> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gdeltcloud.com/llms.txt
> Use this file to discover all available pages before exploring further.

# multi-surface-synthesis

> Combining GDELT Cloud + macro-finance + prediction markets to find the divergence; five canonical divergence shapes; weighting rules for conflicting signals

## Overview

Load the `multi-surface-synthesis` skill whenever you have data from two or more of GDELT Cloud, macro-finance, and prediction markets. It's the difference between a report that lists three surfaces side-by-side and one that finds the **divergence** between them — which is usually the actual analytical insight.

## GDELT Cloud structured data is the spine

The synthesis depends on having a classified, quantified, linked anchor — GDELT Cloud's structured Events, Stories, and metrics. Without that anchor, divergence framing collapses into impressionistic comparison.

GDELT Cloud gives you:

* A `significance` score on the underlying narrative (so you can claim "narrative is high/moderate/low" with a number)
* `magnitude`, `systemic_importance`, `propagation_potential` (so the divergence finding has structural anchoring)
* `category` / `subcategory` from the structured taxonomy (so the user knows what *kind* of event the synthesis surrounds)
* Linked entities and a date (which feed `SYMBOL_SEARCH` and prediction-market scenario phrasing)

## The canonical 5-step flow

```
1. ANCHOR              (gdelt-discover-and-drill)  →  date, actor, location, entity
2. NARRATIVE           (gdelt-discover-and-drill)  →  story significance, volume, trajectory
2b. DIRECTION (opt)    (macro-finance)             →  NEWS_SENTIMENT to confirm bullish/bearish/neutral
3. PRICED              (macro-finance)             →  market reaction in the relevant instrument
4. EXPECTED            (prediction-markets)        →  market-implied probability of the scenario
5. DIVERGE             (this skill)                →  where the surfaces disagree — that's the story
```

Step 5 is the value-add. Steps 1–4 produce data; step 5 produces analysis.

## The five divergence shapes

When narrative volume, market price, and implied probability disagree, the disagreement falls into one of five characteristic shapes. Recognize the shape and lead the brief with it.

| Shape                               | Pattern                                                                 | Lead                                                                                                                                                       |
| ----------------------------------- | ----------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **1. Priced-in**                    | High narrative + flat market + flat probability                         | "Despite N articles, instrument is unchanged and probability is stable. The market has fully discounted this scenario."                                    |
| **2. Market sees what news misses** | Low narrative + sharp market move + elevated probability                | "Narrative volume is low but the instrument has moved X over the last window. The market is pricing a development that public reporting has not captured." |
| **3. News-driven panic**            | High narrative + sharp market move + flat/declining probability         | "Significant market move on heavy coverage, but prediction markets show probability unchanged. The price action is sentiment-driven."                      |
| **4. Three-way confirmation**       | All three rising and aligned                                            | State the converging signal and focus on second-order effects.                                                                                             |
| **5. Surface-redirect**             | All three converge on a topic *adjacent* to the user's literal question | "You asked about A. All three surfaces are saying the answer to a better question — B — is the more important finding."                                    |

Shape 2 (early signal) and shape 5 (re-pose the question) are typically the highest-value findings.

## Weighting conflicting signals

When surfaces conflict, weight by:

1. **GDELT Cloud structured metrics first.** A Story with `significance > 0.4` and `linked_event significance > 0.4` outranks a Story with `significance 0.1` and high `article_count`.
2. **Confidence on GDELT events.** `confidence > 0.85` beats lower-confidence event coding.
3. **Liquidity / volume on prediction markets.** A probability with $50K open interest beats one with $500.
4. **Specificity of the contract.** A direct contract beats a proxy contract.
5. **Recency.** Last 7 days beats 30-day-aggregate signal for fast-moving stories.
6. **Source diversity.** 50 articles from 30 distinct domains beats 50 articles from 3 domains.

When the conflict can't be resolved, name it: *"Signals diverge; the higher-liquidity prediction-market reading suggests X (probability 0.55, \$87K OI), while the GDELT Story significance is 0.18. We weight the market read because the structured GDELT score doesn't support the narrative-volume framing."*

## When NOT to use this skill

* Single-surface tasks. Don't manufacture macro-finance and prediction-market hops to use the skill.
* Lookups. Specific quote, entity profile, or known contract terms.
* The data isn't there. If one surface returned empty, say so honestly — don't invent a divergence.