tradermonty avatar

Edge Signal Aggregator

Combines outputs from multiple edge-finding skills into a single ranked dashboard with weighted scoring and contradiction detection. You run this after collecting signals from edge-candidate-agent, theme-detector, sector-analyst, and other upstream tools to get a unified view before making allocation decisions. It deduplicates overlapping themes, flags when different skills contradict each other (like sector-analyst being bearish while institutional-flow-tracker shows heavy buying), and tracks provenance so you know which skills contributed to each idea. The weights are configurable if you trust certain signals more than others. Honest take: this is glue code with opinions about how to combine signals, and those opinions matter more than the aggregation itself.

skills.sh installs
3.4K
GitHub stars
3.7K
last updated
Aug 21, 2026

Install

$ npx -y skills add tradermonty/claude-trading-skills --skill edge-signal-aggregator --agent claude-code

Installs into .claude/skills of the current project.

Files

Edge Signal Aggregator

Overview

Combine outputs from multiple upstream edge-finding skills into a single weighted conviction dashboard. This skill applies configurable signal weights, deduplicates overlapping themes, flags contradictions between skills, and ranks composite edge ideas by aggregate confidence score. The result is a prioritized edge shortlist with provenance links to each contributing skill.

When to Use

  • After running multiple edge-finding skills and wanting a unified view
  • When consolidating signals from edge-candidate-agent, theme-detector, sector-analyst, and institutional-flow-tracker
  • Before making portfolio allocation decisions based on multiple signal sources
  • To identify contradictions between different analysis approaches
  • When prioritizing which edge ideas deserve deeper research

Prerequisites

  • Python 3.9+
  • No API keys required (processes local JSON/YAML files from other skills)
  • Dependencies: pyyaml (standard in most environments)

Workflow

Step 1: Gather Upstream Skill Outputs

Sponsors

Details

Repository
github.com/tradermonty/claude-trading-skills
Categories
Backend & APIs, AI & Agent Building, Finance & Trading
First seen
Jun 3, 2026

More from tradermonty/claude-trading-skills

All 54
1affaan-m avataruspto-databaseaffaan-m/eccUSPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.3.2Kskills.sh installs
2redis avatarredis-connectionsredis/agent-skillsRedis client and connection guidance covering connection pooling, multiplexing, pipelining, client-side caching with RESP3, avoiding slow commands (KEYS, SMEMBE3Kskills.sh installs
3dpearson2699 avatarswift-api-design-guidelinesdpearson2699/swift-ios-skillsApply Swift API Design Guidelines to name, label, and document Swift APIs. Covers argument label rules (prepositional phrase rule, grammatical phrase rule, firs3Kskills.sh installs
4redis avatarredis-observabilityredis/agent-skillsRedis observability guidance — which metrics to monitor (memory, connections, hit ratio, ops/sec, rejected connections), which built-in commands to reach for du2.5Kskills.sh installs
5affaan-m avatarclaude-apiaffaan-m/everything-claude-codeclaude api2.4Kskills.sh installs
6google-deepmind avataralphafold-database-fetch-and-analyzegoogle-deepmind/science-skillsRetrieve and analyze AlphaFold predicted structures for a protein. Use when the user provides a specific UniProt Accession ID and wants structural confidence me2.3Kskills.sh installs