emblem-token-swap
Execute token swaps across 6 blockchains via EmblemAI. Automatic route optimization and cross-chain bridging via ChangeNow. Use when the user wants to swap tokens, exchange crypto, convert between currencies, or bridge assets cross-chain.
- Installs
- 8.6K
- Last 24h
- —
- Trending rank
- —
- Security
- Warn
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/emblemcompany/agent-skills --skill emblem-token-swap- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads emblem-token-swap automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
Security audits
Independent scans of the skill's instructions and bundled files.
SKILL.md
The instructions your agent reads when the skill is triggered.
Emblem Token Swap
Guided token swapping powered by EmblemAI. Swap tokens on Solana, Ethereum, Base, BSC, Polygon, and Hedera with automatic routing. Cross-chain bridging via ChangeNow.
Requires: npm install -g @emblemvault/agentwallet
What This Skill Can Do
| Chain | Quote Tool | Swap Tool | Balance Tool | Token Search |
|---|---|---|---|---|
| Solana | splBuyIntent (quote mode) | splBuyIntent (swap mode) | solanaBalances | findSolanaSwapToken |
| Ethereum | ethSwapQuote | ethSwap | ethGetBalances | searchCryptoByName |
| Base | baseSwapQuote | baseSwap | baseGetBalances | searchEvmTokensBirdeye |
| BSC | bscSwapQuote | bscSwap | bscGetBalances | searchEvmTokensBirdeye |
| Polygon | polygonSwapQuote | polygonSwap | polygonGetBalances | searchEvmTokensBirdeye |
| Hedera | hederaTokensSwapQuote | hederaTokensSwap | hederaGetBalances | hederaFindTokens |
| Cross-chain | getChangeNowSwapQuote | swapUsingChangeNow | — | getChangeNowSupportedCurrencies |
Notes
- Solana uses
splBuyIntentfor both quotes and execution — it handles token lookup by name/symbol/CA and flexible amounts ($USD, SOL, or token quantity) - EVM chains (Ethereum, Base, BSC, Polygon) route through automatic DEX aggregation
- Cross-chain bridges via ChangeNow support 500+ currencies
- Bitcoin has balance support (
getBTCBalances) but no on-chain swap tools — use ChangeNow for BTC bridges
Quick Start
npm install -g @emblemvault/agentwallet
# Solana swap (uses splBuyIntent)
emblemai --agent --profile default -m "Use splBuyIntent to swap 5 SOL for USDC on Solana"
# Cross-chain bridge (uses ChangeNow)
emblemai --agent --profile default -m "Use getChangeNowSwapQuote to get a quote for bridging 0.05 ETH from Ethereum to SOL on Solana"
Trigger phrases:
- "Swap SOL to USDC"
- "Exchange ETH for USDT"
- "Convert my tokens"
- "Bridge tokens to Base"
Workflow: Safe Token Swap
Step 1: Check Balance
Confirm you have enough of the source token.
emblemai --agent --profile default -m "Use solanaBalances to show my Solana token balances"
Step 2: Get a Quote
Preview the swap before executing.
emblemai --agent --profile default -m "Use splBuyIntent to get a quote for swapping 5 SOL to USDC"
Step 3: Execute the Swap
emblemai --agent --profile default -m "Use splBuyIntent to swap 5 SOL for USDC on Solana"
Safe mode requires your confirmation before executing.
Step 4: Verify
Confirm the new balance.
emblemai --agent --profile default -m "Use solanaBalances to show my updated balances"
Swap Patterns
Solana Swaps
# By token amount
emblemai --agent --profile default -m "Use splBuyIntent to swap 0.5 SOL for USDC"
# By dollar amount
emblemai --agent --profile default -m "Use splBuyIntent to swap $20 of SOL for JUP"
# By token name
emblemai --agent --profile default -m "Use splBuyIntent to swap 100 USDC for BONK"
EVM Swaps
# Ethereum
emblemai --agent --profile default -m "Use ethSwapQuote to get a quote for swapping 0.01 ETH to USDC, then use ethSwap to execute"
# Base
emblemai --agent --profile default -m "Use baseSwapQuote to quote 0.005 ETH to USDC on Base"
# BSC
emblemai --agent --profile default -m "Use bscSwapQuote to quote 0.1 BNB to USDT on BSC"
# Polygon
emblemai --agent --profile default -m "Use polygonSwapQuote to quote 10 POL to USDC on Polygon"
Hedera Swaps
emblemai --agent --profile default -m "Use hederaTokensSwapQuote to get a quote for 100 HBAR to USDC, then use hederaTokensSwap to execute"
Cross-Chain Bridge
emblemai --agent --profile default -m "Use getChangeNowSwapQuote to quote bridging 0.1 ETH to SOL"
emblemai --agent --profile default -m "Use getChangeNowSupportedCurrencies to show available bridge currencies"
Communication Rules
Always include these in swap requests:
- Tool name — specify the exact tool for reliable routing
- Amount — dollar value or token quantity
- Source token — what you're swapping from
- Target token — what you're swapping to
| Bad | Good |
|---|---|
"swap sol usdc" | "Use splBuyIntent to swap 5 SOL for USDC" |
"buy eth" | "Use ethSwap to swap 100 USDC to ETH on Ethereum" |
"bridge" | "Use getChangeNowSwapQuote to bridge 0.05 ETH to SOL" |
Safety
All swaps require explicit user confirmation (safe mode). The agent will:
- Show you the swap details (amount, route, estimated output)
- Wait for your approval before executing
- Report the transaction result
Never bypasses confirmation for any value-moving operation.
Helper Script
bash scripts/swap-helper.sh
See scripts/swap-helper.sh for an interactive swap walkthrough.
Links
FAQ
What does the emblem-token-swap skill do?
Execute token swaps across 6 blockchains via EmblemAI. Automatic route optimization and cross-chain bridging via ChangeNow. Use when the user wants to swap tokens, exchange crypto, convert between currencies, or bridge assets cross-chain.
How do I install emblem-token-swap?
Run npx skills add https://github.com/emblemcompany/agent-skills --skill emblem-token-swap in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/emblem-token-swap/ (personal) or .claude/skills/emblem-token-swap/ (project).
Which AI agents can use emblem-token-swap?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is emblem-token-swap safe to install?
Security partners have reviewed it: Gen Agent Trust Hub passed; Socket passed; Snyk flagged items to review. As with any skill, read the SKILL.md and bundled scripts before installing.
Who maintains emblem-token-swap?
It is published by emblemcompany in emblemcompany/agent-skills. It has 8,595 recorded installs.
More from emblemcompany/agent-skills
emblem-portfolio-tracker
emblemcompany/agent-skills
Track crypto portfolio across 7 blockchains via EmblemAI. Aggregated balances with USD values, conditional trade P&L, and DeFi position tracking via Nansen. Use when the user wants to check their portfolio, see balances across chains, or review trade positions.
emblem-market-research
emblemcompany/agent-skills
Crypto market intelligence via EmblemAI. Trending tokens, on-chain analytics, derivatives data, and smart money tracking from CoinGecko, CoinGlass, Birdeye, and Nansen. Use when the user wants market data, trending tokens, derivatives analytics, or on-chain intelligence.
emblem-ai-agent-wallet
emblemcompany/agent-skills
Connect to EmblemVault and manage wallet-aware workflows via EmblemAI with review-first, operator-controlled actions. Supports Solana, Ethereum, Base, BSC, Polygon, Hedera, and Bitcoin. Also use when the user needs Emblem's auth model explained: one browser auth flow can log a user in with wallets, email/password, or social sign-in, while agent mode can auto-provision a profile-scoped wallet with no manual setup.
emblem-ai-prompt-examples
emblemcompany/agent-skills
Curated prompt and usage examples for research, portfolio review, quote requests, approval-gated drafts, NFT discovery, prediction-market analysis, and assistant workflows. Emphasis is review-first, trust-boundary-aware use of external data, and explicit confirmation before any value-moving action. Use when the user wants example prompts, phrasing guidance, or sample requests for end-user EmblemAI tasks.
emblem-ai-react
emblemcompany/agent-skills
React integration skill for EmblemAI's one-shot user management. Use when the user wants to add website authentication plus wallet-enabled users to a React app with EmblemAuthProvider, ConnectButton, social/email/wallet login, chat components, React auth hooks, React composition patterns, or Migrate.fun React hooks.
emblem-ai
emblemcompany/agent-skills
One-shot user management for apps, multi-chain wallet authentication, an AI-powered assistant, and AI app introspection. Use when the user wants to let website users sign in with wallets, email/password, or social login and give each user a wallet-enabled account, then embed EmblemAI chat surfaces, connect plugins, or add Reflexive observability. Provides React components, TypeScript SDKs, session-based authentication, and pointers to the React and agent-wallet skills for specialized workflows.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available