edge-hint-extractor

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Edge Hint Extractor

Overview

概述

Convert raw observation signals (

market_summary

anomalies

news reactions

) into structured edge hints. This skill is the first stage in the split workflow:

observe -> abstract -> design -> pipeline

将原始观察信号（

market_summary

、

anomalies

、

news reactions

）转换为结构化的边缘提示。该技能是拆分工作流的第一阶段：

observe -> abstract -> design -> pipeline

。

When to Use

适用场景

You want to turn daily market observations into reusable hint objects.
You want LLM-generated ideas constrained by current anomalies/news context.
You need a clean
```
hints.yaml
```
input for concept synthesis or auto detection.

希望将每日市场观察转换为可复用的提示对象时。
希望在当前异常/新闻背景约束下，由LLM生成创意时。
需要为概念合成或自动检测提供干净的
```
hints.yaml
```
输入时。

Prerequisites

前置条件

Python 3.9+
```
PyYAML
```

Optional inputs from detector run:

```
market_summary.json
```
```
anomalies.json
```
```
news_reactions.csv
```
or
```
news_reactions.json
```

Python 3.9+
```
PyYAML
```

检测器运行产生的可选输入：

```
market_summary.json
```
```
anomalies.json
```
```
news_reactions.csv
```
或
```
news_reactions.json
```

Output

输出

```
hints.yaml
```
containing:
- ```
hints
```
  list
- generation metadata
- rule/LLM hint counts

```
hints.yaml
```
文件，包含：
- ```
hints
```
  列表
- 生成元数据
- 规则/LLM提示计数

Workflow

工作流

Gather observation files (
```
market_summary
```
,
```
anomalies
```
, optional news reactions).
Run
```
scripts/build_hints.py
```
to generate deterministic hints.
Optionally add
```
--llm-ideas-cmd
```
to augment hints.
Pass
```
hints.yaml
```
into concept synthesis or auto detection.

收集观察文件（
```
market_summary
```
、
```
anomalies
```
，可选新闻反馈）。
运行
```
scripts/build_hints.py
```
生成确定性提示。
可选添加
```
--llm-ideas-cmd
```
参数来扩充提示。
将
```
hints.yaml
```
传入概念合成或自动检测环节。

Quick Commands

快速命令

Rule-based only:

bash

python3 skills/edge-hint-extractor/scripts/build_hints.py \
  --market-summary /tmp/edge-auto/market_summary.json \
  --anomalies /tmp/edge-auto/anomalies.json \
  --news-reactions /tmp/news_reactions.csv \
  --as-of 2026-02-20 \
  --output /tmp/edge-hints/hints.yaml

Rule + LLM augmentation:

bash

python3 skills/edge-hint-extractor/scripts/build_hints.py \
  --market-summary /tmp/edge-auto/market_summary.json \
  --anomalies /tmp/edge-auto/anomalies.json \
  --llm-ideas-cmd "python3 /path/to/llm_ideas_cli.py" \
  --output /tmp/edge-hints/hints.yaml

仅基于规则：

bash

python3 skills/edge-hint-extractor/scripts/build_hints.py \
  --market-summary /tmp/edge-auto/market_summary.json \
  --anomalies /tmp/edge-auto/anomalies.json \
  --news-reactions /tmp/news_reactions.csv \
  --as-of 2026-02-20 \
  --output /tmp/edge-hints/hints.yaml

规则 + LLM扩充：

bash

python3 skills/edge-hint-extractor/scripts/build_hints.py \
  --market-summary /tmp/edge-auto/market_summary.json \
  --anomalies /tmp/edge-auto/anomalies.json \
  --llm-ideas-cmd "python3 /path/to/llm_ideas_cli.py" \
  --output /tmp/edge-hints/hints.yaml

Resources

资源

skills/edge-hint-extractor/scripts/build_hints.py

skills/edge-hint-extractor/references/hints_schema.md

skills/edge-hint-extractor/scripts/build_hints.py

skills/edge-hint-extractor/references/hints_schema.md