Agent skill

Sealeap Amazon Low Bid Discovery Ads

by xjli360 in xjli360/sealeap-amazon-skills

Diagnose and design low-bid Amazon Ads discovery experiments that probe residual traffic, minimum viable bids, placements, and harvestable search terms under a portfolio cap.

MITAuto-check passed

Install Sealeap Amazon Low Bid Discovery Ads

skills CLI
$ npx skills add xjli360/sealeap-amazon-skills --skill sealeap-amazon-low-bid-discovery-ads -a claude-code

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

GitHub CLI
$ gh skill install xjli360/sealeap-amazon-skills sealeap-amazon-low-bid-discovery-ads --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/douyin/qilin/sealeap-amazon-low-bid-discovery-ads .claude/skills/sealeap-amazon-low-bid-discovery-ads && 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-amazon-low-bid-discovery-ads
GitHub stars
251
Token cost
~577 tokens
SKILL.md length
91 words
Files
4 (incl. scripts, references)
Skills in repo
179
Repo updated
First seen
Licence
MIT

At a glance

Diagnose and design low-bid Amazon Ads discovery experiments that probe residual traffic, minimum viable bids, placements, and harvestable search terms under a portfolio cap.

  • Works in 6 steps: 划定实验单元 → 计算安全竞价 → 从低向高探测 → …
  • The user asks about 捡漏广告
  • SKILL.md covers 目标, 适用任务, 开始前要拿到 and 不可妥协的边界, plus 4 more sections
  • Runs Python scripts from its folder

What it does

Sealeap Amazon Low Bid Discovery Ads is an agent skill from xjli360/sealeap-amazon-skills. Diagnose and design low-bid Amazon Ads discovery experiments that probe residual traffic, minimum viable bids, placements, and harvestable search terms under a portfolio cap. Use when the user asks about 捡漏广告, low-CPC discovery, bid floors, incremental keyword testing, or turning cheap traffic into a durable campaign. Default to analysis and draft changes; never mutate live ads without explicit approval.

Its SKILL.md is about 580 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/mcp-data-plan.md` and `scripts/mcp_research.py`).

It works with Model Context Protocol. 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

  • The user asks about 捡漏广告
  • Low-CPC discovery
  • Incremental keyword testing
  • Turning cheap traffic into a durable campaign

Example prompts

  • “/sealeap-amazon-low-bid-discovery-ads”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. 划定实验单元
  2. 计算安全竞价
  3. 从低向高探测
  4. 验证而非猜测
  5. 迁移赢家
  6. 复盘增量

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 Amazon Low Bid Discovery Ads loads about 577 tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 111 tokens; SKILL.md has 91 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~111
When it runs · the whole SKILL.md, loaded when a task matches
~577
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.1k

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). 91 words, ~577 tokens.

Download SKILL.mdSave it as .claude/skills/sealeap-amazon-low-bid-discovery-ads/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
sealeap-amazon-low-bid-discovery-ads
description
Diagnose and design low-bid Amazon Ads discovery experiments that probe residual traffic, minimum viable bids, placements, and harvestable search terms under a portfolio cap. Use when the user asks about 捡漏广告, low-CPC discovery, bid floors, incremental keyword testing, or turning cheap traffic into a durable campaign. Default to analysis and draft changes; never mutate live ads without explicit approval.

Amazon 低竞价流量发现

目标

在不挤占主力广告预算的前提下,探索可获得曝光、点击和订单的最低有效竞价,并把被验证的流量迁移到可独立管理的结构中。

适用任务

  • 为单个 ASIN、同类产品组或店铺组合设计低竞价探索。
  • 判断无曝光、低点击、偶发出单究竟是竞价不足、流量稀薄还是转化不成立。
  • 把搜索词或商品投放中的低成本赢家迁移为主力广告。

开始前要拿到

  • 站点、币种、ASIN、商品阶段、目标利润和广告目标。
  • 搜索词、投放、广告位和已购商品报告,建议窗口至少覆盖一个完整购买周期。
  • 售价、贡献毛利、目标 ACoS 或盈亏平衡 CPC,以及组合级预算上限。

缺失的数据要明确列为缺口,并把结论标成事实、估算或假设;不要补造数字。

不可妥协的边界

  • 不要照搬固定低价或极端广告位系数;先按站点、类目和币种计算安全测试区间。
  • 不得把全部店铺产品无差别混入同一实验;相关性、库存和利润边界必须可解释。
  • 不把偶发订单当成稳定结论,也不把广告订单直接归因为自然排名提升。
  • 当前 Amazon 官方政策、帮助页、账户资格和后台实际字段优先于本 Skill 中的经验框架;规则可能变化时先核验。
  • 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。
  • 不输出原素材的创作者身份、账号、链接、视频编号或可反查线索;当前业务证据的官方来源、采集时间和口径仍需保留。

第三方 MCP 数据

只有在本任务确实需要外部市场、竞品、关键词或公开网页证据时,才读取 references/mcp-data-plan.md,并使用 scripts/mcp_research.py。

  • 先动态执行 tools/list、search-tools 和 describe,依据实时 inputSchema 构造参数,不照搬历史工具名。
  • 凭证只从环境变量读取,不放进命令参数、URL、Skill、结果文件或 Git。
  • tools/call 可能计费。调用前展示 Provider、工具名、无密钥参数、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。
  • 第三方数据标为估算或代理证据,记录 Provider、工具、无密钥参数、查询时间和原始结果位置;失败一次后记录缺口,不反复消耗额度。
  • 脱敏结果用 --output 写到 Skill 包之外的任务私有目录;不假设安装位置受仓库 .gitignore 保护,不把运行结果写入 Skill 包。

工作流

1. 划定实验单元

按单 ASIN、同类产品组和店铺级探索分层;每个单元单独设置预算帽、命名、观察窗口和停止条件。

2. 计算安全竞价

用盈亏平衡 CPC、历史 CPC 分位数和预估转化率建立起始区间。广告位加价后的有效竞价也必须落在风险预算内。

3. 从低向高探测

先以保守竞价运行;无曝光时按预定小步幅上调,并记录每次调整、曝光首次出现点和点击首次出现点,避免同日反复改动。

4. 验证而非猜测

按搜索词累计足够点击后比较转化率、CPA、订单利润和广告位表现。无效词降价、暂停或否定;数据不足标为待观察。

5. 迁移赢家

把稳定出单且利润成立的搜索词迁移到精准或独立广告,把商品目标迁移到独立商品投放;原探索活动保留隔离和去重策略。

6. 复盘增量

按周评估新增订单、TACoS、毛利、主力广告蚕食和自然订单变化,只扩大具备增量证据的单元。

判断标准

  • 有效竞价 = 基础竞价乘以适用广告位调整后的上限,必须展示计算口径。
  • 每个结论标注事实、估算或假设,并写明样本窗口。
  • 同时报告赢家、失败项、数据不足项和下一轮单一变量。

必须交付的结果

  • 实验分层表与预算帽。
  • 竞价阶梯、观察周期和停止规则。
  • 搜索词或商品目标的保留、迁移、降价、暂停清单。
  • 只读诊断结论;如需执行,另列待批准变更。

结尾列出数据窗口、关键假设、证据缺口、风险和下一步;如包含待执行动作,单独放在“待批准变更”中。

© 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 3 other files (scripts, references) in amazon-skills/douyin/qilin/sealeap-amazon-low-bid-discovery-ads of xjli360/sealeap-amazon-skills.

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

Open the folder on GitHubat commit 497d4b8

Compare with similar skills

Sealeap Amazon Low Bid Discovery Ads 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 Amazon Low Bid Discovery Ads compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sealeap Amazon Low Bid Discovery Ads this skillxjli360/sealeap-amazon-skills251—~577Automated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Figma use_figma Plugin API Ruleswarpdotdev/warp65k4 repos~4.4kAutomated safety check: PassAGPL-3.0
Stitch to Remotion Walkthrough Videosgoogle-labs-code/stitch-skills8.5k6 repos~3.2kAutomated safety check: NotesApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.

    65k GitHub starsUsed in 4 repos~4.4k tokens
    Frontend & DesignAuto-check passed
  • Stitch to Remotion Walkthrough Videos

    google-labs-code/stitch-skills

    Official

    Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.

    8.5k GitHub starsUsed in 6 repos~3.2k tokens
    Media & CreativeAuto-check: notes
  • MCP Development

    coollabsio/coolify

    A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 1 repo~949 tokens
    Frontend & DesignAuto-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 Amazon Low Bid Discovery Ads

What does Sealeap Amazon Low Bid Discovery Ads do?

Diagnose and design low-bid Amazon Ads discovery experiments that probe residual traffic, minimum viable bids, placements, and harvestable search terms under a portfolio cap. Sealeap Amazon Low Bid Discovery Ads is an agent skill from xjli360/sealeap-amazon-skills. Diagnose and design low-bid Amazon Ads discovery experiments that probe residual traffic, minimum viable bids, placements, and harvestable search terms under a portfolio cap.

When should I use Sealeap Amazon Low Bid Discovery Ads?

Sealeap Amazon Low Bid Discovery Ads fits situations like: the user asks about 捡漏广告; low-CPC discovery; incremental keyword testing; turning cheap traffic into a durable campaign.

How do I install Sealeap Amazon Low Bid Discovery Ads in Claude Code?

Run `npx skills add xjli360/sealeap-amazon-skills --skill sealeap-amazon-low-bid-discovery-ads -a claude-code`. Or copy the skill folder (amazon-skills/douyin/qilin/sealeap-amazon-low-bid-discovery-ads in xjli360/sealeap-amazon-skills) into .claude/skills/sealeap-amazon-low-bid-discovery-ads in your project. Claude Code loads it when a task matches its description.

How do I install Sealeap Amazon Low Bid Discovery Ads in Codex?

Run `npx skills add xjli360/sealeap-amazon-skills --skill sealeap-amazon-low-bid-discovery-ads -a codex`. Or copy the skill folder (amazon-skills/douyin/qilin/sealeap-amazon-low-bid-discovery-ads in xjli360/sealeap-amazon-skills) into .agents/skills/sealeap-amazon-low-bid-discovery-ads in your project. Codex loads it when a task matches its description.

Can I use Sealeap Amazon Low Bid Discovery Ads 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-amazon-low-bid-discovery-ads -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-amazon-low-bid-discovery-ads, .gemini/skills/sealeap-amazon-low-bid-discovery-ads, .github/skills/sealeap-amazon-low-bid-discovery-ads and .opencode/skills/sealeap-amazon-low-bid-discovery-ads in your project.

What does Sealeap Amazon Low Bid Discovery Ads need to run?

Going by SKILL.md and its folder, Sealeap Amazon Low Bid Discovery Ads needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Sealeap Amazon Low Bid Discovery Ads 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 Amazon Low Bid Discovery Ads 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 Amazon Low Bid Discovery Ads use?

Sealeap Amazon Low Bid Discovery Ads 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 Amazon Low Bid Discovery Ads use?

About 577 tokens (SKILL.md is roughly 2.3k 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 1.5k tokens, read only when the agent opens those files.

What are the alternatives to Sealeap Amazon Low Bid Discovery Ads?

Skills that share tags, products or a category with Sealeap Amazon Low Bid Discovery Ads: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sealeap Amazon Low Bid Discovery Ads?

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.