Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add majiayu000/spellbook --skill xiaohongshu-netfeel-guardiangit clone --depth 1 https://github.com/majiayu000/spellbookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/majiayu000/spellbook/xiaohongshu-netfeel-guardian)<a href="https://agentmods.dev/skills/majiayu000/spellbook/xiaohongshu-netfeel-guardian"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/xiaohongshu-netfeel-guardian/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/majiayu000/spellbook/xiaohongshu-netfeel-guardian"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/xiaohongshu-netfeel-guardian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00189 | $0.02067 |
| Opus 5 | $0.00095 | $0.01033 |
| Sonnet 5 | $0.00038 | $0.00413 |
| Haiku 4.5 | $0.00019 | $0.00207 |
Grade A, and why
xiaohongshu-netfeel-guardian scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小红书/内容网感守护者
帮助个人内容创作者对抗 Claude 常见的“英文思考”污染，输出真正有情绪、有网感的中文内容。
核心问题（PAIN-301 实证）
Claude 在复杂内容生成任务中容易回退到英文思维链，导致：
- 句式僵硬（“亲爱的朋友们，你们能理解这种感受吗”）
- 文化框架西化（美剧梗、In conclusion、西方线性逻辑）
- 情绪稀释
- 长内容中途失效概率大幅上升
社区共识：Claude 适合做框架，网感需要额外守护。
触发场景（真实用户原话）
当用户说以下任意一句话时，立即激活本技能：
- “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”
- “写着写着就变成外国人假装写中文了”
- “前800字还行，后800字直接In conclusion”
完整工作流程（强制中文思维链 + 检测 + 重写）
第一阶段：强制纯中文思维链（最关键防御）
在开始任何规划、结构、举例前，必须先输出一段完整中文内部独白：
- “我现在是拥有10万+粉丝的资深小红书/公众号博主，正在用中文大脑回忆自己真实的亲身经历、尴尬瞬间、读者会共鸣的细节。”
- 用中文写出：这个选题最打动我的真实时刻是什么？读者最痛的点是？情绪曲线如何？会用什么口头禅表达？
严禁在这一步使用英文思考再翻译。
第二阶段：生成初稿后立即进行英文泄露检测
逐段扫描以下翻译腔标志（硬指标 + 文化框架）：
- 硬翻译句式：“亲爱的朋友们，你们能理解这种感受吗？” “姐妹们/兄弟们谁懂啊”的生硬版 “这个东西也太XX了！”
- 西方框架：“In conclusion / Furthermore / It is important to note / We should consider”
- 文化错位：美剧梗、好莱坞叙事、个人主义英雄故事、线性“问题-解决方案-结论”
- 节奏问题：所有句子长度几乎一致、缺少真实“翻车/心动/后悔”第一人称细节
检测结果必须输出：泄露片段标注 + 严重程度。
第三阶段：网感重写（注入真实语料）
针对检测到的每个问题段落：
- 强制用中文脑重写：“回忆你自己作为博主的真实时刻，用口语 + 情绪 + 短句 + 停顿感重写这一段”
- 注入
references/真实高赞网感示例.md中的真实高互动表达（“绝绝子”“泪目”“yyds”“姐妹们冲就完事儿了”） - 按平台适配（见
references/平台网感适配器.md详细规则）
第四阶段：多版本 + 最终自检
输出 2-3 个不同情绪强度的版本（保守 / 标准 / 情绪拉满）。 最后再跑一遍检测清单，输出：
- 网感评分（1-10）
- 剩余泄露片段
- 改动对照表（Before → After + 为什么这样改更像真人）
第五阶段（可选但推荐）：生成持久化守护片段
如果用户频繁使用，自动生成一段“反英文思考系统提示”，建议用户粘贴到 CLAUDE.md 最前面。
推荐的“中文网感守护协议 v1.0”
完整可复制协议 见 references/中文网感守护协议.md。
强烈建议：所有写作类 Skill（包括你自己写的）都在“写文案”步骤之前引用本协议。
平台具体语气差异和适配 Prompt 模板见 references/平台网感适配器.md。
最强组合工作流（实测最有效）
- 先调用
xiaohongshu技能 → 拿框架 + 平台硬约束 + 7-3原则 + 真实数据 - 把 xiaohongshu 的输出喂给本技能做“强制中文 CoT + 翻译腔全量清洗 + 真实网感注入”
- 可选再接
humanizer做最后一层去 AI 味打磨（24模式自审计）
这条链路把“Claude 框架能力” + “中文网感” + “去AI味”三者正交组合，实测效果远好于单独使用任何一个。
安全契约（Safety Contract，绝不违反）
- 只改语言和文化表达，绝不改变用户原本想表达的核心观点、结构、数据
- 永远尊重 用户在 CLAUDE.md / AGENTS.md 里设定的人设、语气、禁忌词
- 提供多个版本供用户选择，而不是强行替换原稿
- 所有修改必须给出可追溯的改动对照 + 改动理由
- 发现用户原稿本身就有极强网感时，优先输出“你的原稿网感已经很好了，以下是微调建议”，绝不过度润色
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 127 lines · 189 tokens per session scan A 026b74b97866
xiaohongshu-netfeel-guardian is a skill published in the GitHub repository majiayu000/spellbook (278 stars, last pushed yesterday), licensed MIT. It adds 189 tokens to every session and 2,067 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
pneuma-session
Instructions for renaming an active Pneuma session and replacing its default preview with a useful title and summary. A Pneuma session is one work area inside a larger project.
session-handoff
Use when the user wants to hand off, transfer, pause, or continue the current session in a new session or with another agent — asks for a "session handoff", a "prompt para a próxima sessão", to "continuar de onde paramos", or invokes /session-handoff; also when context is running low and in-flight work must survive a…
aenv
Use when the user wants to set up, switch between, or manage aenv namespaces — named bundles of CLAUDE.md, skills, MCP entries, and other AI-coding-harness config — in a project OR globally across $HOME. Triggers include aenv … mentioned directly, "switch namespace/profile", "activate/deactivate", "create/snapshot a…
cao-session-management
Interact with CAO (CLI Agent Orchestrator) — launch multi-agent sessions, check status, send follow-up instructions, unblock stuck terminals, or shut down sessions. Use when working with CAO sessions in any capacity.
mulmoterminal-keys
Bind keyboard shortcuts and fix keyboard/clipboard behaviour in MulmoTerminal. Writes keymap, which Settings cannot set at all — its Keyboard shortcuts section is read-only, listing every action bound or not plus a send row. Explains copyOnSelect, questionPaneEnabled and terminalSubmit, which have their own Settings…
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.