Skip to main content
skill CX Codex

edge-concept-synthesizer — Claude Code skill: guide and install

Abstracts raw detector tickets and hints into reusable edge concepts before drafting strategies. Helps prevent overfitting by grouping repeating market conditions.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add tradermonty/claude-trading-skills --skill edge-concept-synthesizer -a claude-code
Open on GitHub

What edge-concept-synthesizer does

This skill adds an intermediate layer between raw anomaly detection and trading strategy design. It parses detector ticket YAML files from directories like tickets/exportable and clusters recurring market conditions into edge_concepts.yaml. Each concept receives an abstract thesis, support statistics, invalidation signals, and an export readiness flag.

Execution relies on scripts/synthesize_edge_concepts.py, which requires Python 3.9+ and PyYAML. The script handles concept deduplication by merging identical hypotheses when condition overlap exceeds the threshold set by --overlap-threshold. It can also filter weak evidence using --min-ticket-support and incorporate optional context from hints.yaml.

Running the synthesis script without detector ticket files produces no output. Prepare your detector YAML exports beforehand so the script has raw evidence to cluster.

What it helps with

  • Cluster raw detector tickets into structured trading hypotheses
  • Prevent strategy overfitting from single-ticket market noise
  • Extract invalidation signals and support stats into edge_concepts.yaml
  • Merge overlapping concept conditions using deduplication thresholds

Example prompts for the agent

  • Synthesize edge concepts from tickets/exportable into edge_concepts.yaml with minimum ticket support of 2.
  • Run scripts/synthesize_edge_concepts.py on /tmp/edge-auto/tickets with hints from hints.yaml and --promote-hints.
  • Deduplicate concepts from the ticket directory using --overlap-threshold 0.6.

How to install edge-concept-synthesizer

1Skills CLI (Vercel)

npx skills add tradermonty/claude-trading-skills --skill edge-concept-synthesizer -a claude-code

2Manually: put the files in place

~/.claude/skills/edge-concept-synthesizer/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/edge-concept-synthesizer/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about edge-concept-synthesizer

How to install edge-concept-synthesizer in Claude Code?

Run npx skills add tradermonty/claude-trading-skills --skill edge-concept-synthesizer -a claude-code. This adds the skill files to your project.

What does edge-concept-synthesizer do?

It aggregates detector tickets and hints into trade concepts with clear thesis logic and invalidation triggers. The clustered output is written to edge_concepts.yaml.

What are the prerequisites for running the synthesizer?

You need Python 3.9+, the PyYAML package, and a directory containing detector ticket YAML files. An optional hints.yaml file can be provided for additional context.

Source text

SKILL.md · MIT
---
name: edge-concept-synthesizer
description: Abstract detector tickets and hints into reusable edge concepts with thesis, invalidation signals, and strategy playbooks before strategy design/export.
---

# Edge Concept Synthesizer

## Overview

Create an abstraction layer between detection and strategy implementation.
This skill clusters ticket evidence, summarizes recurring conditions, and outputs `edge_concepts.yaml` with explicit thesis and invalidation logic.

## When to Use

- You have many raw tickets and need mechanism-level structure.
- You want to avoid direct ticket-to-strategy overfitting.
- You need concept-level review before strategy drafting.

## Prerequisites

- Python 3.9+
- `PyYAML`
- Ticket YAML directory from detector output (`tickets/exportable`, `tickets/research_only`)
- Optional `hints.yaml`

## Output

- `edge_concepts.yaml` containing:
  - concept clusters
  - support statistics
  - abstract thesis
  - invalidation signals
  - export readiness flag

## Workflow

1. Collect ticket YAML files from auto-detection output.
2. Optionally provide `hints.yaml` for context matching.
3. Run `scripts/synthesize_edge_concepts.py`.
4. Deduplicate concepts: merge same-hypothesis concepts with overlapping conditions (containment > threshold).
5. Review concepts and promote only high-support concepts into strategy drafting.

## Quick Commands

```bash
python3 skills/edge-concept-synthesizer/scripts/synthesize_edge_concepts.py \
  --tickets-dir /tmp/edge-auto/tickets \
  --hints /tmp/edge-hints/hints.yaml \
  --output /tmp/edge-concepts/edge_concepts.yaml \
  --min-ticket-support 2

# With hint promotion and synthetic cap
python3 skills/edge-concept-synthesizer/scripts/synthesize_edge_concepts.py \
  --tickets-dir /tmp/edge-auto/tickets \
  --hints /tmp/edge-hints/hints.yaml \
  --output /tmp/edge-concepts/edge_concepts.yaml \
  --promote-hints \
  --max-synthetic-ratio 1.5

# With custom dedup threshold (or disable dedup)
python3 skills/edge-concept-synthesizer/scripts/synthesize_edge_concepts.py \
  --tickets-dir /tmp/edge-auto/tickets \
  --output /tmp/edge-concepts/edge_concepts.yaml \
  --overlap-threshold 0.6

python3 skills/edge-concept-synthesizer/scripts/synthesize_edge_concepts.py \
  --tickets-dir /tmp/edge-auto/tickets \
  --output /tmp/edge-concepts/edge_concepts.yaml \
  --no-dedup
```

## Resources

- `skills/edge-concept-synthesizer/scripts/synthesize_edge_concepts.py`
- `references/concept_schema.md`

© tradermonty · MIT · tradermonty/claude-trading-skills

Similar skills

Everything for Finance and business →

From the same set73

finviz-screener Turns a plain-language request into a FinViz screener URL and opens it in Chrome. Handy when you need to filter stocks by fundamentals or technicals fast. CX Codex +1 3,400installs market-breadth-analyzer Quantifies market breadth health on a 0–100 scale using TraderMonty's public CSV data. Useful when deciding equity exposure based on market participation. CX Codex +1 3,500installs dual-axis-skill-reviewer Reviews skills with deterministic checks and an LLM axis, then combines both into one score. Use it to inspect quality before a merge or find concrete fixes. CX Codex +1 3,300installs edge-hint-extractor Turns daily market observations and news reactions into structured edge hints, written out as hints.yaml. CX Codex +1 3,300installs trader-memory-core This skill keeps investment theses from a screener idea through a closed position with a postmortem. Useful when trade decisions get lost between chats. CX Codex +1 3,300installs pead-screener Screens gap-up stocks after earnings for PEAD follow-through, reading weekly candles for red-candle pullbacks and breakouts. Handy for post-report drift setups. CX Codex +1 3,300installs kanchi-dividend-us-tax-accounting Classifies US dividend streams for stocks, REITs, and BDCs while evaluating holding periods and placement across taxable and retirement accounts. CX Codex +1 3,300installs edge-candidate-agent Turns US equity EOD observations into research tickets and exports validated candidates for trade-strategy-pipeline Phase I. CX Codex +1 3,300installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor