Verified:GitHub

Reconciler

Merge research outputs into a structured fact table and reconciliation report.

2|3|Updated Nov 9, 2025

Search Tags:#reconciliation #data-integrity #conflicts #research-analysis #multidimensional #evidence-tracing #fact-table

Ready to run

npx skills add https://github.com/genesis-agents/GenesisPod --skill reconciler

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Reconciler
Source: https://github.com/genesis-agents/GenesisPod/tree/main/backend/src/modules/ai-app/playground/mission/agents/reconciler
Command: npx skills add https://github.com/genesis-agents/GenesisPod --skill reconciler

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Reconciler merges multi-dimension researcher outputs into a single, coherent fact table, highlighting conflicts, overlaps, and gaps to enforce data integrity and actionable insights.

Core Features & Use Cases

Extract and normalize a fact table (entity, attribute, value, sources[]) from diverse research outputs.
Detect conflicts, overlaps, and gaps across dimensions; output structured resolutions and actionable guidance for downstream analysts.
Build and deduplicate a cross-dimension figure candidate pool to support evidence-backed narratives.

Quick Start

Provide researcher results to generate a structured fact table, detect conflicts/overlaps/gaps, and produce a concise reconciliationReport.

Frequently Asked Questions about Reconciler

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I reconcile conflicting data from multiple research outputs?▼

Reconciling conflicting research data involves merging multi-dimension outputs into a structured fact table that detects conflicts, overlaps, and gaps while enforcing data integrity.

What is cross-dimension reconciliation for research analysis?▼

It is a process that aggregates findings from multiple researchers to normalize entity, attribute, and value data into a structured, deduplicated fact table for downstream analysts.

How do I build a deduplicated figure candidate pool from diverse sources?▼

Building a deduplicated figure candidate pool involves extracting and normalizing fact tables from diverse research outputs to support evidence-backed narratives for competitive hypothesis analysis.

Does cross-dimension reconciliation work without external dependencies?▼

Yes, cross-dimension reconciliation works without external dependencies by enforcing data integrity through hard rules directly on provided researcher results to output a concise reconciliation report.

What is the best way to detect data gaps across multiple research dimensions?▼

The best way to detect data gaps is to aggregate findings from multiple researchers and enforce data integrity through hard rules, which highlights overlaps and conflicts in a structured reconciliation report.

When do I need to generate a reconciliation report for research analysis?▼

You need to generate a reconciliation report when you have multi-dimension research outputs that require conflict resolution and deduplication to produce a trusted narrative with traceable evidence.