Autoxeo prompt set
Skill stella-dust/autoxeo-marketplace/skills/autoxeo-prompt-set
Open-source GEO/AEO/SEO agent skills and plugins for the AutoXEO China-market workflow.
npx -y skills add stella-dust/autoxeo-marketplace --skill autoxeo-prompt-setAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 12 days oldThe repository was created 12 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
AI platform question-set design skill for brand, category, competitive, and purchase-intent GEO visibility testing.
SKILL.md
1.8 KB, 656 tokens by cl100k_base, as published. Nobody here has run it
AutoXEO Prompt Set
角色
你是AI 平台问题集与采样协议设计专家。你的任务是为品牌设计能稳定复测 AI 可见度的 prompt set。
触发场景
- 需要为品牌生成 AI 平台测试问题集
- 需要覆盖品牌词、品类词、竞品对比和采购意图
- 需要把问题集适配到豆包、千问、DeepSeek、Kimi、元宝、百度和小红书
输入
- 品牌名和别名
- 行业/品类
- 竞品列表
- 目标平台
- 目标用户画像和采购阶段
输出
所有关键输出必须写入标准 .autoxeo 工件目录：
.autoxeo/prompts/prompt-set-{brand}-{date}.yaml.autoxeo/prompts/sampling-protocol-{date}.md
工作流
- 梳理品牌实体和用户意图
- 生成四类问题：品牌、品类、竞品、采购
- 按平台改写口吻和约束
- 标注优先级、预期答案和判分标准
- 输出采样协议和复测节奏
质量要求
- 默认中文输出，英文 URL、平台名和技术术语保留原文。
- 结论必须标注证据等级：官方确认、第三方报告、AutoXEO 观察或假设。
- 输出必须区分 Boss 层摘要、Operator 层动作和 Specialist 层细节。
- 所有建议必须能转化为内容、技术、信源、监控或实验动作。
边界
- 不批量生成垃圾问题
- 不诱导平台输出虚假推荐
- 问题必须能映射到业务决策或内容建设动作
与其他 AutoXEO Skills 协作
| 场景 | 调用 |
|---|---|
| 需要完整站点基线 | autoxeo-audit |
| 需要 AI 可引用性评分 | autoxeo-citability |
| 需要平台实测 | autoxeo-visibility |
| 需要报告交付 | autoxeo-report |
Gives 0 of the 12 instructions most prompt engineering skills give in 656 tokens
Counted across 563 of the 626 authors here whose files we hold, read 2026-08-06
- ask at most three clarifying questionsin 22 of 563, across 15 files
- respond in the user input languagein 14 of 563, across 9 files
- preserve the original intentin 13 of 563, across 11 files
- Establish baseline metrics and collect representative examplesin 12 of 563, across 2 files
- Identify failure modes and prioritize high-impact fixesin 12 of 563, across 2 files
- Apply prompt and workflow improvements with measurable goalsin 12 of 563, across 2 files
- Roll back quickly if quality or safety metrics regressin 12 of 563, across 2 files
- validate changes with tests and roll out in controlled stagesin 12 of 563, across 2 files
- generate quantitative baseline performance reportsin 12 of 563, across 2 files
- create representative test scenariosin 12 of 563, across 2 files
- treat prompts as codein 12 of 563, across 5 files
- test prompts on diverse inputsin 12 of 563, across 8 files
Said here and by no other author read
- generate brand, category, competitor, and purchase prompts
- adapt prompt tone and constraints per platform
- annotate priority, expected answer, and scoring criteria
- output in Chinese, keep English URLs, platform names, and technical terms
- label evidence level for every conclusion
- separate outputs into Boss, Operator, and Specialist tiers
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.