Heurist Mesh Skill logo

Heurist Mesh Skill

OrganizationPopular
internet-court
heurist-mesh-skill

Access real-time crypto token data, DeFi analytics, wallet intelligence, project research, and blockchain insights through Heurist Mesh agents. Use when the user asks about token trends, DeFi protocols, wallet holdings, project due diligence, Twitter/X crypto sentiment, or deeper market analysis.

Overview

Publisherinternet-court
Repositoryinternet-court-skill
Skill nameheurist-mesh-skill
Stars
5.8K
Forks
106
Bundled files
4
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.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by internet-court on GitHub. Read the source before you install it.

Installation

Install the Heurist Mesh Skill 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.
  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/internet-court/internet-court-skill.git /tmp/internet-court-skill
mkdir -p .claude/skills
cp -r /tmp/internet-court-skill/vendored/heurist/heurist-mesh-skill .claude/skills/heurist-mesh-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Heurist Mesh Skill 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 Heurist Mesh Skill 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 Heurist Mesh Skill 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.

Heurist Mesh

Heurist Mesh is an open network of modular AI agent tools for cryptocurrency and blockchain data, accessible via a unified REST API.

When to Use

Use this skill when the user asks for crypto or Web3 intelligence that benefits from live data retrieval, including:

  • Token discovery, trending pairs, and market snapshots
  • DeFi protocol metrics, chain-level activity, and revenue/TVL comparisons
  • Wallet holdings, address labels, or NFT portfolio lookups
  • Twitter/X signal checks, project due diligence, and ecosystem research
  • Deeper market questions that should escalate to AskHeuristAgent

Recommended Agents and Tools

TrendingTokenAgent — Trending tokens and market summary

  • get_trending_tokens — Get trending tokens most talked about and traded on CEXs and DEXs
  • get_market_summary — Get recent market-wide news including macro and major updates

TokenResolverAgent — Find tokens and get detailed profiles

  • token_search — Find tokens by address, ticker/symbol, or name (up to 5 candidates)
  • token_profile — Get detailed token profile with pairs, funding rates, and indicators

DefiLlamaAgent — DeFi protocol and chain metrics

  • get_protocol_metrics — Get protocol TVL, fees, volume, revenue, chains, and growth trend
  • get_chain_metrics — Get blockchain TVL, fees, top protocols, and growth trends

TwitterIntelligenceAgent — Twitter/X data

  • user_timeline — Fetch a user's recent posts and announcements
  • tweet_detail — Get a tweet with thread context and replies
  • twitter_search — Search for posts and influential mentions on any topic

ExaSearchDigestAgent — Web search with summarization

  • exa_web_search — Search the web with LLM summarization, time and domain filters
  • exa_scrape_url — Scrape a URL and summarize or extract information

ChainbaseAddressLabelAgent — EVM address labels

  • get_address_labels — Get labels for ETH/Base addresses (identity, contract names, wallet behavior, ENS)

ZerionWalletAnalysisAgent — EVM wallet holdings

  • fetch_wallet_tokens — Get token holdings with USD value and 24h price change
  • fetch_wallet_nfts — Get NFT collections held by a wallet

ProjectKnowledgeAgent — Crypto project database

  • get_project — Look up a project by name, symbol, or X handle (team, investors, events)
  • semantic_search_projects — Natural language search across 10k+ projects (filter by investor, tag, funding year, exchange)

CaesarResearchAgent — Academic research

  • caesar_research — Submit a research query for in-depth analysis
  • get_research_result — Retrieve research results by ID

AskHeuristAgent — Crypto Q&A and deep analysis (Important: recommended for in-depth crypto topics)

  • ask_heurist — Submit a crypto question (normal or deep analysis mode)
  • check_job_status — Check status of a pending analysis job

Setup (must complete before making API calls)

At least one payment path must be configured. Do not call Mesh APIs until setup is verified.

Step 1: Choose one payment path

Step 2: Verify setup in .env

  • API key path: HEURIST_API_KEY is set and non-empty
  • x402 path: WALLET_PRIVATE_KEY is set, starts with 0x, and is 66 characters
  • Inflow path: INFLOW_USER_ID and INFLOW_PRIVATE_KEY are set and non-empty

If none are configured, STOP and ask the user to set up a payment method. Do not make API calls without valid credentials.

Step 3: Fetch schema before tool calls

Use mesh_schema to confirm parameter names, required fields, and pricing before calling any tool. Cache the result per agent for the session — schemas do not change between calls:

GET https://mesh.heurist.xyz/mesh_schema?agent_id=TokenResolverAgent&agent_id=TrendingTokenAgent

Default pricing is in credits (1 credit = $0.01). Add &pricing=usd for USD-denominated prices with x402 or Inflow.

Then use configured credentials in requests:

bash
# With API key
curl -X POST https://mesh.heurist.xyz/mesh_request \
  -H "Authorization: Bearer $HEURIST_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"agent_id": "TokenResolverAgent", "input": {"tool": "token_search", "tool_arguments": {"query": "ETH"}}}'

# With x402 — sign with cast (Foundry), no account or SDK needed
# See references/x402-payment.md for the full cast-based flow and helper script

Examples

Example 1: Trending tokens

User asks: "What tokens are trending right now?"

  1. Fetch schema: GET /mesh_schema?agent_id=TrendingTokenAgent
  2. Call tool: TrendingTokenAgent.get_trending_tokens
  3. Return top tokens with key metrics, then summarize notable moves

Example 2: Deep market question

User asks: "Give me a deep view on current market risk and opportunity."

  1. Run AskHeuristAgent.ask_heurist with the user question using deep mode
  2. Poll with AskHeuristAgent.check_job_status until complete

Error Handling

  • 401/403: Treat as credential issue; ask user to re-check .env values and do not continue calls with the same secret
  • 402: Payment required; follow the selected payment path (HEURIST_API_KEY, x402 flow, or Inflow approval)
  • status: "payment_pending" (Inflow): ask for approval status, then retry with backoff
  • 429 or 5xx: retry with exponential backoff and cap retries before surfacing failure details
  • Ambiguous token_search results: request user disambiguation before calling expensive downstream tools

Discover More Agents

For full agent discovery workflow and examples, see references/discover-agents.md.

  • All agents: https://mesh.heurist.ai/metadata.json
  • x402-enabled agents: https://mesh.heurist.xyz/x402/agents

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Heurist Mesh Skill AI skill do?

Access real-time crypto token data, DeFi analytics, wallet intelligence, project research, and blockchain insights through Heurist Mesh agents. Use when the user asks about token trends, DeFi protocols, wallet holdings, project due diligence, Twitter/X crypto sentiment, or deeper market analysis.

Why use Heurist Mesh Skill on TypingMind?

Because you install it once and use it with any model. Heurist Mesh Skill 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 Heurist Mesh Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/internet-court/internet-court-skill/tree/main/vendored/heurist/heurist-mesh-skill. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Heurist Mesh Skill?

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 Heurist Mesh Skill?

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

Is the Heurist Mesh Skill AI skill free?

It is published on GitHub by internet-court. Check the repository for licensing terms. 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 👇