edge-concept-synthesizer
tradermonty/claude-trading-skills
Cluster trading detector tickets into reusable edge concepts with thesis and invalidation signals.
What is edge-concept-synthesizer?
Synthesizes raw detection tickets into abstracted edge concepts with explicit thesis, invalidation logic, and strategy readiness flags. Use this after auto-detection to create a mechanism-level review layer before strategy design, avoiding direct ticket-to-strategy overfitting.
- Clusters ticket evidence by recurring conditions and mechanisms
- Generates abstract thesis statements for each concept
- Defines invalidation signals to test concept validity
- Outputs edge_concepts.yaml with support statistics and export readiness
- Deduplicates overlapping concepts by containment threshold
- Optionally promotes hint-based concepts and caps synthetic concept ratio
How to install edge-concept-synthesizer
npx skills add https://github.com/tradermonty/claude-trading-skills --skill edge-concept-synthesizer- Python 3.9 or later
- PyYAML library
- Ticket YAML directory from detector output (tickets/exportable or tickets/research_only)
- Optional: hints.yaml for context matching
How to use edge-concept-synthesizer
- 1.Collect ticket YAML files from auto-detection output into a tickets directory
- 2.Optionally prepare hints.yaml with high-conviction market conditions
- 3.Run synthesize_edge_concepts.py with --tickets-dir and --output paths
- 4.Review the generated edge_concepts.yaml for concept clusters, thesis clarity, and invalidation signals
- 5.Adjust --min-ticket-support or --overlap-threshold if deduplication is too aggressive or lenient
- 6.Promote only high-support concepts into strategy drafting phase
Use cases
- Organize hundreds of raw detector tickets into 10–20 actionable edge concepts
- Review mechanism-level patterns before committing to strategy implementation
- Identify which concepts have sufficient evidence (ticket support) for strategy drafting
- Merge duplicate concepts that describe the same market condition with different evidence
- Promote high-conviction hints into formal concepts with ticket backing
- Quantitative traders building systematic strategies
- Strategy researchers analyzing detector output at scale
- Teams needing concept-level review gates before strategy export
- Traders avoiding overfitting by abstracting ticket patterns first
edge-concept-synthesizer FAQ
An edge concept is an abstracted market condition or mechanism inferred from multiple detector tickets. It includes a thesis (what you believe), invalidation signals (how you know you're wrong), and support statistics (how many tickets back it).
Use this when you have many tickets and want to avoid overfitting to noise. The synthesis step clusters evidence, identifies duplicates, and enforces concept-level review before strategy design.
It controls deduplication: concepts with hypothesis overlap above this threshold are merged. Higher values (e.g., 0.8) merge fewer concepts; lower values (e.g., 0.4) are more aggressive. Use --no-dedup to skip merging entirely.
Yes, with --promote-hints. Hint-based concepts are created and marked in the output. Use --max-synthetic-ratio to cap the ratio of hint-only concepts relative to ticket-backed ones.
A concept is export-ready when it has sufficient ticket support (above --min-ticket-support threshold) and clear invalidation signals, indicating it is ready for strategy drafting.
Full instructions (SKILL.md)
Source of truth, from tradermonty/claude-trading-skills.
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.yamlcontaining:- concept clusters
- support statistics
- abstract thesis
- invalidation signals
- export readiness flag
Workflow
- Collect ticket YAML files from auto-detection output.
- Optionally provide
hints.yamlfor context matching. - Run
scripts/synthesize_edge_concepts.py. - Deduplicate concepts: merge same-hypothesis concepts with overlapping conditions (containment > threshold).
- Review concepts and promote only high-support concepts into strategy drafting.
Quick Commands
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.pyreferences/concept_schema.md
Related skills
More from tradermonty/claude-trading-skills and the wider catalog.
edge-hint-extractor
Extract market observations into structured edge hints for trading concept synthesis and auto-detection.
edge-pipeline-orchestrator
Orchestrate multi-stage edge research pipelines from candidate detection through strategy export.
edge-signal-aggregator
Aggregate and rank signals from multiple edge-finding skills into a prioritized conviction dashboard with weighted scoring and contradiction detection.
edge-strategy-designer
Convert trading edge concepts into strategy draft variants with optional exportable ticket YAMLs.
edge-strategy-reviewer
Quality gate for trading strategy drafts—evaluates edge plausibility, overfitting risk, and execution realism before pipeline export.
exposure-coach
Synthesize market signals into a unified exposure ceiling and portfolio posture recommendation.