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 lj22503/awesome-finai-tools-zn --skill awesome-finai-tools-zngit clone --depth 1 https://github.com/lj22503/awesome-finai-tools-znWrote 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/lj22503/awesome-finai-tools-zn/awesome-finai-tools-zn)<a href="https://agentmods.dev/skills/lj22503/awesome-finai-tools-zn/awesome-finai-tools-zn"><img src="https://agentmods.dev/badge/skills/lj22503/awesome-finai-tools-zn/awesome-finai-tools-zn/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/lj22503/awesome-finai-tools-zn/awesome-finai-tools-zn"><img src="https://agentmods.dev/badge/skills/lj22503/awesome-finai-tools-zn/awesome-finai-tools-zn.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 | $0.00063 | $0.04457 |
| Opus 5.5 | $0.00025 | $0.01783 |
| Sonnet 5.5 | $0.00013 | $0.00891 |
| Haiku 4.5 | $0.00006 | $0.00446 |
Grade A, and why
finai-tools-hub 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.
How it starts
The opening of the file, as written. The whole thing — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.
命名说明：本仓库 GitHub 名
awesome-finai-tools-zn，Anthropic Skill 内部标识名为finai-tools-hub（SKILL.md frontmattername）。两者不同是按 Anthropic Skills 规范的有意设计——仓库名是 GitHub 标识，Skill 内部名是 agent 加载时的 unique identifier。
FinAI Tools Hub — Agent Skill
使用方法
- 用户提出金融需求 → 2. 从下方分类找到对应工具 → 3. 按安装命令安装 → 4. 按输入/输出格式调用
工具分类索引
用户需求 → 工具推荐映射
| 用户需求 | 推荐工具 | 理由 |
|---|---|---|
| 查A股实时行情（零配置） | opencli-eastmoney-quote |
秒出结果，无需任何安装确认 |
| 看今日主力资金流向 | opencli-eastmoney-money-flow |
今日/5日/10日排行 |
| 查板块涨跌/资金 | opencli-eastmoney-sectors |
行业/概念/地域 |
| 看北向资金 | opencli-eastmoney-northbound |
逐分钟数据 |
| 查龙虎榜 | opencli-eastmoney-longhu |
营业部/机构席位 |
| 看散户关注度 | opencli-eastmoney-hot-rank |
人气排行 |
| 搜股票代码/名称 | opencli-xueqiu-search |
中文/代码均可 |
| 看社区舆情/热帖 | opencli-xueqiu-hot |
雪球热门帖子 |
| 获取多维度A股数据 | ashare-mcp 或 stock-data-mcp |
30~43个tool，MCP协议 |
| 免费历史K线 | baostock |
1990年至今，零配置 |
| 多数据源聚合行情 | akshare |
东方财富/新浪/腾讯 |
| 高质量财务数据 | tushare |
需注册（免费有积分） |
| Alpha因子计算 | finance-mcp-alpha |
WorldQuant 101因子 |
| 量化策略回测 | qtrade 或 qlib |
15种策略/微软框架 |
| 多Agent投研分析 | tradingagents |
基本面+舆情+技术面团队 |
| 强化学习量化 | finrl |
DDPG/PPO/SAC |
| 机构级最全数据 | wind |
昂贵但最全 |
| 实时A股（最完整MCP） | ashare-mcp |
30 tool，生产级 |
| 免 Key 查 A股行情（MCP） | mcp-eastmoney |
东方财富公开延时接口，uvx 即用 |
| A股盘后复盘/涨停梯队 | wudao-mcp |
63 工具远程 MCP，需 API Key |
| A股财报/估值/宏观（MCP） | cn-financial-mcp |
42 工具，Apache-2.0 可自建 |
| akshare 数据 MCP 封装 | akshare-one-mcp |
Smithery / uvx 一键安装 |
| 多源行情本地入库 | AxData |
Python SDK + CLI + 本地 API |
| 同花顺官方数据接口 | hithink-financial-api |
官方 API / MCP / CLI / Python |
| 本机 Level-2 行情插件 | fqgate-agent |
同花顺非官方，Windows 插件 |
| 自动挖掘 Alpha 因子 | quantaalpha |
LLM + 进化策略自动演化 |
| WorldQuant BRAIN 因子 | quantgpt |
Agent 自动设计并回测提交 |
| 量化 MCP 工具集线器 | tradex-hub |
129 个 MCP 工具聚合 |
| 金融 Agent Skills 合集 | awesome-finance-skills |
npx skills add 一键安装 |
| A股多智能体投研（中文） | tradingagents-astock |
8 维数据源，输出买卖与仓位建议 |
| 威科夫量价结构信号 | wyckoff-trading-agent |
吸筹/派发阶段识别 |
| 价值投资公司研究 | ai-berkshire |
巴菲特/芒格框架多智能体 |
| 全网热点舆情监控 | trendradar |
多平台热榜聚合 + MCP |
| 个人持仓看板 | easy-stock |
非商业许可 |
What ships with it
24 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.
- data/candidate-review-2026-09-22.json 81 KB
- data/candidate-review-2026-09-22.md 48 KB
- data/institution-dynamics.json 4.7 KB
- data/institution-skills.json 42 KB
- data/pending-review.json 165 KB
- data/tools.json 65 KB
- data/weekly-report-2026-09-22.md 4.3 KB
- data/weekly-report-2026-09-28.md 4.4 KB
- data/weekly-report-2026-10-05.md 4.0 KB
- data/weekly-report-2026-10-12.md 4.4 KB
- data/weekly-report-2026-10-19.md 4.6 KB
- data/weekly-report-2026-10-26.md 4.6 KB
- data/weekly-report-china-2026-09-22.md 19 KB
- data/weekly-report-china-2026-09-28.md 18 KB
- data/weekly-report-china-2026-10-05.md 19 KB
- data/weekly-report-china-2026-10-12.md 17 KB
- data/weekly-report-china-2026-10-19.md 18 KB
- data/weekly-report-china-2026-10-26.md 19 KB
- scripts/add_institution.py 6.1 KB runs code
- scripts/fix_clawhub_links.py 5.1 KB runs code
- scripts/generate_readme.py 26 KB runs code
- scripts/review_candidates.py 19 KB runs code
- scripts/update_china_platforms.py 31 KB runs code
- scripts/update_tools.py 17 KB runs code
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 Changed · +16 lines b29122838730
- 1mo ago First seen · 402 lines · 63 tokens per session scan A c1e84895071f
finai-tools-hub is a skill published in the GitHub repository lj22503/awesome-finai-tools-zn (32 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 4,457 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
financial-expert
A financial research skill for China and Hong Kong securities, funds, company finances, economic indicators, research reports, announcements, news, and business-risk data. It returns data and neutral analysis rather than placing trades or recommending investments.
china-dcf-model
A documented discounted-cash-flow model for valuing non-financial A-share companies. A discounted-cash-flow model estimates today’s value from expected future cash flows and makes its assumptions, valuation date, and adjustments explicit.
national-team-position
A Chinese-language analysis tool that estimates changes in China’s government-backed ETF holdings by tracking ETF share counts and related index prices. ETFs are funds traded on stock exchanges, and the “national team” refers here to Central Huijin, a state investment company.
industry-etf-research
A research workflow for studying Chinese A-share industry ETFs and the indexes they track. It compares index rules, holdings, company fundamentals, industry conditions, valuations and market evidence.
pptx-author
Produce a .pptx file on disk for headless Chinese A-share market research, using python-pptx with Chinese font support. Use when no controllable Office session is available.
china-market-data
A routing and quality-check process for obtaining Chinese stock-market and company-financial data from sources such as Tushare Pro and AKShare.