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 mingli30119/stock-analysis --skill stock-analysisgit clone --depth 1 https://github.com/mingli30119/stock-analysisWrote 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/mingli30119/stock-analysis/stock-analysis)<a href="https://agentmods.dev/skills/mingli30119/stock-analysis/stock-analysis"><img src="https://agentmods.dev/badge/skills/mingli30119/stock-analysis/stock-analysis/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/mingli30119/stock-analysis/stock-analysis"><img src="https://agentmods.dev/badge/skills/mingli30119/stock-analysis/stock-analysis.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 | $0.00091 | $0.17450 |
| Opus 5 | $0.00046 | $0.08725 |
| Sonnet 5 | $0.00018 | $0.03490 |
| Haiku 4.5 | $0.00009 | $0.01745 |
Grade A, and why
stock-analysis-enhanced 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 — 1,152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
一句话搞定个股分析
版本:v3.1 | 更新:2026-05-30 | 用户说一句话 → 30+数据源采集 → Step 0-8 基本面 + 第9章技术面 + 资金面 → 双主题交互式HTML
📋 快速导航
- ⚡ 使用方式 — 一句话触发,全自动执行
- 🏗️ 三层架构 — Phase 1 数据采集 → Phase 2 AI分析 → Phase 3 HTML
- 📊 输出内容 — MD 报告 + HTML 报告的完整结构
- 🎨 HTML手写规范 — 分批手写 + grep 机械校验
- 🔧 执行流程 — Phase 1/2/3 详细步骤
- 🔄 增量更新详细说明 — 脚本自动 + AI 手动
⚡ 使用方式
场景判断
AI必须根据用户输入的关键词判断场景:
场景A:首次分析(完整流程)
触发关键词:
- "分析 XXX股票"
- "个股分析 XXX"
- "研究 XXX"
- "生成 XXX报告"
- 用户明确说"首次分析"
判断逻辑:
- 用户输入包含上述关键词 → 执行首次分析(Phase 1→2→3)
场景B:增量更新(只更新数据)
触发关键词:
- "更新 XXX股票"
- "刷新 XXX报告"
- "增量更新 XXX"
- "更新报告"
- 用户明确说"更新"
判断逻辑:
- 用户输入包含上述关键词
- 检查
output/个股研究-{股票名称}.html是否存在 - 如果存在 → 执行增量更新
- 如果不存在 → 提示用户:"未找到 XXX 的报告,是否需要首次分析?"
场景A:首次分析
当用户说"分析 XXX股票"时,一句话触发全流程:
Phase 1: 数据采集(3-5分钟)
cd G:/vibe/my-skills/stock-analysis-enhanced
python stock_full_report.py <股票代码>
示例:
python stock_full_report.py 600519 # 贵州茅台
python stock_full_report.py 600673 # 东阳光
唯一输出: output/data_<股票代码>.json(包含K线、财务、股东、业务构成等完整数据,供Phase 2/3使用)
⚠️ Phase 1完成后立即进入Phase 2,不要停下来询问用户。JSON只是数据中间产物。
⚠️ Phase 1 新增功能: 自动计算技术指标(MACD/KDJ/RSI/BOLL/MA),保存到 data_{代码}.json 的 technical_indicators 和 technical_signals 字段,供 Phase 3 生成第9章使用。
场景B:增量更新
执行命令:
cd G:/vibe/my-skills/stock-analysis-enhanced副本
python update_stock_report.py <股票代码>
常用参数:
# 基本用法(自动查找HTML文件)
python update_stock_report.py 000066
# 指定HTML文件
python update_stock_report.py 000066 --html output/个股研究-中国长城.html
# 强制更新(跳过检查,直接更新)
python update_stock_report.py 000066 --force
更新内容:
- ✅ K线数据(rawData数组)
- ✅ Hero区域(最新价、涨跌幅)
- ✅ 第9章技术指标(MACD/KDJ/RSI/BOLL图表)
- ❌ 基本面分析(Step 0-8,不更新)
详细说明: 见本文件末尾"🔄 增量更新详细说明"章节
Phase 2: AI深度分析(30-60分钟)
AI必须手动执行以下步骤:
- 读取数据:
output/data_<股票代码>.json - 执行MCP搜索: 根据实际需要搜索(通常3-6次)
- 行业趋势、市场规模
- 竞争对手、市场份额
- 券商研报、目标价
- 最新新闻、政策动态
- 逐步完成Step 0-8分析: 严格按照分析框架,每个Step达到要求
- 输出MD报告:
output/个股研究-<股票名称>.md
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 · 1,152 lines · 91 tokens per session scan A a630ebcd47c9
stock-analysis-enhanced is a skill published in the GitHub repository mingli30119/stock-analysis (621 stars, last pushed 3mo ago), licensed MIT. It adds 91 tokens to every session and 17,450 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
sn-search-finance
A finance research tool for looking up stocks, indexes, funds, financial statements, market prices, charts over time, company filings, and financial news across global, Hong Kong, and Chinese markets.
sn-search-year-report
A workflow for finding free official annual reports and periodic filings from public companies and bond issuers.
augur-aschenbrenner
Leopold Aschenbrenner AI — AGI infrastructure + geopolitics, AI/semiconductor supply chains.
augur-dalio
Ray Dalio AI — macro / all-weather portfolio, debt cycles.
augur-lynch
Peter Lynch AI — GARP / PEG, consumer growth, everyday observations.
augur-serenity
Serenity AI — AI/semiconductor supply chain bottlenecks, chokepoint assets.