wenziai/wenzi-xiaohongshu-workflow / xhs-account-profile
xhs-account-profile
VerifiedUse when the user wants an agent to remember an account's positioning, voice, boundaries, data, trust assets, personal IP story, and content rules across sessions. Trigger phrases: "账号档案", "记住我的账号", "写入记忆", "人设垂直", "信任名片", "brand profile", "account memory", "style guide". Do not use for one-off post drafting unless profile data is missing.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.0 KB |
| test-prompts.json | config | 3.6 KB |
test-prompts.json
View on GitHub{
"skill": "xhs-account-profile",
"version": "0.1.0",
"source_book": "别不信!WorkBuddy 就可以把你的小红书从0粉干到1000 — 文子 + yanliudreamer 小红书系列",
"darwin_compatible": true,
"test_cases": [
{
"id": "should-trigger-01",
"type": "should_trigger",
"prompt": "帮我建一个小红书账号档案,让 Agent 以后记住我的定位和语气。",
"expected_behavior": "应激活本 skill,收集字段并输出账号档案。",
"notes": "典型账号记忆场景。"
},
{
"id": "should-trigger-02",
"type": "should_trigger",
"prompt": "每次 AI 写出来都不像我,怎么让它记住我的风格?",
"expected_behavior": "应激活本 skill,建立语气规则、边界和示例。",
"notes": "风格长期记忆。"
},
{
"id": "should-trigger-03",
"type": "should_trigger",
"prompt": "Create an account memory file for my XHS brand profile.",
"expected_behavior": "应激活本 skill,生成 account profile and memory write instruction.",
"notes": "英文触发。"
},
{
"id": "should-trigger-04",
"type": "should_trigger",
"prompt": "我想做个人 IP,但内容里有职场、AI、旅行,帮我整理人设垂直和账号档案。",
"expected_behavior": "应激活本 skill,整理信任资产、主线话题、延展话题和小号边界。",
"notes": "融合后新增的人设垂直场景。"
},
{
"id": "should-not-trigger-01",
"type": "should_not_trigger",
"prompt": "帮我找 10 个低粉爆款对标。",
"expected_behavior": "不应激活本 skill,应激活 xhs-low-follower-pattern。",
"notes": "样本拆解场景。"
},
{
"id": "should-not-trigger-02",
"type": "should_not_trigger",
"prompt": "我想做小红书,但完全不知道怎么变现。",
"expected_behavior": "不应激活本 skill,应激活 xhs-monetization-backsolve。",
"notes": "兄弟 skill 混淆测试。"
},
{
"id": "edge-01",
"type": "edge_case",
"prompt": "帮我写简介:我是一个教 AI 的文科生。",
"expected_behavior": "若只是简介可直接写;若用户要长期记忆和内容边界,应激活本 skill。",
"notes": "单次简介与账号档案边界。"
},
{
"id": "edge-02",
"type": "edge_case",
"prompt": "我想发一篇旅行感悟,会不会影响我的职场号人设?",
"expected_behavior": "应激活本 skill 判断该话题是否能被账号主线接住,必要时建议放小号或改写角度。",
"notes": "人设延展边界判断。"
},
{
"id": "should-trigger-05",
"type": "should_trigger",
"prompt": "帮我补一个账号档案,重点记录我的真实语言样本、能证明的观点和不能承诺的边界。",
"expected_behavior": "应激活本 skill,补充个人语言样本、可信主张清单、证据、offer 和表达边界。",
"notes": "dbskill 文风诊断和可信主张模块补充场景。"
},
{
"id": "should-trigger-visual-01",
"type": "should_trigger",
"prompt": "帮我建账号档案时,也把我的小红书封面风格、配色、字体、内页组件和禁用视觉风格记下来。",
"expected_behavior": "应激活本 skill,在账号档案中加入视觉身份规则,包括画幅、主/辅助风格、色彩令牌、字体系统、封面规则和视觉反模式。",
"notes": "融合 xhs-visual-director 后的视觉身份档案场景。"
}
],
"minimum_pass_rate": 0.8
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |