edge-signal-aggregator
starsforks
How to install edge-signal-aggregator?
mphinance/alpha-skills/edge-signal-aggregator
$npx -y skills add mphinance/alpha-skills --skill edge-signal-aggregatorAggregate and rank signals from multiple edge-finding skills (edge-candidate-agent, theme-detector, sector-analyst, institutional-flow-tracker) into a prioritized conviction dashboard with weighted scoring, deduplication, and contradiction detection.
SKILL.md
| 1 | # Edge Signal Aggregator |
| 2 | |
| 3 | ## Overview |
| 4 | |
| 5 | 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. |
| 6 | |
| 7 | ## When to Use |
| 8 | |
| 9 | - After running multiple edge-finding skills and wanting a unified view |
| 10 | - When consolidating signals from edge-candidate-agent, theme-detector, sector-analyst, and institutional-flow-tracker |
| 11 | - Before making portfolio allocation decisions based on multiple signal sources |
| 12 | - To identify contradictions between different analysis approaches |
| 13 | - When prioritizing which edge ideas deserve deeper research |
| 14 | |
| 15 | ## Prerequisites |
| 16 | |
| 17 | - Python 3.9+ |
| 18 | - No API keys required (processes local JSON/YAML files from other skills) |
| 19 | - Dependencies: `pyyaml` (standard in most environments) |
| 20 | |
| 21 | ## Workflow |
| 22 | |
| 23 | ### Step 1: Gather Upstream Skill Outputs |
| 24 | |
| 25 | Collect output files from the upstream skills you want to aggregate: |
| 26 | - `reports/edge_candidate_*.json` from edge-candidate-agent |
| 27 | - `reports/edge_concepts_*.yaml` from edge-concept-synthesizer |
| 28 | - `reports/theme_detector_*.json` from theme-detector |
| 29 | - `reports/sector_analyst_*.json` from sector-analyst |
| 30 | - `reports/institutional_flow_*.json` from institutional-flow-tracker |
| 31 | - `reports/edge_hints_*.yaml` from edge-hint-extractor |
| 32 | |
| 33 | ### Step 2: Run Signal Aggregation |
| 34 | |
| 35 | Execute the aggregator script with paths to upstream outputs: |
| 36 | |
| 37 | ```bash |
| 38 | python3 skills/edge-signal-aggregator/scripts/aggregate_signals.py \ |
| 39 | --edge-candidates reports/edge_candidate_agent_*.json \ |
| 40 | --edge-concepts reports/edge_concepts_*.yaml \ |
| 41 | --themes reports/theme_detector_*.json \ |
| 42 | --sectors reports/sector_analyst_*.json \ |
| 43 | --institutional reports/institutional_flow_*.json \ |
| 44 | --hints reports/edge_hints_*.yaml \ |
| 45 | --output-dir reports/ |
| 46 | ``` |
| 47 | |
| 48 | Optional: Use a custom weights configuration: |
| 49 | |
| 50 | ```bash |
| 51 | python3 skills/edge-signal-aggregator/scripts/aggregate_signals.py \ |
| 52 | --edge-candidates reports/edge_candidate_agent_*.json \ |
| 53 | --weights-config skills/edge-signal-aggregator/assets/custom_weights.yaml \ |
| 54 | --output-dir reports/ |
| 55 | ``` |
| 56 | |
| 57 | ### Step 3: Review Aggregated Dashboard |
| 58 | |
| 59 | Open the generated report to review: |
| 60 | 1. **Ranked Edge Ideas** - Sorted by composite conviction score |
| 61 | 2. **Signal Provenance** - Which skills contributed to each idea |
| 62 | 3. **Contradictions** - Conflicting signals flagged for manual review |
| 63 | 4. **Deduplication Log** - Merged overlapping themes |
| 64 | |
| 65 | ### Step 4: Act on High-Conviction Signals |
| 66 | |
| 67 | Filter the shortlist by minimum conviction threshold: |
| 68 | |
| 69 | ```bash |
| 70 | python3 skills/edge-signal-aggregator/scripts/aggregate_signals.py \ |
| 71 | --edge-candidates reports/edge_candidate_agent_*.json \ |
| 72 | --min-conviction 0.7 \ |
| 73 | --output-dir reports/ |
| 74 | ``` |
| 75 | |
| 76 | ## Output Format |
| 77 | |
| 78 | ### JSON Report |
| 79 | |
| 80 | ```json |
| 81 | { |
| 82 | "schema_version": "1.0", |
| 83 | "generated_at": "2026-03-02T07:00:00Z", |
| 84 | "config": { |
| 85 | "weights": { |
| 86 | "edge_candidate_agent": 0.25, |
| 87 | "edge_concept_synthesizer": 0.20, |
| 88 | "theme_detector": 0.15, |
| 89 | "sector_analyst": 0.15, |
| 90 | "institutional_flow_tracker": 0.15, |
| 91 | "edge_hint_extractor": 0.10 |
| 92 | }, |
| 93 | "min_conviction": 0.5, |
| 94 | "dedup_similarity_threshold": 0.8 |
| 95 | }, |
| 96 | "summary": { |
| 97 | "total_input_signals": 42, |
| 98 | "unique_signals_after_dedup": 28, |
| 99 | "contradictions_found": 3, |
| 100 | "signals_above_threshold": 12 |
| 101 | }, |
| 102 | "ranked_signals": [ |
| 103 | { |
| 104 | "rank": 1, |
| 105 | "signal_id": "sig_001", |
| 106 | "title": "AI Infrastructure Capex Acceleration", |
| 107 | "composite_score": 0.87, |
| 108 | "contributing_skills": [ |
| 109 | { |
| 110 | "skill": "edge_candidate_agent", |
| 111 | "signal_ref": "ticket_2026-03-01_001", |
| 112 | "raw_score": 0.92, |
| 113 | "weighted_contribution": 0.23 |
| 114 | }, |
| 115 | { |
| 116 | "skill": "theme_detector", |
| 117 | "signal_ref": "theme_ai_infra", |
| 118 | "raw_score": 0.85, |
| 119 | "weighted_contribution": 0.13 |
| 120 | } |
| 121 | ], |
| 122 | "tickers": ["NVDA", "AMD", "AVGO"], |
| 123 | "direction": "LONG", |
| 124 | "time_horizon": "3-6 months", |
| 125 | "confidence_breakdown": { |
| 126 | "multi_skill_agreement": 0.30, |
| 127 | "signal_strength": 0.35, |
| 128 | "recency": 0.22 |
| 129 | } |
| 130 | } |
| 131 | ], |
| 132 | "contradictions": [ |
| 133 | { |
| 134 | "contradiction_id": "contra_001", |
| 135 | "description": "Conflicting sector view on Energy", |
| 136 | "skill_a": { |
| 137 | "skill": "sector_analyst", |
| 138 | "signal": "Energy sector bearish rotation", |
| 139 | "direction": "SHORT" |
| 140 | }, |
| 141 | "skill_b": { |
| 142 | "skill": "institutional_flow_tracker", |
| 143 | "signal": "Heavy institutional buying in XLE", |
| 144 | "direction": "LONG" |
| 145 | }, |
People who liked this also viewed
6 picksType
- azure-costAzure cost management: query costs, forecast spending, optimize to reduce waste. WHEN: \"Azure costs\", \"Azure bill\", \"cost breakdown\", \"how much am I spending\", \"forecast spending\", \"optimizSkillsJul 2026
- pricingWhen the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increaseSkillsJul 2026
- stripe-integrationMulti-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLISkillsJul 2026
- startup-financial-modelingMulti-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLISkillsJul 2026
- tushare-finance专为 Claude Code 设计的 Tushare Pro 金融数据技能包，支持 220+ 个接口，用自然语言获取 A 股行情、财务数据、宏观经济等金融数据。SkillsJul 2026
- azure-pricingFetches real-time Azure retail pricing using the Azure Retail Prices API (prices.azure.com) and estimates Copilot Studio agent credit consumption. Use when the user asks about the cost of any Azure seSkillsJul 2026
