TronLink Skills

Overview

GitHub: https://github.com/TronLink/tronlink-skills

TronLink Wallet Skills is an AI Agent skill set that provides complete TRON blockchain wallet and DeFi functionality through natural language. Designed for Claude Code, Cursor, OpenCode, Codex CLI, and other AI agents.

Key Highlights: - 6 skills, 41 commands covering wallet, token research, market data, swaps, resources, and staking - Zero npm dependencies for all read-only operations (uses native Node.js 18+ fetch and crypto) - TRON-specific domain knowledge — dedicated handling of Energy + Bandwidth resource model - Multi-platform support — Claude Code, Cursor, OpenCode, Codex CLI, LangChain/CrewAI - Human-in-the-loop confirmation for all fund-moving operations - MCP server wrapper for structured AI agent integration

Why TronLink Skills?

TRON has a fundamentally different fee model than EVM chains. Instead of unified gas, TRON uses Energy (for smart contracts) and Bandwidth (for all transactions). No existing AI agent skill properly covers:

• TRON's unique resource model and cost optimization strategies
• Stake 2.0 (freezing TRX to obtain resources and earn rewards)
• Super Representative (SR) voting mechanics
• DEX aggregation across SunSwap V2/V3 and Sun.io
• The 14-day unfreezing wait period and its implications

TronLink Skills fills this gap with deep TRON-specific domain knowledge.

Architecture

Natural Language Input
         |
         v
AI Agent (Claude Code / Cursor / OpenCode / Custom)
         |
         v
tron_api.mjs (Node.js 18+, native fetch, 1,248 lines)
    ├── Zero dependencies for read operations
    ├── Optional: tronweb for signing
    ├── TronGrid HTTP API (public or with API key)
    └── Tronscan API for token metadata
         |
         v
Structured JSON → Agent interprets → Natural language response

The 6 Skills

1. tron-wallet (8 commands)

Wallet management and basic operations.

Features: Handles both Base58Check (T...) and hex address formats, supports known token symbols, auto-converts decimals.

2. tron-token (7 commands)

Token research and security analysis.

Features: Detects rug pulls, analyzes holder concentration, checks liquidity locks.

3. tron-market (8 commands)

Real-time market data and whale monitoring.

Features: Multi-DEX aggregation, smart money signal detection, K-line analysis.

4. tron-swap (5 commands)

DEX trading and swap execution.

Features: Aggregates liquidity from multiple sources, estimates Energy cost, handles multi-hop routes, enforces human-in-the-loop confirmation.

5. tron-resource (7 commands)

Energy & Bandwidth management — TRON-specific.

Features: Decision tree logic for cost optimization, tracks daily free bandwidth, calculates TRX burn equivalent.

6. tron-staking (8 commands)

Stake 2.0 and SR voting.

Features: Full Stake 2.0 support, 14-day unlock management, APY calculation, SR commission tracking.

Recommended Skill Workflows

Check & Transfer

tron-wallet (check balance) → tron-resource (estimate energy) → tron-wallet (send)

Research & Buy

tron-token (search) → tron-market (price/chart) → tron-resource (check energy) → tron-swap (execute)

Staking Flow

tron-wallet (check balance) → tron-staking (freeze) → tron-staking (vote) → tron-staking (claim)

Resource Optimization

tron-resource (check status) → tron-resource (estimate cost) → tron-staking (freeze) OR tron-resource (rent)

TRON Resource Model Reference

Energy vs. Bandwidth

Cost Examples

Stake 2.0 Key Facts

• Freeze TRX → Get Energy or Bandwidth → Vote for SR → Earn rewards
• Unfreezing has 14-day wait before withdrawal
• Votes reset if you unfreeze; must re-vote after re-freezing
• 1 frozen TRX ≈ 4.5 Energy/day
• Voting rewards claimable every 6 hours

Integration Methods

Method 1: Claude Code (Recommended)

# Clone and use directly
git clone <repo>
cd tronlink-skills
claude   # Auto-discovers SKILL.md files

No npm install needed for read-only operations.

Method 2: MCP Server

# Register as MCP server
claude mcp add tronlink -- node ~/.tronlink-skills/scripts/mcp_server.mjs

# Provides 25 MCP tools callable by Claude Desktop / Claude Code

Method 3: Manual CLI

# Direct command execution
node scripts/tron_api.mjs wallet-balance --address TAddress...
node scripts/tron_api.mjs token-price --token USDT
node scripts/tron_api.mjs swap-quote --from TRX --to USDT --amount 100

Method 4: Other AI Platforms

Quick Setup Script

# Auto-install for all AI environments
bash install.sh

# Clean uninstall
bash uninstall.sh

Configuration

Environment Variables

# Optional: TronGrid API key for higher rate limits
export TRONGRID_API_KEY="your-api-key"

# Optional: Switch network (default: mainnet)
export TRON_NETWORK="mainnet"    # or "shasta" / "nile"

# For signing operations (choose one):
export TRON_PRIVATE_KEY="your-hex-private-key"
# or
export TRON_PRIVATE_KEY_FILE="/path/to/keyfile.txt"

Network Support

Built-In Token Shortcuts

Project Structure

tronlink-skills/
├── README.md                          # Main documentation
├── package.json                       # Node.js manifest
├── install.sh                         # Auto-install for all AI environments
├── uninstall.sh                       # Clean uninstall
│
├── scripts/
│   ├── tron_api.mjs                   # Main CLI (1,248 lines, 41 commands)
│   └── mcp_server.mjs                 # MCP protocol server wrapper
│
├── skills/                            # Skill definitions (auto-discovered)
│   ├── tron-wallet/SKILL.md
│   ├── tron-token/SKILL.md
│   ├── tron-market/SKILL.md
│   ├── tron-swap/SKILL.md
│   ├── tron-resource/SKILL.md
│   └── tron-staking/SKILL.md
│
├── docs/
│   ├── claude-integration-guide.md    # 3 integration methods
│   ├── resource-model.md              # Energy & Bandwidth deep dive
│   ├── staking-guide.md               # Stake 2.0 & APY explanation
│   └── integration-guide.sh
│
├── .claude-plugin/                    # Claude Code plugin config
├── .cursor-plugin/                    # Cursor IDE plugin config
├── .opencode/                         # OpenCode config
├── .codex/                            # Codex CLI setup
├── .claude/                           # Pre-configured test commands
├── _meta.json                         # Metadata for skill registries
└── LICENSE                            # MIT

Dependencies

Security Model

Address Format Support

Both formats are supported and auto-normalized across all commands:

Key Design Decisions

1. Zero Dependencies by Default — Read-only operations don't require npm install, making it lightweight and instant for AI agents
2. Human-in-the-Loop for Fund Movements — All transactions that move funds require explicit user confirmation
3. TRON-Specific Domain Knowledge — Dedicated skills for Energy/Bandwidth and Stake 2.0, acknowledging TRON's unique architecture
4. Multi-Format Address Support — Handles both Base58Check and hex formats transparently
5. Token Symbol Resolution — Common tokens have built-in shortcuts; unknown contracts work by address
6. Cost Optimization Recommendations — The optimize-cost command provides personalized strategies
7. MCP Server Wrapper — Provides structured integration for Claude Desktop and modern AI agents

Quick Start

# 1. Clone
git clone <repo>
cd tronlink-skills

# 2. Use with Claude Code (no install needed for reads)
claude
> "What's the TRX balance of TAddress...?"
> "Show me the top trending tokens on TRON"
> "How much Energy do I need to send USDT?"
> "What's the best way to get Energy — freeze, rent, or burn?"

# 3. Or use directly
node scripts/tron_api.mjs wallet-balance --address TAddress...
node scripts/tron_api.mjs token-price --token USDT
node scripts/tron_api.mjs optimize-cost --address TAddress...