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 serejaris/kimi-skills --skill cn-finance-datagit clone --depth 1 https://github.com/serejaris/kimi-skillsWrote 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/serejaris/kimi-skills/cn-finance-data)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/cn-finance-data"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/cn-finance-data/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/serejaris/kimi-skills/cn-finance-data"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/cn-finance-data.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 | $0.00102 | $0.00802 |
| Opus 5.5 | $0.00041 | $0.00321 |
| Sonnet 5.5 | $0.00020 | $0.00160 |
| Haiku 4.5 | $0.00010 | $0.00080 |
Grade A, and why
cn-finance-data 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 1mo 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.
What it actually says
Tushare 金融数据 Skill
本 skill 通过 Tushare Pro API 获取中国金融市场数据，支持 220+ 个数据接口。
快速开始
1. Token 配置
询问用户：是否已配置 Tushare Token？
如未配置，引导用户：
- 访问 https://tushare.pro 注册
- 获取 Token
- 配置环境变量：
export TUSHARE_TOKEN="your_token"
2. 验证依赖
检查 Python 环境：
python -c "import tushare, pandas; print('OK')"
如报错，安装依赖：
pip install tushare pandas
常用接口速查
| 数据类型 | 接口方法 | 说明 |
|---|---|---|
| 股票列表 | pro.stock_basic() |
获取所有股票列表 |
| 日线行情 | pro.daily() |
获取日线行情数据 |
| 财务指标 | pro.fina_indicator() |
财务指标（ROE等） |
| 利润表 | pro.income() |
利润表数据 |
| 指数行情 | pro.index_daily() |
指数日线数据 |
| 基金净值 | pro.fund_nav() |
基金净值数据 |
| GDP数据 | pro.gdp() |
国内生产总值 |
| CPI数据 | pro.cpi() |
居民消费价格指数 |
完整接口列表：查看 接口文档索引
数据获取流程
- 查找接口：根据需求在 接口索引 找到对应接口
- 阅读文档：查看
reference/接口文档/[接口名].md了解参数 - 编写代码：
import tushare as ts # 初始化（使用环境变量中的 Token） pro = ts.pro_api() # 调用接口 df = pro.daily(ts_code='000001.SZ', start_date='20241201', end_date='20241231') - 返回结果：DataFrame 格式
参数格式说明
- 日期：YYYYMMDD（如 20241231）
- 股票代码：ts_code 格式（如 000001.SZ, 600000.SH）
- 返回格式：pandas DataFrame
接口文档参考
接口索引：reference/README.md
接口文档按类别组织：
- 股票数据（39 个接口）
- 指数数据（18 个接口）
- 基金数据（11 个接口）
- 期货期权（16 个接口）
- 宏观经济（10 个接口）
- 港股美股（23 个接口）
- 债券数据（16 个接口）
参考资源
- Tushare 官方文档：https://tushare.pro/document/2
- API 测试工具：https://tushare.pro/document/1
What ships with it
60 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.
- _meta.json 134 B
- metadata.json 819 B
- QUICK_REFERENCE.md 4.6 KB
- README.md 7.8 KB
- reference/all_links.json 36 KB
- reference/README.md 28 KB
- reference/接口文档/AH股比价.md 3.7 KB
- reference/接口文档/ETF份额规模.md 3.3 KB
- reference/接口文档/ETF分钟行情.md 3.2 KB
- reference/接口文档/ETF基准指数.md 2.4 KB
- reference/接口文档/ETF基本信息.md 6.1 KB
- reference/接口文档/ETF复权因子.md 2.5 KB
- reference/接口文档/ETF实时日线.md 3.4 KB
- reference/接口文档/ETF日线行情.md 2.9 KB
- reference/接口文档/Hibor利率.md 3.8 KB
- reference/接口文档/IPO新股上市.md 3.6 KB
- reference/接口文档/Libor利率.md 4.2 KB
- reference/接口文档/LPR贷款基础利率.md 2.8 KB
- reference/接口文档/Shibor利率.md 4.4 KB
- reference/接口文档/Shibor报价数据.md 5.5 KB
- reference/接口文档/ST股票列表.md 2.2 KB
- reference/接口文档/上市公司公告.md 3.0 KB
- reference/接口文档/上市公司基本信息.md 4.1 KB
- reference/接口文档/上市公司管理层.md 4.3 KB
- reference/接口文档/上海黄金基础信息.md 3.4 KB
- reference/接口文档/上海黄金现货日行情.md 3.7 KB
- reference/接口文档/上证e互动问答.md 5.3 KB
- reference/接口文档/业绩快报.md 4.5 KB
- reference/接口文档/业绩预告.md 4.3 KB
- reference/接口文档/东方财富App热榜.md 2.7 KB
- reference/接口文档/东方财富概念成分.md 2.1 KB
- reference/接口文档/东方财富概念板块.md 3.0 KB
- reference/接口文档/东财概念和行业指数行情.md 3.3 KB
- reference/接口文档/中信行业成分.md 5.3 KB
- reference/接口文档/中信行业指数日行情.md 2.8 KB
- reference/接口文档/中央结算系统持股明细.md 3.2 KB
- reference/接口文档/中央结算系统持股统计.md 3.0 KB
- reference/接口文档/主营业务构成.md 2.6 KB
- reference/接口文档/交易日历.md 3.4 KB
- reference/接口文档/仓单日报.md 4.1 KB
- reference/接口文档/债券回购日行情.md 5.4 KB
- reference/接口文档/做市借券交易汇总(停).md 2.5 KB
- reference/接口文档/全国电影剧本备案数据.md 1.8 KB
- reference/接口文档/全国电视剧备案公示数据.md 9.8 KB
- reference/接口文档/全球财经事件.md 4.3 KB
- reference/接口文档/分红送股数据.md 2.8 KB
- reference/接口文档/利润表.md 12 KB
- reference/接口文档/券商月度金股.md 1.7 KB
- reference/接口文档/券商盈利预测数据.md 4.1 KB
- reference/接口文档/前十大流通股东.md 2.9 KB
- reference/接口文档/前十大股东.md 3.0 KB
- reference/接口文档/北交所新旧代码对照.md 1.3 KB
- reference/接口文档/南华期货指数行情.md 6.5 KB
- reference/接口文档/历史Tick行情.md 2.1 KB
- reference/接口文档/历史分钟.md 3.2 KB
- reference/接口文档/历史分钟行情.md 3.7 KB
- reference/接口文档/历史日线.md 3.6 KB
- reference/接口文档/可转债发行.md 4.8 KB
- reference/接口文档/可转债基础信息.md 4.5 KB
- reference/接口文档/可转债技术面因子(专业版).md 11 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.
- 1mo ago First seen · 92 lines · 102 tokens per session scan A 796043ae8e98
cn-finance-data is a skill published in the GitHub repository serejaris/kimi-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 102 tokens to every session and 802 once invoked, about $0.0004 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.
Other skills, from other repositories
ai-product-canvas
Structure AI and ML product decisions with the rigour of any product decision. Use when building AI-powered features, evaluating LLM integrations, designing AI products, or assessing AI readiness. Produces a complete AI product canvas covering problem definition, model approach, data requirements, evaluation…
prompt-regression-suite
Design a regression test suite that catches an LLM feature getting worse when the prompt, model, or context changes. Use when asked to stop prompt changes breaking production, set up golden tests or CI gates for an LLM feature, or test a model/prompt upgrade before shipping it. Produces a golden case set, per-case…
ai-roi-audit
Audit whether the organisation's AI spend actually paid — measured against baselines, not vendor math or vibes. Use when a CFO asks what the AI tools returned, when renewing AI contracts, when consolidating overlapping AI subscriptions, or to build the measurement plan before the next spend. Produces an ROI audit with…
credit-memo
Write a credit memo for a lending decision: borrower story, facility structure, repayment sources, financial-ratio spread with covenant headroom, risk factors with mitigants, risk-rating rationale, and a recommendation. Use when asked to write a credit memo, credit application, credit paper, loan write-up, or prepare…
loan-covenant-review
Run a quarterly loan covenant compliance review: covenant table with required vs actual vs headroom, trend and trajectory-to-breach analysis, waiver and amendment options with pricing implications, early-warning indicators, and a watch-list recommendation. Use when asked to review covenant compliance, check covenant…
ai-context-primer
Build the context an AI needs to do a task well — the background, constraints, examples, and format it can't guess — so you get a great result on the first try instead of a generic one you have to keep correcting. Use when asked why does AI give me generic answers, how do I give AI better context, my AI results are…