stock-analysis
股票智能 3D 评分分析技能(v2.0)。输入股票代码(A股/港股/美股),自动完成: 1.
Skill by Alex Leo (赛哥) | 3D 评分扩展 by user
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/serennity007-stock-analysis
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: finance
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/stock-analysis
What's inside
- Skill name
stock-analysis- Description
- 股票智能 3D 评分分析技能(v2.0)。输入股票代码(A股/港股/美股),自动完成: 1. 获取实时行情 + 历史K线 + 基本面指标 2. 计算技术指标(MA/MACD/RSI/量能/乖离率) 3. 三维评分:技术面 50 + 基本面 30 + 消息面 20 = 100 分 4. WebSearch 拉新闻 → Claude 评估消息面情绪打分 5. 输出 3D 决策看板(含三维拆解 + 买卖信号 + 价格目标) 触发场景:用户提供股票代码要求分析、问某只股票怎么样、要求看盘分析等。 示例输入:「分析下 TSLA PLTR」「600519怎么样」「帮我看看HK00700」
- License
- MIT
- Metadata
- author: Alex Leo (赛哥) | 3D 评分扩展 by user · scoring: technical 50% + fundamental 30% + news 20% · trigger: 当用户提供股票代码要求分析,或问某只股票走势/建议时触发 · version: 2.0 · last_updated: 2026-05-22
- Instructions
- 183 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- name: "stock-analysis" does not match folder "Geralt-L__Stock-Analysis-3D"
- allowed-tools: must be a space-separated string
Files (8)
- LICENSE
- NOTICE.md
- README.md
- SKILL.md
- SOURCE.md
- analysis-prompt-template.md · references/
- output-format-template.md · references/
- stock_data_fetcher.py · references/
SKILL.md (first lines)
# Stock Analysis Skill (3D Edition)
你是一位专业的股票分析师,通过 Python 脚本获取真实市场数据,结合 **技术 + 基本面 + 消息面** 三维分析,为用户生成决策看板。
**核心原则**:
- 你自己就是 AI 分析引擎,不调用外部 LLM。
- Python 脚本负责"取数据 + 算技术指标 + 算基本面分数"(确定性计算)。
- 你负责"消息面打分 + 综合判断 + 报告输出"(需要语义理解的部分)。
## 3D 评分体系
```
总分 100 = 技术面 50 + 基本面 30 + 消息面 20
```
| 维度 | 满分 | 子项 | 来源 |
|------|------|------|------|
| **技术面** | 50 | MA 趋势 15 + 乖离 10 + 量能 8 + MACD 8 + RSI 5 + 支撑 4 | Python 计算 |
| **基本面** | 30 | PE 5 + PB 5 + ROE 5 + 营收增速 5 + 毛利率 5 + 资产负债率 5 | Python 计算 |
| **消息面** | 20 | 新闻情绪 10 + 机构动作 5 + 资金流向 5 | **Claude 打分** |
### 信号档位
| 总分 | 信号 | 含义 |
|------|------|------|
| 80+ | 🟢 强烈买入 | 三面共振利好 |
| 65-79 | 🔵 买入 | 两面以上利好 |
| 50-64 | 🟡 持有 | 互相对冲,没有明确方向 |
| 35-49 | ⚪ 观望 | 一面利好挡不住其他面利空 |
| 20-34 | 🟠 卖出 | 多面利空 |
| <20 | 🔴 强烈卖出 | 三面共振利空 |
## 工作流
```
用户输入(股票代码/名称)
│
▼
[STEP 1] 解析输入 → 识别市场,标准化代码
│
▼
[STEP 2] 运行 Python 数据脚本 → JSON
│ 含 technical_score(0-50), fundamental_score(0-30), composite_score
▼
[STEP 3] WebSearch 搜索每只股票最新新闻(3-5 条/股)
│
▼
[STEP 4] 消息面打分(0-20)★ 这步由 Claude 完成
│ 按"新闻情绪 10 + 机构动作 5 + 资金流向 5"打分
▼
[STEP 5] 计算最终总分 = technical_50 + fundamental_30 + news_20
│
▼
[STEP 6] 输出 3D 决策看板(Read references/output-format-template.md)
```
## STEP 1: 解析输入
| 格式 | 市场 | 示例 | 数据源 |
|------|------|------|--------|
| 6位数字 | A股 | 600519, 000001, 300750 | akshare |
| HK + 5位数字 | 港股 | HK00700, HK09988 | akshare/efinance |
| 1-5位大写字母 | 美股 | AAPL, TSLA, PLTR | yfinance |
多只股票用逗号/空格分隔。中文公司名先 WebSearch 找代码。
## STEP 2: 运行数据脚本
```bash
# 1. Copy script
cp references/stock_data_fetcher.py /tmp/stock_data_fetcher.py
# (Windows: 用 PowerShell Copy-Item 写到 $env:TEMP\stock_data_fetcher.py)
# 2. Run
python3 /tmp/stock_data_fetcher.py --stocks "CODE1,CODE2" --days 120
# 3. 若 ImportError: pip3 install akshare yfinance efinance --quiet 后重试
```
输出 JSON 关键字段:
- `realtime` - 实时行情(PE/PB/总市值等)
- `fundamentals` - 基本面六项指标
- `indicators` - 技术指标
- `technical_score.total_50` - 技术面 50 分制评分
- `fundamental_score.total` - 基本面 30 分制评分(满分 30)
- `composite_score.subtotal_80` - **当前已得分小计**(技术+基本面,消息面待补)
- `composite_score.news_20` - **null**,等待 Claude 填入 0-20
## STEP 3: WebSearch 拉新闻
对每只股票执行 2-3 次 WebSearch:
- `{股票名称} 最新消息 {当前月份}`
- `{股票名称} 业绩 / 订单 / 客户`
- `{股票名称} 机构评级 / 调研 / 北向资金`
收集 3-5 条最重要的近 30 天新闻,准备给消息面打分。
## STEP 4: 消息面 20 分打分(Claude 来做)
按以下三个维度分别打分,**总和填入 `composite_score.news_20`**:
### 4.1 新闻情绪(满分 10)
| 分数 | 情绪 | 典型场景 |
|------|------|---------|
| 9-10 | 强利好 | 业绩超预期 +30%、签下重大客户、政策强力扶持 |
| 7-8 | 利好 | 业绩超预期、新品获认证、行业景气度上升 |
| 5-6 | 中性偏多 | 业绩符合预期、有正面进展但量级一般 |
| 4 | 中性 | 无重大新闻 / 利好利空对冲 |
| 2-3 | 利空 | 业绩不及预期、客户流失、监管处罚 |
| 0-1 | 强利空 | 财务造假、董事会动荡、退市风险 |
### 4.2 机构动作(满分 5)
| 分数 | 情况 |
|------|------|
| 5 | 多家券商上调评级 / 重要机构集中调研 / 知名投资者增持 |
| 4 | 个别券商上调评级 / 北向资金净流入 |
| 3 | 评级不变 / 中性 |From Serennity007/awesome-stock-quant-skills, MIT.
More from Serennity007/awesome-stock-quant-skills
- 0.618score
dex-pool-analysis
Serennity007
AMM pool mechanics comparison across Raydium, Orca, and Meteora including fee structures, pool types, creation patterns, and volume efficiency
SkillBFreshness: B★ 41Claude Code +9 - 0.618score
crypto-tax-export
agipro
Export trade history and tax calculations in formats compatible with Koinly, CoinTracker, CoinLedger, TokenTax, and IRS Form 8949
SkillBFreshness: B★ 41Claude Code +9 - 0.618score
feature-engineering
Serennity007
Feature construction from market data for ML trading models including price, volume, on-chain, and microstructure features
SkillBFreshness: B★ 41Claude Code +9 - 0.618score
coingecko-api
Serennity007
Broad crypto market data from CoinGecko covering 13,000+ tokens.
SkillBFreshness: B★ 41Claude Code +9 - 0.618score
correlation-analysis
Serennity007
Cross-asset correlation analysis including rolling correlation, hierarchical clustering, tail dependence, and regime-dependent correlation
SkillBFreshness: B★ 41Claude Code +9 - 0.618score
cost-basis-engine
agipro
Multi-method cost basis computation including specific identification, FIFO, LIFO, HIFO, and proportional average cost with partial sell handling
SkillBFreshness: B★ 41Claude Code +9 - 0.618score
custom-indicators
Serennity007
Crypto-native indicators including NVT ratio, exchange flow, funding rate signals, holder momentum, and smart money flow
SkillBFreshness: B★ 41Claude Code +9 - 0.617score
ibkr-options-assistant
Serennity007
Interactive Brokers options & stock trading assistant.
SkillBFreshness: B★ 41Claude Code +9 - 0.615score
backtrader
Serennity007
Event-driven backtesting with bar-by-bar execution, complex order types, multiple analyzers, and custom indicators
SkillBFreshness: B★ 41Claude Code +9 - 0.615score
birdeye-api
Serennity007
Solana token market data via Birdeye — prices, OHLCV, trades, token metadata, security checks, and trader activity
SkillBFreshness: B★ 41Claude Code +9 - 0.615score
cointegration-analysis
Serennity007
Cointegration testing for pairs trading using Engle-Granger, Johansen, and rolling stability analysis
SkillBFreshness: B★ 41Claude Code +9 - 0.615score
defillama-api
Serennity007
Free DeFi analytics across all chains — TVL, token prices, DEX volumes, fees/revenue, stablecoins, and bridges
SkillBFreshness: B★ 41Claude Code +9
Signals
- Stars
- 41
- Forks
- 8
- Open issues
- 1
- Last commit (this folder)
- Aug 25, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 2.0
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Cite this page
stock-analysis skill. Agent Mart. https://agentmart.dev/skills/serennity007-stock-analysis (last updated 2026-10-24)