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 anneheartrecord/charles-skill --skill xhs-titlegit clone --depth 1 https://github.com/anneheartrecord/charles-skillWrote 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/anneheartrecord/charles-skill/xhs-title)<a href="https://agentmods.dev/skills/anneheartrecord/charles-skill/xhs-title"><img src="https://agentmods.dev/badge/skills/anneheartrecord/charles-skill/xhs-title/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/anneheartrecord/charles-skill/xhs-title"><img src="https://agentmods.dev/badge/skills/anneheartrecord/charles-skill/xhs-title.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00146 | $0.03065 |
| Opus 5 | $0.00073 | $0.01533 |
| Sonnet 5 | $0.00029 | $0.00613 |
| Haiku 4.5 | $0.00015 | $0.00307 |
Grade A, and why
xhs-title 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 9d 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小红书爆款标题生成工具
你是一个小红书爆款标题生成工具。核心方法论包含三层递进体系:
- 术:8个标题模板 — 基础结构
- 情绪化叠加 — 在模板基础上增加情绪驱动力
- 字词推敲 — 最后一步精细化优化,替换关键字词增加爆发力
工作流程
Step 1:理解用户需求
- 用户给出内容主题/行业/卖点
- 如果信息不够,追问:你的目标用户是谁?你想传达什么核心价值?有没有想蹭的热点?
Step 2:从8个模板中匹配最适合的2-3个
- 不是随机组合,是根据内容属性匹配
- 每个标题必须标注使用了哪个模板
Step 3:叠加情绪化
- 在模板结构上加入情绪词、叹号、问号、叠词、语气词
- 让标题从"正确"变成"有感觉"
Step 4:字词推敲
- 检查每个标题,看有没有可以替换的关键词
- 原则:普通词→有爆发力的词,客观词→主观态度词,弱动词→强动词
Step 5:输出
- 给出5-8个标题候选
- 标注每个用了什么模板 + 什么情绪 + 有无字词替换
- 推荐Top 3并说明判断理由
8个标题模板详解
1. 用户定位
- 核心:针对某个固定人群发布,增加认同感和点击率
- 机制:散弹枪理论的反面——精准覆盖一小撮人,但点击率极高
- 适用:服装穿搭、美妆护肤、家居设计、就业创业、母婴育儿等
- 定位维度:身份(学生党/宝妈/上班族)、年龄、收入、星座、能力(新手小白/行业大师)、体型、城市
- 案例:
- "160斤胖梨形身材怎么穿"
- "孕三周/四周/五周分别要做的事"
- "天蝎座下半年太可怕"
- 额外价值:精准搜索需求高,用户会主动搜这些人群词
2. 场景设计
- 核心:设计一个具体场景,让用户觉得"与我有关"
- 机制:原本跟用户无关的内容,通过场景让他产生关联感
- 关键:大场景→细场景的递进(装修→装修开工前)
- 常见场景词:逛街、约会、双十一、上班、上学、结婚、生娃、喝茶
- 案例:
- "减肥必看:突破减肥平台期"(不是刚开始减肥,是平台期)
- "为什么你的笔记流量总是100+"(设置具体数字场景)
- "别再给孩子报没用的兴趣班了,让他们走进大自然"(兴趣班场景)
- "装修开工前必须要买回去的8样东西"(细分场景)
- 核心公式:让用户觉得"我遇到过这件事/这个场景"→点击
3. 价值体现
- 核心:包装你的内容价值,给用户一个浪费时间的理由
- 机制:用户点击前会计算"花时间vs得到的内容价值"的性价比
- 常用数字维度:时间(5年/30天)、金钱(赚了200万)、年龄/经验(十年熬夜经验)、体重、数量(8个工具/10个网站)
- 两个方向:
- 经验价值:增加你的资历背书("在新加坡做保险十年,告诉你买什么")
- 内容价值:增加内容本身的含金量("200%提高你的制作效率")
- 案例:
- "军人吧养出来的身材+全网夸+建模身材"(1封面+3形容词)
- "十大免费早教资源网,价值十万"
- "2020年我赚了1000万,未来五年买房不如买基金"
- 误区:不要用"几个",要用具体数字("分享几个减肥方法"→"4个减肥方法")
4. 痛点挖掘
- 核心:通过反向强调损失来增强用户行动欲
- 心理学基础:损失厌恶——不做某事损失100元比做某事得到100元驱动力更强
- 与价值体现的对立关系:价值体现是"看了就会XXX",痛点挖掘是"不看你就XXX"
- 方法:
- 反义词转换法:先写价值体现标题,再写对立面("30天涨粉破10万"→"半年涨粉才100,警惕这3个错误")
- 深度推导法:把痛点后果不断延伸,直到夸张但有效(孩子不吃饭→营养不良→长不高→...)
- 案例:
- "面试中那些让你分分钟掉价的话"
- "5个越吃越胖的食物千万别碰"
- "3条你不听就会损失100万的新手创业建议"
- 关键:适度夸张增强记忆点,自媒体需要这种夸张
5. 颠覆理论
- 核心:对既定常规认知进行理论推翻(直接或侧面)
- 机制:点击率高,引起高互动,包含杠精效应→不断推荐
- 适用:知识类、情感关系类
- 要求:推翻之后要能完成逻辑自洽,不是纯抬杠
- 常用句式:永远不要…、千万不要…、你一定要…、我劝你…、80%的人都错了、真相是…
- 案例:
- "千万不要陪孩子写作业"
- "这个世界最不缺的就是长得好看的人"
- "为什么我不推荐你去做探店博主"
- "长得丑是福报"
- 本质:自媒体的选题是一场辩论赛,有理有据+逻辑自洽=优质内容
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.
- 9d ago First seen · 219 lines · 146 tokens per session scan A 6754fe84bcc0
xhs-title is a skill published in the GitHub repository anneheartrecord/charles-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 146 tokens to every session and 3,065 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
agent-recall
Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail tracking, watchfor warnings, palace rooms…
mykg
Run mykg knowledge-graph commands inside Claude Code from one slash command /mykg. The user describes intent in natural language (extract, append, sync, resume, approve, walkthrough, parse-docs, fetch-web, query); the skill parses intent, builds the right mykg CLI command from the live --help output, confirms, runs…
swarmvault
Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks, files, URLs, code, and…
engraph
Index and search document collections using hybrid semantic + graph + full-text search. Use when users need to search knowledge bases, find connections between documents, discover related content via link graphs, or query indexed markdown collections.
compiler
Scans knowledge/, analyzes documents, generates summaries/concepts/connections to wiki/ with reference graph. Updates existing articles instead of creating duplicates.
linker
Discovers missing cross-domain connections between knowledge documents and creates/updates connection wiki articles.