent skill

Sealeap Hundun Amazon Auto Campaign Bid Lifecycle

by xjli360 in xjli360/sealeap-amazon-skills

Structure an automatic Sponsored Products campaign with a naming and portfolio convention that scales across many products, then match its bid strategy — dynamic up-and-down, fixed, or…

MITAuto-check passed

Install Sealeap Hundun Amazon Auto Campaign Bid Lifecycle

skills CLI
$ npx skills add xjli360/sealeap-amazon-skills --skill sealeap-hundun-amazon-auto-campaign-bid-lifecycle -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install xjli360/sealeap-amazon-skills sealeap-hundun-amazon-auto-campaign-bid-lifecycle --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/xjli360/sealeap-amazon-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/amazon-skills/bilibili/hundun/sealeap-hundun-amazon-auto-campaign-bid-lifecycle .claude/skills/sealeap-hundun-amazon-auto-campaign-bid-lifecycle && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sealeap-hundun-amazon-auto-campaign-bid-lifecycle
GitHub stars
251
Token cost
~1k tokens
SKILL.md length
194 words
Files
5 (incl. scripts, references)
Skills in repo
179
Repo updated
First seen
Licence
MIT

At a glance

Structure an automatic Sponsored Products campaign with a naming and portfolio convention that scales across many products, then match its bid strategy — dynamic up-and-down, fixed, or…

  • Works in 4 steps: 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。 → …
  • 自动广告竞价策略怎么选、新品期出价多少合适、什么时候用固定竞价、否定词和否定词组区别、要不要否定竞品ASIN
  • SKILL.md covers 目标, 不可妥协的边界, 先判断任务模式 and 开始前要拿到, plus 3 more sections
  • Runs Python scripts from its folder

What it does

Sealeap Hundun Amazon Auto Campaign Bid Lifecycle is an agent skill from xjli360/sealeap-amazon-skills. Structure an automatic Sponsored Products campaign with a naming and portfolio convention that scales across many products, then match its bid strategy — dynamic up-and-down, fixed, or dynamic-down-only — to the listing's lifecycle stage (new, growing, mature) using observed CPC ranges and organic-share trends as evidence, deferring negative keywords and negative product targeting until enough real search-term and click data exists. The stage-to-bid-strategy mapping and any organic-rank-lift effect from sustained…

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/mcp-data-plan.md` and `references/playbook.md`).

The repository describes itself as: Reusable Agent Skills for Amazon product research, listings, advertising, inventory, and operations. The licence is MIT.

When your agent uses it

  • 自动广告竞价策略怎么选、新品期出价多少合适、什么时候用固定竞价、否定词和否定词组区别、要不要否定竞品ASIN
  • Pre-emptively add negative keywords before any real search-term data exists
  • Do not assume a specific daily-budget number is safe for all accounts without checking current context

Example prompts

  • “/sealeap-hundun-amazon-auto-campaign-bid-lifecycle”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. 诊断:读取现状、证据和缺口,不生成线上写入动作。
  2. 方案草案:输出可审核的结构、参数范围、实验和回退值。
  3. 执行准备:只生成待批准变更表或 API/控制台操作草案。
  4. 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。

What it can do on your machine

Read from SKILL.md and the folder at commit 497d4b8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sealeap Hundun Amazon Auto Campaign Bid Lifecycle loads about 1k tokens when it runs, and up to ~3.7k if it reads all its reference files. Until then it costs about 230 tokens; SKILL.md has 194 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~230
When it runs · the whole SKILL.md, loaded when a task matches
~1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from xjli360/sealeap-amazon-skills at commit 497d4b8, republished under its MIT licence (© xjli360). 194 words, ~1,009 tokens.

Download SKILL.mdSave it as .claude/skills/sealeap-hundun-amazon-auto-campaign-bid-lifecycle/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
sealeap-hundun-amazon-auto-campaign-bid-lifecycle
description
Structure an automatic Sponsored Products campaign with a naming and portfolio convention that scales across many products, then match its bid strategy — dynamic up-and-down, fixed, or dynamic-down-only — to the listing's lifecycle stage (new, growing, mature) using observed CPC ranges and organic-share trends as evidence, deferring negative keywords and negative product targeting until enough real search-term and click data exists. The stage-to-bid-strategy mapping and any organic-rank-lift effect from sustained ad placement are treated as account-level hypotheses, not guaranteed platform mechanics. Use for 自动广告竞价策略怎么选、新品期出价多少合适、什么时候用固定竞价、否定词和否定词组区别、要不要否定竞品ASIN. Do not use to pre-emptively add negative keywords before any real search-term data exists, and do not assume a specific daily-budget number is safe for all accounts without checking current context.

Amazon 自动广告竞价阶段与否定词

目标

Structure an automatic Sponsored Products campaign with a naming and portfolio convention that scales across many products, then match its bid strategy — dynamic up-and-down, fixed, or dynamic-down-only — to the listing's lifecycle stage (new, growing, mature) using observed CPC ranges and organic-share trends as evidence, deferring negative keywords and negative product targeting until enough real search-term and click data exists. The stage-to-bid-strategy mapping and any organic-rank-lift effect from sustained ad placement are treated as account-level hypotheses, not guaranteed platform mechanics.

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。
  • 默认只读诊断和草案;任何广告、Listing、库存、促销或外部系统写操作都需逐项展示并取得明确批准。
  • 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。
  • 竞价策略与产品阶段的对应关系(新品期动态、成长期固定、成熟期只降)是来源账户内观察到的经验模式,不是所有类目/竞争强度下都适用,需要以当前账户实际测试结果为准。
  • “持续稳定占据某关键词广告位会带动自然排名上升”是待验证的算法假设,不能作为确定性因果结论对待,只能作为观察现象持续跟踪。
  • 日预算的自然月合计上限、否定商品的判断阈值等具体数值均为来源经验值,需要用当前账户的实际数据重新校准。
  • 否定词组存在误伤相关搜索词的风险,使用前应先看清该词组会覆盖哪些相邻词,避免过度否定导致有效流量被一并屏蔽。

先判断任务模式

  1. 诊断:读取现状、证据和缺口,不生成线上写入动作。
  2. 方案草案:输出可审核的结构、参数范围、实验和回退值。
  3. 执行准备:只生成待批准变更表或 API/控制台操作草案。
  4. 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、店铺、ASIN/SKU、广告类型和目标
  • 同口径的 Campaign、Targeting、Search Term、Placement 与 Advertised Product 报告
  • 售价、优惠、COGS、Amazon 费用、退款与目标贡献利润
  • 库存、Buy Box、Listing、评论和同期市场事件

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:

  1. 广告活动命名与分组:不使用系统默认的时间戳命名,改用“产品名+广告类型”的命名规则;用广告组合把同一产品下的自动、手动等广告类型都归到一起,便于按产品维度做优化和看数据。
  2. 起量条件与预算:确认 listing 已在售、有可售库存、有购物车按钮后再开广告;新品期日预算从小额起步,先跑出曝光、点击与首批出单词等数据,不宜一开始就给到较大预算。
  3. 竞价策略按阶段匹配:新品期(尚不知道有效竞价区间)用动态提高/降低竞价,配合第三方关键词工具查到的核心词 CPC 参考区间,设置一个区间中段偏上的起始竞价去探索;成长期(已摸到大致能出单的竞价水平、排名进入类目前列)改为固定竞价,把出价卡在已验证有效的区间内做精准控制;成熟期(自然流量占比明显提高)改为只降不升的动态竞价,控制花费。
  4. 否定词时机:广告刚起量、还没跑出真实搜索词数据时不做否定;等有了实际点击/搜索词数据后,再逐条判断哪些词与产品不相关或转化差,优先用否定精确而不是否定词组,因为否定词组可能连带屏蔽掉本来相关的周边搜索词。
  5. 否定商品定向:当自己的广告持续在某个明显性价比更高(价格更低、评论/评分更好)的竞品详情页下曝光但多次点击不出单时,可以把该 ASIN 加入否定商品,避免继续在无转化机会的位置花钱;不要在没有实际点击数据支持的情况下预判性否定。
  6. 提交前核对:广告组合、开始/结束时间、日预算数值(尤其警惕多输入一位数导致预算被放大一个数量级)、竞价策略、投放商品、匹配方式是否都设置正确。
  7. 提交后预期管理:广告通常需要一定延迟才会在前台产生曝光,短时间内看不到展示不代表配置有误,先等待再排查。

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:获取目标核心关键词的历史CPC区间等第三方代理数据,用于校准新品期起始竞价范围。

  • 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

  • 广告活动命名与组合结构规范
  • 分阶段竞价策略对照表(新品期/成长期/成熟期)
  • 否定词/否定商品判断记录
  • 提交前检查清单
  • 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。

© xjli360, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references) in amazon-skills/bilibili/hundun/sealeap-hundun-amazon-auto-campaign-bid-lifecycle of xjli360/sealeap-amazon-skills.

  • SKILL.md
  • agents/openai.yaml
  • references/mcp-data-plan.md
  • references/playbook.md
  • scripts/mcp_research.py

Open the folder on GitHubat commit 497d4b8

Compare with similar skills

Sealeap Hundun Amazon Auto Campaign Bid Lifecycle next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sealeap Hundun Amazon Auto Campaign Bid Lifecycle compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sealeap Hundun Amazon Auto Campaign Bid Lifecycle this skillxjli360/sealeap-amazon-skills251—~1kAutomated safety check: PassMIT
Campaign Naming Convention Builderirinabuht12-oss/marketing-skills4.1k—~717Automated safety check: PassNone
BidsK-Dense-AI/scientific-agent-skills48k1 repos~3.7kAutomated safety check: PassMIT
Portfolioanthropics/claude-for-legal9.6k3 repos~5.3kAutomated safety check: PassApache-2.0
Ecc Conventionsaffaan-m/ECC276k—~2.8kAutomated safety check: PassMIT
Marketing Campaignaffaan-m/ECC277k1 repos~1.3kAutomated safety check: PassMIT

Similar skills

  • Campaign Naming Convention Builder

    irinabuht12-oss/marketing-skills

    Builds a consistent, filterable naming convention across your Google and Meta accounts based on your campaign types, objectives, targeting, and reporting needs.

    4.1k GitHub stars~717 tokensUpdated 17 days ago
    Marketing & SEOAuto-check passed
  • Bids

    K-Dense-AI/scientific-agent-skills

    Organizes, queries, validates, and converts Brain Imaging Data Structure (BIDS) datasets.

    48k GitHub starsUsed in 1 repo~3.7k tokens
    Research & ScienceAuto-check passed
  • Portfolio

    anthropics/claude-for-legal

    Official

    Track the IP portfolio — registrations, renewals, maintenance fees, and use declarations.

    9.6k GitHub starsUsed in 3 repos~5.3k tokens
    Legal & ComplianceAuto-check passed
  • Ecc Conventions

    affaan-m/ECC

    Development conventions and patterns for ECC. An agent skill from affaan-m/ECC.

    276k GitHub stars~2.8k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Marketing Campaign

    affaan-m/ECC

    End-to-end marketing campaign planning and execution. An agent skill from affaan-m/ECC.

    277k GitHub starsUsed in 1 repo~1.3k tokens
    Marketing & SEOAuto-check passed
  • Sponsor Finder

    github/awesome-copilot

    Official

    Find which of a GitHub repository's dependencies are sponsorable via GitHub Sponsors.

    40k GitHub starsUsed in 1 repo~3k tokens
    Productivity & AutomationAuto-check passed

More from xjli360/sealeap-amazon-skills

All 179 skills in this repo
  • Sealeap Amazon Acos Diagnostics

    xjli360/sealeap-amazon-skills

    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…

    251 GitHub stars~1.2k tokensUpdated 13 days ago
    Auto-check passed
  • Sealeap Amazon Ca Apparel Ads

    xjli360/sealeap-amazon-skills

    Diagnose and draft Amazon Canada apparel advertising plans with lifecycle and seasonal timing, English/French search coverage, account evidence, profitability guardrails, and approval-ready…

    251 GitHub stars~1.2k tokensUpdated 13 days ago
    Auto-check passed
  • Sealeap Amazon Listing Optimizer

    xjli360/sealeap-amazon-skills

    Audit, diagnose, rewrite, creatively brief, test, and safely prepare updates for Amazon product detail pages using live marketplace and product-type requirements, verified product facts, Brand…

    251 GitHub stars~1.4k tokensUpdated 13 days ago
    Auto-check passed
  • Sealeap Amazon Prime Day Planning

    xjli360/sealeap-amazon-skills

    Filter, interpret, and turn the authorized 2025 Amazon Prime Day advertising insight records into a qualified event plan without averaging incompatible slices or treating historical benchmarks as…

    251 GitHub stars~591 tokensUpdated 13 days ago
    Auto-check passed
  • Sealeap Amazon Product Targeting

    xjli360/sealeap-amazon-skills

    Research, diagnose, and draft Amazon Ads ASIN and category product-targeting plans that complement keyword targeting, including audience expansion, competitor and category traffic, cross-sell…

    251 GitHub stars~1.2k tokensUpdated 13 days ago
    Auto-check passed
  • Sealeap Amazon Acos Conversion Diagnostics

    xjli360/sealeap-amazon-skills

    Diagnose high Amazon Ads ACoS by decomposing CPC, conversion rate, price, query mix, placement mix, and sample sufficiency.

    251 GitHub stars~552 tokensUpdated 13 days ago
    Auto-check passed

Questions about Sealeap Hundun Amazon Auto Campaign Bid Lifecycle

What does Sealeap Hundun Amazon Auto Campaign Bid Lifecycle do?

Structure an automatic Sponsored Products campaign with a naming and portfolio convention that scales across many products, then match its bid strategy — dynamic up-and-down, fixed, or…. Sealeap Hundun Amazon Auto Campaign Bid Lifecycle is an agent skill from xjli360/sealeap-amazon-skills. Structure an automatic Sponsored Products campaign with a naming and portfolio convention that scales across many products, then match its bid strategy — dynamic up-and-down, fixed, or dynamic-down-only — to the listing's lifecycle stage (new, growing, mature) using observed CPC ranges and organic-share trends as evidence, deferring negative keywords and negative product targeting until enough real search-term and click data exists.

When should I use Sealeap Hundun Amazon Auto Campaign Bid Lifecycle?

Sealeap Hundun Amazon Auto Campaign Bid Lifecycle fits situations like: 自动广告竞价策略怎么选、新品期出价多少合适、什么时候用固定竞价、否定词和否定词组区别、要不要否定竞品ASIN; pre-emptively add negative keywords before any real search-term data exists; do not assume a specific daily-budget number is safe for all accounts without checking current context.

How do I install Sealeap Hundun Amazon Auto Campaign Bid Lifecycle in Claude Code?

Run `npx skills add xjli360/sealeap-amazon-skills --skill sealeap-hundun-amazon-auto-campaign-bid-lifecycle -a claude-code`. Or copy the skill folder (amazon-skills/bilibili/hundun/sealeap-hundun-amazon-auto-campaign-bid-lifecycle in xjli360/sealeap-amazon-skills) into .claude/skills/sealeap-hundun-amazon-auto-campaign-bid-lifecycle in your project. Claude Code loads it when a task matches its description.

How do I install Sealeap Hundun Amazon Auto Campaign Bid Lifecycle in Codex?

Run `npx skills add xjli360/sealeap-amazon-skills --skill sealeap-hundun-amazon-auto-campaign-bid-lifecycle -a codex`. Or copy the skill folder (amazon-skills/bilibili/hundun/sealeap-hundun-amazon-auto-campaign-bid-lifecycle in xjli360/sealeap-amazon-skills) into .agents/skills/sealeap-hundun-amazon-auto-campaign-bid-lifecycle in your project. Codex loads it when a task matches its description.

Can I use Sealeap Hundun Amazon Auto Campaign Bid Lifecycle in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xjli360/sealeap-amazon-skills --skill sealeap-hundun-amazon-auto-campaign-bid-lifecycle -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sealeap-hundun-amazon-auto-campaign-bid-lifecycle, .gemini/skills/sealeap-hundun-amazon-auto-campaign-bid-lifecycle, .github/skills/sealeap-hundun-amazon-auto-campaign-bid-lifecycle and .opencode/skills/sealeap-hundun-amazon-auto-campaign-bid-lifecycle in your project.

What does Sealeap Hundun Amazon Auto Campaign Bid Lifecycle need to run?

Going by SKILL.md and its folder, Sealeap Hundun Amazon Auto Campaign Bid Lifecycle needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Sealeap Hundun Amazon Auto Campaign Bid Lifecycle access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sealeap Hundun Amazon Auto Campaign Bid Lifecycle safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Sealeap Hundun Amazon Auto Campaign Bid Lifecycle use?

Sealeap Hundun Amazon Auto Campaign Bid Lifecycle is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sealeap Hundun Amazon Auto Campaign Bid Lifecycle use?

About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.7k tokens, read only when the agent opens those files.

What are the alternatives to Sealeap Hundun Amazon Auto Campaign Bid Lifecycle?

Skills that share tags, products or a category with Sealeap Hundun Amazon Auto Campaign Bid Lifecycle: Campaign Naming Convention Builder (irinabuht12-oss/marketing-skills, 4.1k stars), Bids (K-Dense-AI/scientific-agent-skills, 48k stars), Portfolio (anthropics/claude-for-legal, 9.6k stars) and Ecc Conventions (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sealeap Hundun Amazon Auto Campaign Bid Lifecycle?

xjli360 (a GitHub user) maintains it in xjli360/sealeap-amazon-skills, which has 251 GitHub stars. The repository holds 179 skills in this directory. The repository was last updated on September 28, 2026.

Source: xjli360/sealeap-amazon-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.