Messari Token Research logo

Messari Token Research

Organization
moonpay
messari-token-research

Full token research workflow using Messari x402 API. Fetches asset fundamentals, price history, sentiment signals, and news, then synthesizes a research brief via Messari AI. Total cost ~$1.00–$1.50 USDC per run.

Overview

Publishermoonpay
Repositoryskills
Skill namemessari-token-research
Stars
112
Forks
30
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by moonpay on GitHub. Read the source before you install it.

Installation

Install the Messari Token Research AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/moonpay/skills/tree/main/skills/messari-token-research
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/moonpay/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/messari-token-research .claude/skills/messari-token-research
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Messari Token Research in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Messari Token Research on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Messari Token Research is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Messari Token Research Workflow

Goal

Given a token slug (e.g. bitcoin, ethereum, solana), run a 5-step research workflow that pulls fundamentals, price action, signals, news, and finishes with an AI-synthesized brief.

Total cost per run: ~$1.00–$1.50 USDC on Base

Trigger phrases

  • "Research [token]"
  • "Give me a brief on [token]"
  • "What's the outlook on [token]?"
  • "Deep dive on [token]"

Step 0 — Preflight: check balance

bash
mp token balance list --wallet main --chain base --json

Ensure at least $2.00 USDC on Base before starting. If low:

bash
# Bridge USDC from Ethereum to Base
mp token bridge \
  --wallet main \
  --from-chain ethereum \
  --to-chain base \
  --token usdc \
  --amount 10

Step 1 — Asset fundamentals (~$0.05)

Replace {slug} with the token identifier (e.g. bitcoin, solana):

bash
mp x402 request \
  --method GET \
  --url "https://api.messari.io/v2/assets/details?assets={slug}" \
  --wallet main \
  --chain base

Extract: name, symbol, market cap, circulating supply, max supply, category, description, ATH, current price.


Step 2 — Price timeseries (~$0.18)

bash
mp x402 request \
  --method GET \
  --url "https://api.messari.io/v1/assets/timeseries/{slug}?granularity=daily&start_date=$(date -d "30 days ago" +%Y-%m-%d 2>/dev/null || date -v-30d +%Y-%m-%d)&end_date=$(date +%Y-%m-%d)" \
  --wallet main \
  --chain base

Extract: 30-day price trend, volatility pattern, notable pumps/dumps.


Step 3 — Sentiment signals (~$0.35)

bash
mp x402 request \
  --method GET \
  --url "https://api.messari.io/signal/v1/assets?assetSlug={slug}" \
  --wallet main \
  --chain base

Extract: mindshare score, sentiment direction, social volume trend.


Step 4 — Recent news (~$0.55)

bash
mp x402 request \
  --method GET \
  --url "https://api.messari.io/news/v1/news/feed?assets={slug}&limit=10" \
  --wallet main \
  --chain base

Extract: top 5 headlines, publication dates, sentiment of coverage.


Step 5 — AI research synthesis (~$0.25)

Feed all data from Steps 1–4 into Messari AI for a structured brief:

bash
mp x402 request \
  --method POST \
  --url "https://api.messari.io/ai/v2/chat/completions" \
  --body '{
    "model": "messari",
    "messages": [
      {
        "role": "system",
        "content": "You are a crypto research analyst. Given asset data, price action, signals, and news, produce a structured research brief with: 1) Summary, 2) Key metrics, 3) Bullish/bearish factors, 4) Risk factors, 5) Outlook."
      },
      {
        "role": "user",
        "content": "Research brief for {slug}. Fundamentals: {step1_output}. Price trend (30d): {step2_summary}. Signals: {step3_output}. News: {step4_headlines}"
      }
    ]
  }' \
  --wallet main \
  --chain base

Full workflow script

bash
#!/bin/bash
# messari-research.sh <slug>
# Usage: ./messari-research.sh bitcoin

SLUG="${1:-bitcoin}"
WALLET="main"
CHAIN="base"
BASE="https://api.messari.io"
OUT="$HOME/.config/moonpay/research/messari-${SLUG}-$(date -u +%Y%m%d-%H%M%S)"
mkdir -p "$(dirname "$OUT")"

echo "=== [1/4] Asset Fundamentals ==="
FUNDAMENTALS=$(mp x402 request --method GET \
  --url "${BASE}/v2/assets/details?assets=${SLUG}" \
  --wallet "$WALLET" --chain "$CHAIN")
echo "$FUNDAMENTALS" > "${OUT}-fundamentals.json"

echo "=== [2/4] Price Timeseries (30d) ==="
TIMESERIES=$(mp x402 request --method GET \
  --url "${BASE}/v1/assets/timeseries/${SLUG}?granularity=daily" \
  --wallet "$WALLET" --chain "$CHAIN")
echo "$TIMESERIES" > "${OUT}-timeseries.json"

echo "=== [3/4] Signals ==="
SIGNALS=$(mp x402 request --method GET \
  --url "${BASE}/signal/v1/assets?assetSlug=${SLUG}" \
  --wallet "$WALLET" --chain "$CHAIN")
echo "$SIGNALS" > "${OUT}-signals.json"

echo "=== [4/4] News ==="
NEWS=$(mp x402 request --method GET \
  --url "${BASE}/news/v1/news/feed?assets=${SLUG}&limit=10" \
  --wallet "$WALLET" --chain "$CHAIN")
echo "$NEWS" > "${OUT}-news.json"

echo ""
echo "Research data saved to ${OUT}-*.json"
echo "Total cost: ~\$1.13 USDC"
echo ""
echo "Next: pass this data to Messari AI for synthesis (Step 5)"

Output format

Present the final brief to the user as:

## [TOKEN] Research Brief
**Date:** [today]
**Cost:** ~$1.13 USDC

### Summary
[2-3 sentence overview]

### Key Metrics
- Price: $X (ATH: $Y, -Z% from ATH)
- Market Cap: $X (rank #N)
- 30d Performance: +/-X%
- Mindshare Score: X (trend: ↑/↓)

### Bullish Factors
- [factor 1]
- [factor 2]

### Bearish / Risk Factors
- [factor 1]
- [factor 2]

### Outlook
[1-2 sentence assessment]

Notes

  • Slug format: lowercase, hyphenated — bitcoin, ethereum, solana, chainlink
  • For very new tokens, Steps 2–3 may return empty — skip gracefully
  • AI synthesis (Step 5) can use all saved JSON files if running interactively
  • Payments are in USDC on Base — ensure ETH on Base for gas

Related skills

  • messari-x402 — Core endpoint reference
  • messari-alpha-scout — Find trending tokens before researching them
  • messari-deep-research — Deeper async report (10–15 min, more comprehensive)
  • moonpay-swap-tokens — Act on research by swapping tokens
  • moonpay-check-wallet — Verify USDC balance before running

Frequently asked questions

What does the Messari Token Research AI skill do?

Full token research workflow using Messari x402 API. Fetches asset fundamentals, price history, sentiment signals, and news, then synthesizes a research brief via Messari AI. Total cost ~$1.00–$1.50 USDC per run.

Why use Messari Token Research on TypingMind?

Because you install it once and use it with any model. Messari Token Research is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Messari Token Research in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/moonpay/skills/tree/main/skills/messari-token-research. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Messari Token Research?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Messari Token Research?

As many as you like. As long as a model supports skills, you can use Messari Token Research with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Messari Token Research AI skill free?

Yes. It is published on GitHub by moonpay under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇