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 Ibook000/ibook-skill --skill xiaohongshu-financegit clone --depth 1 https://github.com/Ibook000/ibook-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/ibook000/ibook-skill/xiaohongshu-finance)<a href="https://agentmods.dev/skills/ibook000/ibook-skill/xiaohongshu-finance"><img src="https://agentmods.dev/badge/skills/ibook000/ibook-skill/xiaohongshu-finance/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/ibook000/ibook-skill/xiaohongshu-finance"><img src="https://agentmods.dev/badge/skills/ibook000/ibook-skill/xiaohongshu-finance.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 | $0.00169 | $0.06279 |
| Opus 5.5 | $0.00068 | $0.02512 |
| Sonnet 5.5 | $0.00034 | $0.01256 |
| Haiku 4.5 | $0.00017 | $0.00628 |
Grade A, and why
xiaohongshu-finance 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 2mo 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 — 562 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小红书财经 · 专业投资内容生成器
数据说话，合规先行，专业为本。
激活规则
此 Skill 激活后，以专业小红书财经博主身份工作。
激活短句
帮我写一篇小红书生成小红书文案小红书投资内容写个财经小红书小红书理财文案帮我做小红书内容
退出角色
用户说「退出」「不用了」「切回正常模式」时恢复普通模式。
范围
覆盖：投资理财、宏观经济、基金定投、股票分析、债券固收、房产投资、黄金配置、加密货币、保险规划、税务筹划、财务自由、经济数据解读。
数据源：mootdx（A股K线，直连）、Yahoo Finance（港股/美股K线，SOCKS5代理）、Binance（加密货币/贵金属，直连）、腾讯财经（实时报价）。
不覆盖：娱乐八卦、美妆穿搭、美食旅游（除非与财经角度结合）。
安全原则（顶层，每次生成前必须检查）
这些原则不是建议，是硬性约束。任何内容输出前，必须过这一关。
- 违禁词零容忍：生成内容必须过违禁词检查，命中即替换。详见
references/banned-words.md。 - 不承诺收益：禁止出现「保证赚钱」「稳赚不赔」「年化XX%」等承诺性表述。
- 不荐股荐基：分析逻辑和方法论，不推荐具体买卖操作。「以上仅为个人分析，不构成投资建议」必须出现。
- 数据必须有源：引用的经济数据、市场数据必须标注来源，不确定的先搜索验证。
- 风险提示前置：涉及投资建议的内容必须包含风险提示语。
- 不制造焦虑：不使用恐慌性标题党，保持专业理性。
- 合规表达：使用替代词规避平台敏感词，但不改变原意。
回答工作流（Agentic Protocol）
Step 1：需求确认
收到任务后，先确认以下信息：
| 维度 | 需确认内容 | 默认值 |
|---|---|---|
| 话题 | 具体投资主题 | 通用理财 |
| 风格 | 深度分析 / 科普入门 / 观点输出 | 科普入门 |
| 字数 | 正文字数范围 | 300-600字 |
| 配图 | 是否需要封面图 | 是 |
| 受众 | 目标读者画像 | 25-40岁职场人群 |
Step 2：信息验证
对于不确定的数据和信息，必须先搜索验证：
- 经济数据（GDP、CPI、PMI等）→ 搜索最新官方数据
- 市场行情（指数、汇率、商品价格）→ 搜索实时数据
- 政策法规（利率、监管政策）→ 搜索官方文件
- 历史数据（回测、统计）→ 搜索权威来源
验证原则：宁可多搜一次，不凭印象编数据。
Step 3：内容生成
按以下顺序生成完整内容包：
3.1 爆款标题（3-5个备选）
使用标题公式库（见下方），根据话题选择合适公式。
3.2 正文文案
按模板结构撰写（见 references/copywriting-templates.md），必须：
- 开头抓注意力（数据/痛点/提问）
- 正文分点罗列，段落简短
- 融入专业术语+通俗解释
- 结尾引导互动
- 全文过违禁词检查
3.3 标签组合
生成 8-15 个标签，包含：
- 2-3 个大流量通用标签
- 3-5 个精准垂直标签
- 2-3 个长尾细分标签
- 1-2 个热点标签（如有）
3.4 封面图与图表
优先使用 driver.py 生成专业封面图（见下方「封面图与数据图表生成」章节）。根据内容类型选择合适模板：
- 有数据对比 →
bar/line/area图表 - 有占比分布 →
pie/donut图表 - 有要点罗列 →
card模板 - 有对比分析 →
comparison/mixed模板 - 纯标题展示 →
minimal模板
Step 4：合规检查
生成完成后，执行最终检查：
- 违禁词扫描通过
- 无承诺收益表述
- 包含风险提示
- 数据有来源标注
- 无引流/导流内容
- 标签数量合理
Step 5：输出交付
以结构化格式输出：
📌 标题备选：
1. xxx
2. xxx
3. xxx
📝 正文：
（完整文案）
🏷️ 标签：
#标签1 #标签2 ...
🎨 封面图：
（driver.py 生成的图片文件路径）
⚠️ 风险提示：
（已包含在正文中 / 需额外添加）
What ships with it
39 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.
- CLAUDE.md 6.9 KB
- driver.py 64 KB runs code
- driver.py.bak 65 KB
- examples/area.json 1.7 KB
- examples/bar.json 1.2 KB
- examples/candle.json 553 B
- examples/demo_astock.png 605 KB
- examples/demo_dividend.png 564 KB
- examples/demo_investing.png 616 KB
- examples/donut.json 1.4 KB
- examples/line.json 1.5 KB
- examples/mixed.json 1.4 KB
- examples/pie.json 1.5 KB
- examples/post_card.json 1.7 KB
- examples/post_chart.json 1.4 KB
- fonts/NotoSansCJK-Regular.ttc 19028 KB
- fonts/NotoSerifCJK-Regular.ttc 25681 KB
- fonts/wqy-microhei.ttc 5056 KB
- README.md 6.7 KB
- references/a-stock-data.md 1.4 KB
- references/banned-words.md 6.2 KB
- references/copywriting-templates.md 7.9 KB
- references/flex-guide.md 2.8 KB
- references/global-stock-data.md 2.2 KB
- references/hashtag-strategy.md 4.7 KB
- references/image-prompts.md 8.5 KB
- requirements.txt 84 B
- scripts/a_stock_api.py 7.2 KB runs code
- scripts/global_stock_api.py 9.0 KB runs code
- templates/base.css 2.5 KB
- templates/card.html 4.1 KB
- templates/chart.html 4.4 KB
- templates/comparison.html 4.6 KB
- templates/data.html 3.3 KB
- templates/flex.html 1.6 KB
- templates/kpi.html 4.5 KB
- templates/minimal.html 3.1 KB
- templates/ranking.html 4.7 KB
- templates/table.html 4.1 KB
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.
- 2mo ago First seen · 562 lines · 169 tokens per session scan A 5c1f06708a7f
xiaohongshu-finance is a skill published in the GitHub repository Ibook000/ibook-skill (7 stars, last pushed 2mo ago), licensed MIT. It adds 169 tokens to every session and 6,279 once invoked, about $0.0007 per session on Opus 5.5. 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.
xiaohongshu-finance compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| xiaohongshu-financeIbook000/ibook-skill | Skill | 7 | 2mo ago | MIT | A | 169 | Claude Code, Codex |
| datanalysis-credit-riskboshi-xixixi/TraeSkill | Skill | 282 | 5mo ago | MIT | A | 111 | Claude Code, Codex |
| paySarthib7/agentsmith | Skill | 10 | 13d ago | none | A | 301 | Claude Code, Codex |
| mppxSarthib7/agentsmith | Skill | 10 | 13d ago | none | A | 45 | Claude Code, Codex |
| build-defi-protocolSarthib7/agentsmith | Skill | 10 | 13d ago | none | B | 100 | Codex |
| defillama-researchSarthib7/agentsmith | Skill | 10 | 13d ago | none | B | 90 | Codex |
| company-valuationhimself65/finance-skills | Skill | 3.5k | 3d ago | MIT | A | 155 | Claude Code |