AGENT SKILL

edge-hint-extractor

Extract edge hints from daily market observations and news reactions, with optional LLM ideation, and output canonical hints.yaml for downstream concept synthesis and auto detection.

License 许可
MIT
最近更新
2026-11-13
Stars
★ 32
Forks
6

01 前言 Front Matter

name
edge-hint-extractor
description
Extract edge hints from daily market observations and news reactions, with optional LLM ideation, and output canonical hints.yaml for downstream concept synthesis and auto detection.

02 资源文件 6

03 SKILL.md 正文

Edge Hint Extractor

Overview

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.

When to Use

  • 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.

Prerequisites

  • Python 3.9+
  • PyYAML
  • Optional inputs from detector run:
    • market_summary.json
    • anomalies.json
    • news_reactions.csv or news_reactions.json

Output

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

Workflow

  1. Gather observation files (market_summary, anomalies, optional news reactions).
  2. Run scripts/build_hints.py to generate deterministic hints.
  3. Optionally augment hints with LLM ideas via one of two methods:
    • a. --llm-ideas-cmd — pipe data to an external LLM CLI (subprocess).
    • b. --llm-ideas-file PATH — load pre-written hints from a YAML file (for Claude Code workflows where Claude generates hints itself).
  4. Pass hints.yaml into concept synthesis or auto detection.

Note: --llm-ideas-cmd and --llm-ideas-file are mutually exclusive.

Quick Commands

Rule-based only (default output to reports/edge_hint_extractor/hints.yaml):

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-dir reports/

Rule + LLM augmentation (external CLI):

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-dir reports/

Rule + LLM augmentation (pre-written file, for Claude Code):

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-file /tmp/llm_hints.yaml \
  --output-dir reports/

Resources

  • skills/edge-hint-extractor/scripts/build_hints.py
  • references/hints_schema.md

04 同仓库更多 Skills

mphinance
mphinance/alpha-skills

order-lifecycle-safety

Idempotency, reconcile-before-retry, audit-before-forward and environment-proof preflight rules for any code or agent that places broker orders. Use when building or reviewing an order path, handling a timeout or unknown order outcome, adding client_order_id, deciding whether a retry is safe, or confirming paper vs live before sending an order.

★ 32
mphinance
mphinance/alpha-skills

order-lifecycle-safety

Idempotency, reconcile-before-retry, audit-before-forward and environment-proof preflight rules for any code or agent that places broker orders. Use when building or reviewing an order path, handling a timeout or unknown order outcome, adding client_order_id, deciding whether a retry is safe, or confirming paper vs live before sending an order.

★ 32
mphinance
mphinance/alpha-skills

write-a-skill

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

★ 32
mphinance
mphinance/alpha-skills

wireframe-sketch

A hand-drawn wireframe exploration — graph-paper background, marker / pencil tone, multiple tab labels for variants, sticky-note annotations, scribbled chart placeholders, hatched fills. Reads like a designer's whiteboard before any pixels are committed. Use when the brief asks for "wireframe", "sketch wireframe", "hand-drawn", "lo-fi", "whiteboard", "草稿", or "手绘原型".

★ 32
mphinance
mphinance/alpha-skills

weekly-update

Single-file horizontal-swipe slide deck for a weekly team update — shipped, in flight, blocked, metrics, asks. 6–8 slides. Use when the brief mentions "weekly update", "team update slides", "weekly status", "周报演示".

★ 32
mphinance
mphinance/alpha-skills

webull-openapi

Trade stocks, options, futures, crypto, and event contracts on Webull. Query real-time and historical market data. Manage accounts and positions. Supports US, HK, JP, SG, TH, MY, UK, MX, BR, EU, ZA, and AU regions with configurable risk controls.

★ 32