stock-copilot-pro

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Stock Copilot Pro

Global Multi-Source Stock Analysis with QVeris.

基于QVeris的全球多源股票分析工具。

SEO Keywords

SEO关键词

OpenClaw, stock analysis skill, AI stock copilot, China A-shares, Hong Kong stocks, US stocks, quantitative analysis, fundamental analysis, technical analysis, sentiment analysis, industry radar, morning evening brief, watchlist, portfolio monitoring, QVeris API, THS iFinD, Caidazi, Alpha Vantage, Finnhub, X sentiment, investment research assistant

OpenClaw、股票分析Skill、AI股票副驾驶、A股、港股、美股、量化分析、基本面分析、技术面分析、舆情分析、行业雷达、早晚报、关注列表、投资组合监控、QVeris API、同花顺iFinD、财咨达、Alpha Vantage、Finnhub、X平台舆情、投资研究助手

Supported Capabilities

支持的功能

Single-stock analysis (
```
analyze
```
): valuation, quality, technicals, sentiment, risk/timing
Multi-stock comparison (
```
compare
```
): cross-symbol ranking and portfolio-level view
Watchlist/holdings management (
```
watch
```
): list/add/remove for holdings and watchlist
Morning/Evening brief (
```
brief
```
): holdings-focused daily actionable briefing
Industry hot-topic radar (
```
radar
```
): multi-source topic aggregation for investable themes
Multi-format output:
```
markdown
```
,
```
json
```
,
```
chat
```
OpenClaw LLM-ready flow: structured data in code + guided narrative in
```
SKILL.md
```

单股分析（
```
analyze
```
）：估值、质地、技术面、舆情、风险/时机判断
多股对比（
```
compare
```
）：跨标的排名及投资组合视角分析
关注列表/持仓管理（
```
watch
```
）：持仓与关注列表的查看/添加/删除
早晚报生成（
```
brief
```
）：聚焦持仓的每日可执行简报
行业热点雷达（
```
radar
```
）：多源信息聚合挖掘可投资主题
多格式输出：
```
markdown
```
、
```
json
```
、
```
chat
```
适配OpenClaw大模型的流程：代码结构化数据 +
```
SKILL.md
```
中的引导式叙述

Data Sources

数据源

Core MCP/API gateway:
```
qveris.ai
```
(
```
QVERIS_API_KEY
```
)

CN/HK quote and fundamentals:

```
ths_ifind.real_time_quotation
```
```
ths_ifind.financial_statements
```
```
ths_ifind.company_basics
```
```
ths_ifind.history_quotation
```

CN/HK news and research:

```
caidazi.news.query
```
```
caidazi.report.query
```
```
caidazi.search.hybrid.list
```
```
caidazi.search.hybrid_v2.query
```

Global news sentiment:
- ```
alpha_news_sentiment
```
- ```
finnhub.news
```

X/Twitter sentiment and hot topics:

```
qveris_social.x_domain_hot_topics
```
```
qveris_social.x_domain_hot_events
```
```
qveris_social.x_domain_new_posts
```
```
x_developer.2.tweets.search.recent
```

核心MCP/API网关：
```
qveris.ai
```
（需
```
QVERIS_API_KEY
```
）

中港股市行情与基本面数据：

```
ths_ifind.real_time_quotation
```
```
ths_ifind.financial_statements
```
```
ths_ifind.company_basics
```
```
ths_ifind.history_quotation
```

中港股市新闻与研究报告：

```
caidazi.news.query
```
```
caidazi.report.query
```
```
caidazi.search.hybrid.list
```
```
caidazi.search.hybrid_v2.query
```

全球新闻舆情：
- ```
alpha_news_sentiment
```
- ```
finnhub.news
```

X/Twitter舆情与热点话题：

```
qveris_social.x_domain_hot_topics
```
```
qveris_social.x_domain_hot_events
```
```
qveris_social.x_domain_new_posts
```
```
x_developer.2.tweets.search.recent
```

What This Skill Does

本Skill的作用

Stock Copilot Pro performs end-to-end stock analysis with five data domains:

Market quote / trading context
Fundamental metrics
Technical signals (RSI/MACD/MA)
News and sentiment
X sentiment

It then generates a data-rich analyst report with:

value-investing scorecard
event-timing anti-chasing classification
safety-margin estimate
thesis-driven investment framework (drivers/risks/scenarios/KPIs)
multi-style playbooks (value/balanced/growth/trading)
event radar with candidate ideas from news and X
scenario-based recommendations
standard readable output (default) + optional full evidence trace (
```
--evidence
```
)

Stock Copilot Pro基于五大数据维度进行端到端股票分析：

市场行情/交易背景
基本面指标
技术信号（RSI/MACD/均线）
新闻与舆情
X平台舆情

随后生成数据详实的分析师报告，包含：

价值投资评分卡
事件时机与追高风险分类
安全边际估算
逻辑驱动的投资框架（驱动力/风险/场景/关键指标）
多风格操作指南（价值/平衡/成长/交易）
源自新闻与X平台的事件雷达及候选标的
基于场景的投资建议
标准可读输出（默认）+ 可选的完整证据追踪（开启
```
--evidence
```
参数）

Key Advantages

核心优势

Deterministic tool routing via
```
references/tool-chains.json
```
Evolution v2 parameter-template memory to reduce recurring parameter errors
Strong fallback strategy across providers and markets
US/HK/CN market-aware symbol handling
Structured outputs for both analyst reading and machine ingestion
Safety-first handling of secrets and runtime state

通过
```
references/tool-chains.json
```
实现确定性工具路由
版本2进化式参数模板记忆，减少重复参数错误
跨服务商与市场的强降级策略
适配美股/港股/A股的标的代码识别
同时适配分析师阅读与机器 ingestion 的结构化输出
优先保障密钥与运行时状态的安全性

Core Workflow

核心工作流

Resolve user input to symbol + market (supports company-name aliases, e.g. Chinese name ->
```
600089.SH
```
).
Search tools by capability (quote, fundamentals, indicators, sentiment, X sentiment).
Route by hardcoded tool chains first (market-aware), then fallback generic capability search.
- For CN/HK sentiment, prioritize
```
caidazi
```
  channels (report/news/wechat).
- For CN/HK fundamentals, prioritize THS financial statements (income/balance sheet/cash flow), then fallback to company basics.
Before execution, try evolution parameter templates; if unavailable, use default param builder.
Run quality checks:
- Missing key fields
- Data recency
- Cross-source inconsistency
Produce analyst report with:
- composite score
- safety margin
- event-driven vs pullback-risk timing classification
- structured thesis (driver/risk/scenario/KPI)
- event radar (timeline/theme) and candidate ideas
- style-specific execution playbooks
- market scenario suggestions
- optional parsed/raw evidence sections when
```
--evidence
```
  is enabled
Preference routing (public audience default):
- If no preference flags are provided, script returns a questionnaire first.
- You can skip this with
```
--skip-questionnaire
```
  .

将用户输入解析为标的代码 + 市场（支持公司别名映射，例如中文名映射为
```
600089.SH
```
）。
按能力（行情、基本面、指标、舆情、X平台舆情）匹配工具。
优先通过硬编码工具链路由（适配市场），再 fallback 至通用能力搜索。
- 对于中港股市舆情，优先使用
```
caidazi
```
  渠道（研究报告/新闻/微信）。
- 对于中港股市基本面，优先调用同花顺财务报表（利润表/资产负债表/现金流量表），再 fallback 至公司基础信息。
执行前尝试使用进化参数模板；若不存在，则使用默认参数生成器。
执行质量检查：
- 关键字段缺失
- 数据时效性
- 跨数据源不一致
生成分析师报告，包含：
- 综合评分
- 安全边际
- 事件驱动型回调风险时机分类
- 结构化投资逻辑（驱动力/风险/场景/关键指标）
- 事件雷达（时间线/主题）及候选标的
- 风格专属操作指南
- 市场场景建议
- 开启
```
--evidence
```
  时，额外提供解析后/原始的证据章节
偏好路由（默认面向公众用户）：
- 若未提供偏好标识，脚本会先返回问卷。
- 可通过
```
--skip-questionnaire
```
  跳过问卷。

Command Surface

命令行接口

Primary script:

scripts/stock_copilot_pro.mjs

Analyze one symbol:

node scripts/stock_copilot_pro.mjs analyze --symbol AAPL --market US --mode comprehensive

node scripts/stock_copilot_pro.mjs analyze --symbol "<company-name>" --mode comprehensive

Compare multiple symbols:

node scripts/stock_copilot_pro.mjs compare --symbols AAPL,MSFT --market US --mode comprehensive

Manage watchlist:

node scripts/stock_copilot_pro.mjs watch --action list

node scripts/stock_copilot_pro.mjs watch --action add --bucket holdings --symbol AAPL --market US

node scripts/stock_copilot_pro.mjs watch --action remove --bucket watchlist --symbol 0700.HK --market HK

Generate brief:

node scripts/stock_copilot_pro.mjs brief --type morning --format chat

node scripts/stock_copilot_pro.mjs brief --type evening --format markdown

Run industry radar:

node scripts/stock_copilot_pro.mjs radar --market GLOBAL --limit 10

主脚本：

scripts/stock_copilot_pro.mjs

单股分析：

node scripts/stock_copilot_pro.mjs analyze --symbol AAPL --market US --mode comprehensive

node scripts/stock_copilot_pro.mjs analyze --symbol "<公司名称>" --mode comprehensive

多股对比：

node scripts/stock_copilot_pro.mjs compare --symbols AAPL,MSFT --market US --mode comprehensive

关注列表管理：

node scripts/stock_copilot_pro.mjs watch --action list

node scripts/stock_copilot_pro.mjs watch --action add --bucket holdings --symbol AAPL --market US

node scripts/stock_copilot_pro.mjs watch --action remove --bucket watchlist --symbol 0700.HK --market HK

生成简报：

node scripts/stock_copilot_pro.mjs brief --type morning --format chat

node scripts/stock_copilot_pro.mjs brief --type evening --format markdown

运行行业雷达：

node scripts/stock_copilot_pro.mjs radar --market GLOBAL --limit 10

OpenClaw scheduled tasks (morning/evening brief and radar)

OpenClaw定时任务（早晚报与雷达）

To set up morning brief, evening brief, or daily radar in OpenClaw, use only the official OpenClaw cron format and create jobs via the CLI or Gateway cron tool. Do not edit

~/.openclaw/cron/jobs.json

directly.

Reference: the

jobs

array in

config/openclaw-cron.example.json

; each item is one

cron.add

payload (fields:

name

schedule: { kind, expr, tz }

sessionTarget: "isolated"

payload: { kind: "agentTurn", message: "..." }

delivery

Example (morning brief):

openclaw cron add --name "Stock morning brief" --cron "0 9 * * 1-5" --tz Asia/Shanghai --session isolated --message "Use stock-copilot-pro to generate morning brief: run brief --type morning --max-items 8 --format chat" --announce

. To deliver to Feishu, add

--channel feishu --to <group-or-chat-id>

Incorrect: using the legacy example format (e.g.
```
schedule
```
as string,
```
command
```
,
```
delivery.channels
```
array) or pasting the example into jobs.json will cause Gateway parse failure or crash.

如需在OpenClaw中设置早报、晚报或每日雷达任务，请仅使用官方OpenClaw cron格式，并通过CLI或网关cron工具创建任务。请勿直接编辑

~/.openclaw/cron/jobs.json

。

参考：

config/openclaw-cron.example.json

中的

jobs

数组；每个元素是一个

cron.add

请求体（字段包括：

name

、

schedule: { kind, expr, tz }

、

sessionTarget: "isolated"

、

payload: { kind: "agentTurn", message: "..." }

、

delivery

）。

示例（早报）：

openclaw cron add --name "Stock morning brief" --cron "0 9 * * 1-5" --tz Asia/Shanghai --session isolated --message "Use stock-copilot-pro to generate morning brief: run brief --type morning --max-items 8 --format chat" --announce

。如需推送至飞书，添加

--channel feishu --to <群组或会话ID>

。

错误示例：使用旧版示例格式（例如
```
schedule
```
为字符串、
```
command
```
、
```
delivery.channels
```
数组）或将示例内容粘贴至jobs.json，会导致网关解析失败或崩溃。

CN/HK Coverage Details

中港股市覆盖细节

Company-name input is supported and auto-resolved to market + symbol for common names.
Sentiment path prioritizes
```
caidazi
```
(research reports, news, wechat/public-account channels).
Fundamentals path prioritizes THS financial statements endpoints, and always calls THS company basics for profile backfill:
- ```
revenue
```
- ```
netProfit
```
- ```
totalAssets
```
- ```
totalLiabilities
```
- ```
operatingCashflow
```
- ```
industry
```
- ```
mainBusiness
```
- ```
tags
```

支持公司名称输入，常见名称可自动解析为市场+标的代码。
舆情路径优先使用
```
caidazi
```
（研究报告、新闻、微信公众号渠道）。
基本面路径优先调用同花顺财务报表接口，且始终调用同花顺公司基础信息进行资料补全：
- ```
revenue
```
  （营收）
- ```
netProfit
```
  （净利润）
- ```
totalAssets
```
  （总资产）
- ```
totalLiabilities
```
  （总负债）
- ```
operatingCashflow
```
  （经营现金流）
- ```
industry
```
  （行业）
- ```
mainBusiness
```
  （主营业务）
- ```
tags
```
  （标签）

Output Modes

输出模式

```
markdown
```
(default): human-readable report
```
json
```
: machine-readable merged payload
```
chat
```
: segmented chat-friendly output for messaging apps
```
summary-first
```
: compact output style via
```
--summary-only
```

```
markdown
```
（默认）：人类可读报告
```
json
```
：机器可读的合并数据
```
chat
```
：适配消息应用的分段式友好输出
```
summary-first
```
：通过
```
--summary-only
```
参数生成紧凑摘要式输出

Preference & Event Options

偏好与事件选项

Preference flags:

```
--horizon short|mid|long
```
```
--risk low|mid|high
```
```
--style value|balanced|growth|trading
```
```
--actionable
```
(include execution-oriented rules)
```
--skip-questionnaire
```
(force analysis without preference Q&A)

Event radar flags:

```
--event-window-days 7|14|30
```
```
--event-universe global|same_market
```
```
--event-view timeline|theme
```

偏好标识：
- ```
--horizon short|mid|long
```
  （投资周期：短期|中期|长期）
- ```
--risk low|mid|high
```
  （风险承受：低|中|高）
- ```
--style value|balanced|growth|trading
```
  （投资风格：价值|平衡|成长|交易）
- ```
--actionable
```
  （包含执行导向规则）
- ```
--skip-questionnaire
```
  （强制跳过偏好问卷直接分析）
事件雷达标识：
- ```
--event-window-days 7|14|30
```
  （事件窗口天数）
- ```
--event-universe global|same_market
```
  （事件覆盖范围：全球|同市场）
- ```
--event-view timeline|theme
```
  （事件展示方式：时间线|主题）

Dynamic Evolution

动态进化

Runtime learning state is stored in
```
.evolution/tool-evolution.json
```
.
One successful execution can update tool parameter templates.
Evolution stores
```
param_templates
```
and
```
sample_successful_params
```
for reuse.
Evolution does not decide tool priority; tool priority is controlled by
```
tool-chains.json
```
.
Use
```
--no-evolution
```
to disable loading/saving runtime learning state.

运行时学习状态存储于
```
.evolution/tool-evolution.json
```
。
一次成功执行可更新工具参数模板。
进化功能存储
```
param_templates
```
和
```
sample_successful_params
```
以供复用。
进化功能不决定工具优先级；工具优先级由
```
tool-chains.json
```
控制。
可使用
```
--no-evolution
```
参数禁用运行时学习状态的加载/保存。

Safety and Disclosure

安全与披露

Uses only
```
QVERIS_API_KEY
```
.
Calls only QVeris APIs over HTTPS.
```
full_content_file_url
```
fetching is kept enabled for data completeness, but only HTTPS URLs under
```
qveris.ai
```
are allowed.
Does not store API keys in logs, reports, or evolution state.
Runtime persistence is limited to
```
.evolution/tool-evolution.json
```
(metadata + parameter templates only).

Watchlist state is stored at

config/watchlist.json

(bootstrap from

config/watchlist.example.json

OpenClaw scheduled tasks: see
```
config/openclaw-cron.example.json
```
. Create jobs with the official format (
```
schedule.kind
```
,
```
payload.kind
```
,
```
sessionTarget
```
, etc.) via
```
openclaw cron add
```
or the Gateway cron tool; do not paste or merge the example JSON into
```
~/.openclaw/cron/jobs.json
```
(schema mismatch can cause Gateway parse failure or crash). Set
```
delivery.channel
```
and
```
delivery.to
```
for your channel (e.g. feishu).
External source URLs remain hidden by default; only shown when
```
--include-source-urls
```
is explicitly enabled.
No package installation or arbitrary command execution is performed by this skill script.
Research-only output. Not investment advice.

仅使用
```
QVERIS_API_KEY
```
。
仅通过HTTPS调用QVeris API。
为保证数据完整性，
```
full_content_file_url
```
获取功能默认开启，但仅允许
```
qveris.ai
```
域名下的HTTPS链接。
不会在日志、报告或进化状态中存储API密钥。
运行时持久化仅局限于
```
.evolution/tool-evolution.json
```
（仅包含元数据+参数模板）。
关注列表状态存储于
```
config/watchlist.json
```
（可从
```
config/watchlist.example.json
```
初始化）。
OpenClaw定时任务：参考
```
config/openclaw-cron.example.json
```
。请使用官方格式（
```
schedule.kind
```
、
```
payload.kind
```
、
```
sessionTarget
```
等）通过
```
openclaw cron add
```
或网关cron工具创建任务；请勿将示例JSON粘贴或合并至
```
~/.openclaw/cron/jobs.json
```
（ schema不匹配会导致网关解析失败或崩溃）。为渠道（如飞书）设置
```
delivery.channel
```
和
```
delivery.to
```
。
外部源URL默认隐藏；仅在显式开启
```
--include-source-urls
```
参数时显示。
本Skill脚本不会执行包安装或任意命令。
仅作研究用途，不构成投资建议。

Single Stock Analysis Guide

单股分析指南

When analyzing

analyze

output, act as a senior buy-side analyst and deliver a professional but not overlong report.

分析

analyze

输出时，需以资深买方分析师身份，提供专业但不过冗长的报告。

Required Output (7 Sections)

必备输出（7个章节）

Data Snapshot (required)
- Start with a compact metrics table built from
```
data
```
  fields.
- Include at least: price/change, marketCap, PE/PB, profitMargin, revenue, netProfit, RSI, 52W range.
- Example format:

markdown

| Metric | Value |
|--------|-------|
| Price | $264.58 (+1.54%) |
| Market Cap | $3.89T |
| P/E | 33.45 |
| P/B | 57.97 |
| Profit Margin | 27% |
| Revenue (TTM) | $394B |
| Net Profit | $99.8B |
| RSI | 58.3 |
| 52W Range | $164 - $270 |

Key view (30 seconds)
- One-line conclusion: buy/hold/avoid + key reason.
Investment thesis
- Bull case: 2 points (growth driver, moat/catalyst)
- Bear case: 2 points (valuation/risk/timing)
- Final balance: what dominates now.
Valuation and key levels
- PE/PB vs peer or history percentile (cheap/fair/expensive)
- Key levels: current price, support, resistance, stop-loss reference
Recommendation (required)
- Different advice by position status:
  - No position
  - Light position
  - Heavy position / underwater
- Each suggestion must include concrete trigger/price/condition.
Risk monitor
- Top 2-3 risks + invalidation condition (what proves thesis wrong).
Data Sources (required)
- End with a source disclosure line showing QVeris attribution and data channels actually used.
- Include generation timestamp and list of source/tool names from payload metadata such as
```
dataSources
```
  ,
```
meta.sourceStats
```
  , or
```
data.*.selectedTool
```
  .
- Example format:

markdown

> Data powered by [QVeris](https://qveris.ai) | Sources: Alpha Vantage (quote/fundamentals), Finnhub (news sentiment), X/Twitter (social sentiment) | Generated at 2026-02-22T13:00:00Z

数据快照（必填）
- 从
```
data
```
  字段构建紧凑指标表开头。
- 至少包含：价格/涨跌幅、市值、市盈率/市净率、利润率、营收、净利润、RSI、52周价格区间。
- 示例格式：

markdown

| 指标 | 数值 |
|--------|-------|
| 价格 | $264.58 (+1.54%) |
| 市值 | $3.89T |
| 市盈率 | 33.45 |
| 市净率 | 57.97 |
| 利润率 | 27% |
| 营收（TTM） | $394B |
| 净利润 | $99.8B |
| RSI | 58.3 |
| 52周区间 | $164 - $270 |

核心观点（30秒速读）
- 一句话结论：买入/持有/回避 + 核心理由。
投资逻辑
- 看多逻辑：2个要点（增长驱动力、护城河/催化剂）
- 看空逻辑：2个要点（估值/风险/时机）
- 最终平衡：当前主导因素
估值与关键价位
- 市盈率/市净率与同行或历史分位对比（低估/合理/高估）
- 关键价位：当前价格、支撑位、阻力位、止损参考位
投资建议（必填）
- 根据持仓状态给出不同建议：
  - 未持仓
  - 轻仓
  - 重仓/浮亏
- 每个建议需包含具体触发条件/价格/场景
风险监控
- 前2-3大风险 + 逻辑失效条件（即证明投资逻辑错误的信号）
数据源（必填）
- 结尾添加一行QVeris归因及本次报告实际使用的数据渠道。
- 包含生成时间戳及从元数据（如
```
dataSources
```
  、
```
meta.sourceStats
```
  或
```
data.*.selectedTool
```
  ）中提取的源/工具名称列表。
- 示例格式：

markdown

> 数据由[QVeris](https://qveris.ai)提供 | 数据源：Alpha Vantage（行情/基本面）、Finnhub（新闻舆情）、X/Twitter（社交舆情） | 生成时间：2026-02-22T13:00:00Z

Quality Bar

质量标准

Avoid data dumping; each key number must include interpretation.
Every numeric claim must be grounded in actual payload values; do not fabricate numbers.
Keep concise but complete (target 250-500 characters for narrative).
Must include actionable guidance and time window.
Ticker and technical terms in English.

避免数据堆砌；每个关键数值需包含解读。
所有数值结论必须基于实际数据；不得编造数字。
保持简洁但完整（叙述部分目标250-500字符）。
必须包含可执行指导及时间窗口。
标的代码及专业术语保留英文。

Daily Brief Analysis Guide

每日简报分析指南

When analyzing

brief

output, generate an actionable morning/evening briefing for OpenClaw conversation.

分析

brief

输出时，需为OpenClaw对话生成可执行的早/晚报内容。

Morning Brief

早报

Market overview: risk-on/off + key overnight move + today's tone, plus an index snapshot table from
```
marketOverview.indices
```
(index name, price, % change, timestamp)
Holdings check: holdings that need action first, with per-holding price/% change/grade when available
Radar relevance: which radar themes impact holdings
Today's plan (required): specific watch levels / event / execution plan
Data Sources (required): one-line QVeris attribution and channels used in this brief

市场概览：风险偏好（风险偏好上升/下降）+ 隔夜关键变动 + 今日市场基调，同时附上
```
marketOverview.indices
```
中的指数快照表（指数名称、价格、涨跌幅、时间戳）
持仓检查：优先提示需要操作的持仓，若有数据则包含单持仓的价格/涨跌幅/评级
雷达关联：哪些雷达主题会影响持仓
今日计划（必填）：具体关注价位/事件/执行计划
数据源（必填）：一行QVeris归因及本次简报使用的渠道

Evening Brief

晚报

Session recap: index + sector + portfolio one-line recap, with key index close/% change
Holdings change: biggest winners/losers and why, with quantized move (%) where available
Thesis check: whether thesis changed
Tomorrow's plan (required): explicit conditions and actions
Data Sources (required): one-line QVeris attribution and channels used in this brief

当日复盘：指数+板块+投资组合一句话复盘，包含关键指数收盘价/涨跌幅
持仓变动：最大涨幅/跌幅标的及原因，若有数据则量化变动幅度（%）
逻辑验证：投资逻辑是否发生变化
明日计划（必填）：明确条件与行动
数据源（必填）：一行QVeris归因及本次简报使用的渠道

Quality Bar

质量标准

Prioritize user holdings, not generic market commentary.
Quantify changes when possible (%, levels, counts).
Keep concise and decision-oriented.
Include a short source disclosure line at the end to improve traceability and credibility.

优先关注用户持仓，而非通用市场评论。
尽可能量化变动（%、价位、数量）。
保持简洁且以决策为导向。
结尾添加简短数据源披露，提升可追溯性与可信度。

Hot Topic Analysis Guide

热点话题分析指南

When analyzing

radar

output, cluster signals into investable themes and provide concise actionable conclusions.

分析

radar

输出时，需将信号聚类为可投资主题，并提供简洁的可执行结论。

Required Output (per theme)

必备输出（每个主题）

Theme: clear, investable label
Driver: what changed and why now
Impact: beneficiaries/losers + magnitude + duration
Recommendation (required): concrete trigger or level
Risk note: key invalidation or monitoring signal
Source tag (required): include
```
source
```
label for each theme (for example:
```
caidazi_report
```
,
```
alpha_news_sentiment
```
,
```
x_hot_topics
```
)

主题：清晰、可投资的标签
驱动因素：发生了什么变化，以及为何是现在
影响：受益/受损标的 + 影响幅度 + 持续时间
投资建议（必填）：具体触发条件或价位
风险提示：核心失效信号或监控指标
源标签（必填）：为每个主题添加
```
source
```
标签（例如：
```
caidazi_report
```
、
```
alpha_news_sentiment
```
、
```
x_hot_topics
```
）

Execution Rules

执行规则

Cluster into 3-5 themes max.
Cross-verify sources; lower confidence for social-only signals.
Distinguish short-term trade vs mid-term allocation.
Keep each theme concise (<200 characters preferred).
End with a QVeris source disclosure line listing channels that contributed to this radar run.

最多聚类为3-5个主题。
交叉验证数据源；仅来自社交平台的信号可信度较低。
区分短期交易与中期配置。
每个主题保持简洁（建议少于200字符）。
结尾添加一行QVeris数据源披露，列出本次雷达分析贡献的渠道。