---
name: xrpl-research-pro
version: 0.1.0
description: Deep, web-wide, freshness-ranked XRPL research — neural search + synthesis + structured findings, powered by Exa. Free to try (metered by the shared free-call tier; deep-reasoning depth is cost-guarded by FEATURE_XRPL_DEEP_REASONING).
license: MIT
homepage: https://hypermove.xyz
install: Fetch https://hypermove.xyz/api/skills/xrpl-research-pro?format=md and save it as xrpl-research-pro/SKILL.md in your agent's skills directory. No CLI, no npm, no MCP required.
---

# xrpl-research-pro

Deep, web-wide, freshness-ranked XRPL research — neural search + synthesis + structured findings, powered by Exa. Free to try (metered by the shared free-call tier; deep-reasoning depth is cost-guarded by FEATURE_XRPL_DEEP_REASONING).

## Run it (in your workspace — no MCP required)

This is a self-contained agent-skill. Once this SKILL.md is in your skills
directory it autoloads and runs locally by following the procedure below —
no HyperMove server or MCP connection is needed to install or run it.

**Inputs** (required: query):

```json
{
  "query": {
    "type": "string"
  },
  "since": {
    "type": "string",
    "description": "ISO date — freshness floor for \"latest\""
  },
  "depth": {
    "type": "string",
    "enum": [
      "fast",
      "deep-lite",
      "deep",
      "deep-reasoning"
    ],
    "default": "deep-lite"
  },
  "category": {
    "type": "string",
    "enum": [
      "research paper",
      "news",
      "docs",
      "any"
    ],
    "default": "any"
  }
}
```

**Procedure** — apply the HyperMove harness pattern locally:
1. Validate the inputs above and apply your cost / rate / prompt-injection policy.
2. Do the task: Deep, web-wide, freshness-ranked XRPL research — neural search + synthesis + structured findings, powered by Exa. Free to try (metered by the shared free-call tier; deep-reasoning depth is cost-guarded by FEATURE_XRPL_DEEP_REASONING).
3. Definition of done: output includes: summary, resources — if a check fails, feed the failure back and retry up to 1×, then stop.
4. This step needs live web data — use your own web/search tool, or the HyperMove MCP tool `data.call` (external-protocol layer).

Composes (harness primitives you apply above): Exa, lib/mcp/exa-client, lib/harness/output-enforcer.

## External protocol (optional, via HyperMove MCP)

The skill runs fully locally. Connect the HyperMove MCP only if you need the
external-protocol layer — live cross-chain data (`data.call`) or to make/receive
a payment (`payments.settle`, x402/mpp · USDC/RLUSD):

- add MCP server `https://hypermove.xyz/api/mcp` (transport: http)
- Claude Code: `claude mcp add --transport http hypermove https://hypermove.xyz/api/mcp`