majiayu000/spellbook / skills/xiaohongshu-netfeel-guardian
xiaohongshu-netfeel-guardian
Verified当用户用 Claude 写小红书、公众号、视频脚本等内容时,输出出现翻译腔、英文思考、西式框架,导致“像外国人假装写中文”时使用。 典型触发语句: - “Claude写小红书翻译腔太重”“英文思考输出灾难” - “帮我把这个笔记改成纯中文网感”“去除Claude翻译腔” - “公众号文章中途变英文了”“50 Skills内容生成翻车” - “强制Claude用中文思考写笔记”“小红书情绪化表达润色” 始终保护用户原有的 CLAUDE.md / AGENTS.md 中的人设与语气要求,只做最小必要干预。优先与 xiaohongshu 技能组合使用。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.1 KB |
| evals/evals.json | config | 2.6 KB |
| references/中文网感守护协议.md | markdown | 2.7 KB |
| references/平台网感适配器.md | markdown | 847 B |
| references/真实高赞网感示例.md | markdown | 724 B |
evals/evals.json
View on GitHub{
"skill_name": "xiaohongshu-netfeel-guardian",
"description": "测试该技能能否有效检测并修复 Claude 输出中的英文思考、翻译腔、西式框架,让内容更接近真实中文内容创作者的语气(尤其是小红书、公众号场景)。本技能为高度主观写作类,核心评估依赖人工盲测与真实发帖数据。",
"evals": [
{
"id": 1,
"name": "小红书种草笔记翻译腔重写(典型 PAIN-301 案例)",
"prompt": "帮我把下面这篇小红书笔记改得更有网感:\n\n姐妹们,我最近用了一款新耳机,真的太震撼了!它不仅音质出色,而且佩戴舒适。强烈推荐给大家!",
"expected_behavior": "能明显减少翻译腔,注入真实种草情绪(“姐妹们谁懂啊”“绝绝子”“泪目”“后悔没早点入”),增加场景感和个人真实体验感,而不是生硬推荐。输出应包含检测报告 + 改动对照 + 多个情绪强度版本。",
"type": "subjective"
},
{
"id": 2,
"name": "公众号长文中途英文脑崩盘检测(长内容高危场景)",
"prompt": "下面这篇公众号文章写到后面突然很翻译,请帮我整体润色成更自然的中文:\n\n[用户会贴一篇中前半自然、后半突然出现 In conclusion, we should consider... 西方线性框架的 1500 字文章]",
"expected_behavior": "能识别中途英文思维框架(尤其是长内容后半段),进行一致的中文重写,保留用户核心观点和结构,只替换语言和文化框架。必须标注具体泄露片段。",
"type": "subjective"
},
{
"id": 3,
"name": "视频脚本口播感优化 + 停顿感注入",
"prompt": "这个视频脚本太书面了,帮我改得更适合口播,像真实博主在聊天:\n\n[用户贴 3-5 分钟脚本,当前版本全是完整长句、无停顿]",
"expected_behavior": "把书面/翻译体改成可自然朗读的口语,增加停顿感、重复强调、情绪起伏、真实人设细节(“大家好,我是XX,今天我又翻车了...”)。",
"type": "subjective"
},
{
"id": 4,
"name": "多 Agent 流水线污染后的网感恢复",
"prompt": "我用 xiaohongshu 技能先生成了框架和结构,现在输出有明显翻译腔和西方框架,帮我做最后网感守护。",
"expected_behavior": "能作为 xiaohongshu 的下游良好协作,针对已有结构做最小必要网感强化,不破坏原有平台约束和 7-3 原则。",
"type": "subjective"
}
]
}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 |