liquidity-planner▌
uniswap/uniswap-ai · updated Apr 8, 2026
MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.
Plan and generate deep links for creating liquidity positions on Uniswap v2, v3, and v4.
Liquidity Position Planning
Plan and generate deep links for creating liquidity positions on Uniswap v2, v3, and v4.
Runtime Compatibility: This skill uses
AskUserQuestionfor interactive prompts. IfAskUserQuestionis not available in your runtime, collect the same parameters through natural language conversation instead.
Overview
Plan liquidity positions by:
- Gathering LP intent (token pair, amount, version)
- Checking current pool price and liquidity
- Suggesting price ranges based on current price
- Generating a deep link that opens in the Uniswap interface with parameters pre-filled
The generated link opens Uniswap with all parameters ready for position creation.
Note: Browser opening (
xdg-open/open) may fail in SSH, containerized, or headless environments. Always display the URL prominently so users can copy and access it manually if needed.
File Access: This skill has read-only filesystem access. Never read files outside the current project directory unless explicitly requested by the user.
Workflow
Step 1: Gather LP Intent
Extract from the user's request:
| Parameter | Required | Default | Example |
|---|---|---|---|
| Token A | Yes | - | ETH, USDC, address |
| Token B | Yes | - | USDC, WBTC, address |
| Amount | Yes | - | 1 ETH, $1000 |
| Chain | No | Ethereum | Base, Arbitrum |
| Version | No | V3 | v2, v3, v4 |
| Fee Tier | No | Auto | 0.05%, 0.3%, 1% |
| Price Range | No | Suggest | Full range, ±5%, custom |
If any required parameter is missing, use AskUserQuestion with structured options:
For missing chain:
{
"questions": [
{
"question": "Which chain do you want to provide liquidity on?",
"header": "Chain",
"options": [
{ "label": "Base (Recommended)", "description": "Low gas, growing DeFi ecosystem" },
{ "label": "Ethereum", "description": "Deepest liquidity, higher gas" },
{ "label": "Arbitrum", "description": "Low fees, high volume" },
{ "label": "Optimism", "description": "Low fees, Ethereum L2" }
],
"multiSelect": false
}
]
}
For missing token pair:
{
"questions": [
{
"question": "Which token pair do you want to provide liquidity for?",
"header": "Pair",
"options": [
{ "label": "ETH / USDC", "description": "Most popular pair, high volume" },
{ "label": "ETH / USDT", "description": "High volume stablecoin pair" },
{ "label": "WBTC / ETH", "description": "Blue chip crypto pair" },
{ "label": "Custom pair", "description": "Specify your own tokens" }
],
"multiSelect": false
}
]
}
Always use forms instead of plain text questions for better UX.
Step 2: Resolve Token Addresses
Resolve token symbols to addresses. See ../../references/chains.md for common tokens by chain.
For unknown tokens, use web search and verify on-chain.
UNTRUSTED INPUT: Web-Discovered Tokens
Tokens discovered via WebSearch are UNTRUSTED. Before proceeding with any web-discovered token:
- Label the source: Explicitly tell the user "This token address was found via web search, not provided by you"
- Warn about risks: "Web-discovered tokens may be scams, honeypots, or rug pulls"
- Require confirmation: Use AskUserQuestion to get explicit user consent before generating a deep link for a web-discovered token
- Show provenance: In the position summary table, include a "Token Source" row showing whether each token was "User-provided" or "Web-discovered (unverified)"
Never proceed with a web-discovered token without explicit user confirmation via AskUserQuestion.
Input Validation (Required Before Any Shell Command)
Before interpolating user-provided values into any shell command, validate all inputs:
- Token addresses MUST match:
^0x[a-fA-F0-9]{40}$ - Chain/network names MUST be from the allowed list in
../../references/chains.md - Amounts MUST be valid decimal numbers (match:
^[0-9]+\.?[0-9]*$) - Reject any input containing shell metacharacters (
;,|,$,`,&,(,),>,<,\,',", newlines)
Step 3: Discover Available Pools
Before fetching metrics, verify the pool exists and discover available fee tiers.
Find pools for a token using DexScreener:
# Get all Uniswap pools for a token (replace {network} and {address})
# IMPORTANT: Validate address matches ^0x[a-fA-F0-9]{40}$ and network is from allowed list
curl -s "https://api.dexscreener.com/token-pairs/v1/{network}/{address}" | \
jq '[.[] | select(.dexId == "uniswap")] | map({
pairAddress,
pair: "\(.baseToken.symbol)/\(.quoteToken.symbol)",
version: .labels[0],
liquidity: .liquidity.usd,
volume24h: .volume.h24
})'
Network IDs: ethereum, base, arbitrum, optimism, polygon, unichain
From the results, identify:
- Available pools and their addresses (multiple = different fee tiers)
- Pool TVL (
liquidity.usd) to assess liquidity depth - Version (v3 or v4) from
labels[0]
If no Uniswap pools found: The pair may not have an existing pool. Inform the user they would be creating a new pool and setting the initial price.
Step 4: Assess Pool Liquidity
Evaluate if the pool has sufficient liquidity:
| TVL Range | Assessment | Recommendation |
|---|---|---|
| > $1M | Deep liquidity | Safe for most position sizes |
| $100K - $1M | Moderate | Suitable for positions up to ~$10K |
| $10K - $100K | Thin | Warn user about slippage risk, suggest smaller positions |
| < $10K | Very thin | Warn strongly - high IL risk, price impact on entry/exit |
For thin liquidity pools, present a warning:
⚠️ **Low Liquidity Warning**
This pool has only ${tvl} TVL. Consider:
- Your position will be a significant % of the pool
- Entry/exit may move the price against you
- Impermanent loss risk is amplified in thin pools
- You may want to use a wider price range for safety
Step 5: Fetch Pool Metrics
Before suggesting ranges, fetch pool data for informed decisions. See references/data-providers.md for full API details.
Get pool APY and volume with DefiLlama:
# Find Uniswap V3 pools for a token pair
curl -s "https://yields.llama.fi/pools" | jq '[.data[] | select(.project == "uniswap-v3" and .chain == "Ethereum" and (.symbol | test("WETH.*USDC|USDC.*WETH")))]'
Response fields to use:
| Field | Use For |
|---|---|
apy |
Show expected yield |
tvlUsd |
Assess pool depth |
volumeUsd1d |
Estimate fee earnings |
volumeUsd7d |
Check volume consistency |
Get current prices with DexScreener:
# Get token prices from the pool data (already fetched in Step 3)
curl -s "https://api.dexscreener.com/token-pairs/v1/{network}/{address}" | \
jq '[.[] | select(.dexId == "uniswap")][0] | {
baseTokenPrice: .baseToken.priceUsd,
quoteTokenPrice: .quoteToken.priceUsd
}'
Compare fee tiers (if APY data available):
# Find all fee tier variants and compare APY
curl -s "https://yields.llama.fi/pools" | jq '[.data[] | select(.project == "uniswap-v3" and (.symbol | test("WETH.*USDC")))] | map({symbol, tvlUsd, apy, volumeUsd1d})'
If APIs are unavailable, fall back to web search for price estimates.
Step 6: Suggest Price Ranges
Based on current price and pair type, present range options using AskUserQuestion.
For major pairs (ETH/USDC, ETH/WBTC):
{
"questions": [
{
"question": "What price range do you want for your position? (Current: ~3,200 USDC/ETH)",
"header": "Range",
"options": [
{
"label": "±10% (Recommended)",
"description": "2,880 - 3,520 USDC. Higher fees, monitor weekly"
},
{ "label": "±20%", "description": "2,560 - 3,840 USDC. Balanced risk/reward" },
{ "label": "±50%", "description": "1,600 - 4,800 USDC. Rarely out of range" },
{ "label": "Full Range", "description": "Never out of range, lower fee efficiency" }
],
"multiSelect": false
}
]
}
For stablecoin pairs (USDC/USDT, DAI/USDC):
{
"questions": [
{
"question": "What price range for your stablecoin position?",
"header": "Range",
"options": [
{ "label": "±0.5% (Recommended)", "description": "0.995 - 1.005. Tight range, high fees" },
{ "label": "±1%", "description": "0.99 - 1.01. Standard for stables" },
{ "label": "±2%", "description": "0.98 - 1.02. Safer, lower fees" },
How to use liquidity-planner on Cursor
AI-first code editor with Composer
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
- ›Cursor installed and configured on your development machine
- ›Node.js version 16.0+ with npm package manager (verify with
node --version) - ›Active project directory or workspace where you want to add liquidity-planner
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
The skills CLI fetches liquidity-planner from GitHub repository uniswap/uniswap-ai and configures it for Cursor.
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
Verify installation
Confirm successful installation by checking the skill directory location:
Reload or restart Cursor to activate liquidity-planner. Access the skill through slash commands (e.g., /liquidity-planner) or your agent's skill management interface.
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
List & Monetize Your Skill
Submit your Claude Code skill and start earning
Use Cases▌
Task Automation & Efficiency
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Knowledge Enhancement
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Quality Improvement
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
Implementation Guide▌
Prerequisites
- ›Claude Desktop or compatible AI client with skill support
- ›Clear understanding of task or problem to solve
- ›Willingness to iterate and refine outputs
Time Estimate
15-45 minutes depending on use case complexity
Installation Steps
- 1.Install skill using provided installation command
- 2.Test with simple use case relevant to your work
- 3.Evaluate output quality and relevance
- 4.Iterate on prompts to improve results
- 5.Integrate into regular workflow if valuable
Common Pitfalls
- ⚠Expecting perfect results without iteration
- ⚠Not providing enough context in prompts
- ⚠Using skill for tasks outside its intended scope
- ⚠Accepting outputs without review and validation
Best Practices▌
✓ Do
- +Start with clear, specific prompts
- +Provide relevant context and constraints
- +Review and refine all outputs before using
- +Iterate to improve output quality
- +Document successful prompt patterns
✗ Don't
- −Don't use without understanding skill limitations
- −Don't skip validation of outputs
- −Don't share sensitive information in prompts
- −Don't expect skill to replace human judgment
💡 Pro Tips
- ★Be specific about desired format and style
- ★Ask for multiple options to choose from
- ★Request explanations to understand reasoning
- ★Combine AI efficiency with human expertise
When to Use This▌
✓ Use When
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid When
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
Learning Path▌
- 1Familiarize yourself with skill capabilities and limitations
- 2Start with low-risk, non-critical tasks
- 3Progress to more complex and valuable use cases
- 4Build expertise through regular use and experimentation
Discussion
Product Hunt–style comments (not star reviews)- No comments yet — start the thread.
Ratings
4.6★★★★★26 reviews- ★★★★★Dhruvi Jain· Dec 12, 2024
I recommend liquidity-planner for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
- ★★★★★Liam Ndlovu· Dec 4, 2024
Useful defaults in liquidity-planner — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- ★★★★★Zara Chen· Nov 23, 2024
I recommend liquidity-planner for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
- ★★★★★Oshnikdeep· Nov 3, 2024
Useful defaults in liquidity-planner — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- ★★★★★Ira Li· Nov 3, 2024
Keeps context tight: liquidity-planner is the kind of skill you can hand to a new teammate without a long onboarding doc.
- ★★★★★Ganesh Mohane· Oct 22, 2024
liquidity-planner is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
- ★★★★★Emma Rahman· Oct 22, 2024
liquidity-planner has been reliable in day-to-day use. Documentation quality is above average for community skills.
- ★★★★★Liam Nasser· Oct 14, 2024
liquidity-planner reduced setup friction for our internal harness; good balance of opinion and flexibility.
- ★★★★★Rahul Santra· Sep 5, 2024
liquidity-planner fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
- ★★★★★Pratham Ware· Aug 24, 2024
Registry listing for liquidity-planner matched our evaluation — installs cleanly and behaves as described in the markdown.
showing 1-10 of 26