Borrowing it
Nothing to install: this file belongs to belos-street/stock-analytics-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/belos-street/stock-analytics-skill/main/.agents/skills/thematic-stock-picker/SKILL.mdgit clone --depth 1 https://github.com/belos-street/stock-analytics-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/belos-street/stock-analytics-skill/thematic-stock-picker)<a href="https://agentmods.dev/skills/belos-street/stock-analytics-skill/thematic-stock-picker"><img src="https://agentmods.dev/badge/skills/belos-street/stock-analytics-skill/thematic-stock-picker/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/belos-street/stock-analytics-skill/thematic-stock-picker"><img src="https://agentmods.dev/badge/skills/belos-street/stock-analytics-skill/thematic-stock-picker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.02481 |
| Opus 5 | $0.00039 | $0.01241 |
| Sonnet 5 | $0.00016 | $0.00496 |
| Haiku 4.5 | $0.00008 | $0.00248 |
Grade A, and why
thematic-stock-picker 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 12d 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
按主题选股
技能核心定位
核心目标
主题选股技能，适用于赛道投资、产业链机会挖掘和概念股筛选场景。能够系统拆解当前市场交易的核心逻辑，结合关键数据验证逻辑兑现程度，筛选真正受益标的，并给出估值历史分位和交易视角建议。
目标用户
- 主题投资者：关注特定主题机会（AI、新能源等）
- 赛道投资者：看好某条赛道，寻找产业链标的
- 事件驱动者：关注政策、技术突破带来的主题机会
- 组合优化者：为现有组合寻找新的alpha来源
技能边界
可提供服务：
- 主题产业链拆解
- 受益标的筛选
- 概念股真伪辨别
- 估值空间分析
- 交易建议
不可提供服务：
- 具体买卖指令
- 承诺收益
- 预测股价
- 内幕信息
主题分类体系
科技主题
AI人工智能：
- 基础层：AI芯片（寒武纪、海光信息）、算力（浪潮信息、光模块）
- 应用层：垂直应用（金融AI、医疗AI、教育AI）
- 基础设施：云计算、大数据
半导体：
- 设备：光刻机、刻蚀机、沉积设备
- 材料：硅片、光刻胶、电子特气
- 设计：CPU、GPU、FPGA、模拟芯片
- 封测：封装、测试
新能源汽车：
- 整车：比亚迪、特斯拉、蔚来
- 电池：宁德时代、亿纬锂能
- 材料：碳酸锂、隔膜、电解液
- 零部件：热管理、域控制器
消费主题
消费升级：
- 高端白酒：茅台、五粮液、泸州老窖
- 医美：爱美客、华熙生物
- 新能源汽车：理想、小鹏
国货崛起：
- 国产美妆：珀莱雅、花西子
- 国产运动：李宁、安踏
- 国产家电：美的、格力、海尔
老龄化：
- 创新药：恒瑞医药、百济神州
- 医疗器械：迈瑞医疗、微创医疗
- 医疗服务：通策医疗、爱尔眼科
新能源主题
光伏：
- 硅料：通威股份、大全能源
- 硅片：隆基绿能、TCL中环
- 电池片：爱旭股份、钧达股份
- 组件：晶科能源、天合光能
- 逆变器：阳光电源、锦浪科技
风电：
- 海风：东方电缆、明阳智能
- 叶片：中材科技、时代新材
- 主轴：金雷股份、通裕重工
储能：
- 电池：宁德时代、亿纬锂能
- 集成：阳光电源、科华数据
- 材料：德方纳米、贝特瑞
政策主题
国产替代：
- 半导体设备：北方华创、中微公司
- 工业软件：用友网络、金山办公
- 科学仪器：鼎阳科技、坤恒顺维
专精特新：
- 细分行业龙头
- 关键零部件
- 核心材料
碳中和：
- 新能源：光伏、风电、储能
- 环保：垃圾焚烧、污水处理
- 碳交易：园林碳汇
筛选流程
第一步：主题逻辑拆解
示例：AI算力主题
1. 核心驱动力：
- ChatGPT引爆AI浪潮
- 大模型军备竞赛
- 算力需求爆发式增长
2. 传导路径：
- 最先受益：底层芯片（GPU、CPU）
- 第二层：服务器、光模块
- 第三层：云计算、IDC
- 第四层：应用层
3. 验证指标：
- 英伟达业绩
- 服务器招标数据
- 云厂商资本开支
第二步：标的筛选
筛选条件：
1. 业务相关性：AI收入占比 > 30%或AI为核心业务
2. 产业链位置：基础层/应用层
3. 竞争壁垒：技术优势、客户资源、生态
4. 商业化进程：已有收入或明确商业化路径
第三步：估值分析
分析维度：
- 历史PE分位
- 相对行业平均PE
- PEG估值
- PS估值（适合成长股）
第四步：风险评估
风险点：
- 估值过高风险
- 技术路径变化
- 竞争格局恶化
- 政策变化
- 业绩兑现风险
标的分类标准
核心受益标的
- AI相关收入占比 > 50%
- 行业龙头地位
- 技术壁垒高
- 已有明确商业化收入
受益标的
- AI相关收入占比 30-50%
- 行业地位中等
- 具备一定竞争力
- 潜在受益但尚未充分体现
概念炒作标的
- AI相关收入占比 < 10%
- 蹭热度、炒概念
- 无实质业务关联
- 纯情绪驱动
报告输出格式
主题选股报告
# AI算力主题投资分析报告
## 一、主题逻辑拆解
### 核心驱动力
- AI大模型发展带动算力需求爆发
- 国内外科技巨头加码AI投资
- 算力国产化需求迫切
### 产业链结构
芯片/算力 → 服务器 → 光模块/存储 → IDC → 云服务 → 应用
### 受益路径
1. 第一层（最先）：AI芯片、服务器
2. 第二层：光模块、存储
3. 第三层：IDC、云计算
4. 第四层：应用层（长期）
## 二、受益标的筛选
### 核心受益标的（5-8只）
| 代码 | 公司 | 业务相关性 | 竞争壁垒 | 估值分位 | 推荐理由 |
|------|------|-----------|---------|---------|---------|
| 688256 | 寒武纪 | 95% | 高 | 85% | AI芯片龙头 |
### 受益标的（3-5只）
| 代码 | 公司 | 业务相关性 | 竞争壁垒 | 估值分位 | 备注 |
|------|------|-----------|---------|---------|-----|
| 000977 | 浪潮信息 | 60% | 中 | 65% | 服务器龙头 |
## 三、估值对比
| 公司 | PE(TTM) | 历史分位 | 行业平均 | 评价 |
|------|---------|---------|---------|------|
| 寒武纪 | xxx | 85% | xxx | 偏高 |
| 浪潮信息 | xxx | 55% | xxx | 合理 |
## 四、交易建议
### 核心配置
- 标的：XXXX
- 逻辑：
- 持有期：6-12个月
### 卫星配置
- 标的：XXXX
- 逻辑：
- 持有期：3-6个月
### 风险提示
- 估值回调风险
- 技术路径变化
- 业绩兑现延后
## 五、跟踪要点
### 需要持续跟踪
- 政策变化
- 技术突破
- 业绩兑现
- 竞争格局
### 卖出信号
- 估值严重泡沫化
- 逻辑被证伪
- 发现更好标的
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.
- 12d ago First seen · 326 lines · 78 tokens per session scan A fe53db700574
thematic-stock-picker is a skill published in the GitHub repository belos-street/stock-analytics-skill (49 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 2,481 once invoked, about $0.0004 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.