Skip to content
Agentmart
Submit a tool

cross-domain-engine

Discover hidden correlations between disparate research domains using EVEZ OODA loop architecture.

Skill by EvezArt

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/evezart-cross-domain-engine

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Discover hidden correlations between disparate research domains using EVEZ OODA loop architecture. Use when finding novel cross-domain connections, detecting emerging technology intersections, cross-referencing threat patterns, identifying investment signals, or mining unclaimed innovations across fields. Covers signal observation, cross-domain scoring, verifiable correlation events, and append-only spine protocol.

Use cases: security, research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/cross-domain-engine

What's inside

Skill name
cross-domain-engine
Description
Discover hidden correlations between disparate research domains using EVEZ OODA loop architecture. Use when finding novel cross-domain connections, detecting emerging technology intersections, cross-referencing threat patterns, identifying investment signals, or mining unclaimed innovations across fields. Covers signal observation, cross-domain scoring, verifiable correlation events, and append-only spine protocol.
License
MIT
Instructions
53 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • files: referenced but missing: scripts/correlation_engine.py

Files (4)

  • origin.json · .clawhub/
  • SKILL.md
  • _meta.json
  • skill-card.md

SKILL.md (first lines)

# EVEZ Cross-Domain Correlation Engine

Discover hidden correlations between disparate research domains.

## When to Use

- Finding novel cross-domain connections nobody else would think to cross-reference
- Detecting emerging technology intersections before they're obvious
- Cross-referencing threat patterns across cybersecurity, finance, and materials science
- Identifying investment signals from undervalued research intersections
- Mining unclaimed patent territory between fields

## Architecture

The engine runs an EVEZ OODA loop:

1. **OBSERVE** — Scan domains, collect signals with intensity scores and keywords
2. **ORIENT** — Score cross-domain pairs by keyword overlap × intensity × base novelty
3. **BRANCH** — Generate verifiable correlation events with confidence scores
4. **ACT** — Commit to append-only spine (no edits, no deletes)
5. **COMPRESS** — Hash-chain the cycle into the immutable ledger

## Key Concepts

- **Spine Protocol**: Every event is written once. No updates. No deletes. The history IS the state.
- **Correlation Events**: Carry unique ID, confidence score, domain classification, and cryptographic hash
- **poly_c = τ × ω × topo / 2√N**: The EVEZ formula for topological proximity scoring
- **MAES Pattern**: Inspired by the autonomous discovery of 0.82 correlation between VQC research and FinCEN SAR patterns

## Verification

Every correlation event can be:
- Verified by checking the hash chain
- Audited via the append-only spine
- Falsified through the VERIFIED/PENDING/INVESTIGATING status system

## Formula

```
poly_c = τ × ω × topo / 2√N
```

Where:
- τ = temporal weight (recency of signals)
- ω = domain weight (importance of each domain)
- topo = topological proximity (keyword overlap between domains)
- N = number of observed signals (normalization factor)

## References

See `scripts/correlation_engine.py` for the full implementation.

From EvezArt/evez-os, MIT.

More from EvezArt/evez-os

Signals

Stars
1
Forks
0
Open issues
13
Last commit (this folder)
Jun 22, 2026 (4 months ago)
Last release
Jun 22, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from EvezArt

Cite this page

cross-domain-engine skill. Agent Mart. https://agentmart.dev/skills/evezart-cross-domain-engine (last updated 2026-10-24)