← Back to Skills Marketplace
793
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install find-yield
Description
Find the highest-yield LP pools on Uniswap filtered by risk tolerance and minimum TVL. Use when the user asks about the best yields, highest APY pools, or where to earn fees.
README (SKILL.md)
Find Yield
Overview
Finds the highest-yield LP opportunities on Uniswap, filtered by risk tolerance, minimum TVL, and optionally capital amount. This is a focused version of scan-opportunities that only returns LP yield opportunities (no arbitrage or new-pool scanning).
Delegates to the opportunity-scanner agent with an LP-only filter.
When to Use
Activate when the user asks:
- "Best yield on Uniswap"
- "Highest APY pools"
- "Where to earn fees"
- "Best LP returns"
- "Top yielding pools"
- "Where can I earn the most?"
Parameters
| Parameter | Required | Default | Description |
|---|---|---|---|
| chains | No | All chains | Specific chains or "all" |
| riskTolerance | No | moderate | "conservative", "moderate", "aggressive" |
| capital | No | — | Available capital (helps rank appropriately) |
| minTvl | No | $100,000 | Minimum TVL for pool consideration |
Workflow
-
Extract parameters from the user's request.
-
Delegate to opportunity-scanner: Invoke
Task(subagent_type:opportunity-scanner)withtype: "lp"and the user's filters. The agent scans pools, ranks by fee APY adjusted for risk, and returns the top opportunities. -
Present results: Format as a ranked yield table.
Output Format
Top LP Yields (moderate risk, min $100K TVL):
| Rank | Pool | Chain | APY 7d | TVL | Risk |
| ---- | ------------------- | -------- | ------ | ------ | ------ |
| 1 | WETH/USDC 0.05% | Ethereum | 21.3% | $332M | LOW |
| 2 | ARB/WETH 0.30% | Arbitrum | 18.5% | $15M | MEDIUM |
| 3 | WETH/USDC 0.05% | Base | 15.2% | $45M | LOW |
| 4 | WBTC/WETH 0.30% | Ethereum | 12.1% | $120M | LOW |
| 5 | OP/WETH 0.30% | Optimism | 11.8% | $8M | MEDIUM |
Note: APY is based on 7-day historical fee revenue. Past performance
does not guarantee future returns. IL risk not included in APY figures.
Important Notes
- APY figures are historical, not guaranteed. Always consider IL risk.
- Higher APY often correlates with higher risk.
- Conservative risk tolerance filters out pools with \x3C $1M TVL and volatile pairs.
- Risk-adjusted yield accounts for estimated impermanent loss.
Error Handling
| Error | User-Facing Message | Suggested Action |
|---|---|---|
| No yields found | "No pools match your risk/TVL criteria." | Lower minTvl or increase risk tolerance |
| Chain unreachable | "Could not scan [chain]. Data may be incomplete." | Try again or narrow chain scope |
Usage Guidance
This skill appears to do what it says (find LP yields) but it defers actual scanning to an 'opportunity-scanner' agent whose behavior and requirements are not included. Before installing or invoking it, verify: 1) the source code of the opportunity-scanner and any remote repo referenced by the README (the npx install URL) to ensure no unexpected downloads or backdoors; 2) what RPC endpoints or third-party APIs the scanner uses and whether it will ask for API keys or other secrets; 3) that network calls will be limited to known, trusted endpoints (e.g., Uniswap subgraph, reputable indexers) and not to arbitrary personal servers. If you cannot review the scanner code, run it in a restricted environment or refuse installation. If you need help, request the opportunity-scanner's SKILL.md or repo before proceeding.
Capability Analysis
Type: OpenClaw Skill
Name: find-yield
Version: 0.1.0
The skill bundle is benign. It defines a clear purpose to find LP yields by delegating to an `opportunity-scanner` subagent. The `SKILL.md` instructions are straightforward, do not contain any prompt injection attempts to subvert the agent's behavior, nor do they instruct the agent to perform any malicious actions such as data exfiltration, unauthorized execution, or persistence. The installation methods in `README.md` are standard for OpenClaw skills. While passing 'user's filters' to a subagent could introduce vulnerabilities if the subagent or framework lacks robust input sanitization, this skill itself does not exhibit malicious intent or instruct the agent to exploit such vulnerabilities.
Capability Assessment
Purpose & Capability
Name, description, and runtime instructions all align: the skill only finds LP yield opportunities and explicitly delegates scanning to an 'opportunity-scanner' subagent with LP-only filters.
Instruction Scope
SKILL.md stays within the stated purpose and does not instruct reading local files or secrets. However it delegates the actual scanning to a separate 'opportunity-scanner' agent without specifying that agent's required data, APIs, or credentials — leaving ambiguity about what will run and what external calls will be made.
Install Mechanism
Registry metadata and package indicate this is instruction-only (no install spec), but README includes npx install commands that pull code from a GitHub path or Clawhub. That mismatch is notable: the skill as registered does not declare an install step, yet the README instructs installing remote code, which could fetch and execute additional code not visible in this bundle.
Credentials
This skill declares no required env vars or credentials — which is plausible for an instruction-only delegator — but scanning Uniswap across chains commonly requires RPC endpoints, API keys (The Graph, third-party indexing services, rate-limited providers), or other credentials. Those needs are not declared here, so installing or invoking the delegated scanner could prompt for or use secrets outside the skill's declared surface.
Persistence & Privilege
The skill does not request persistent presence (always:false), has no install spec in the registry, and does not modify other skills or system-wide settings in the provided instructions.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install find-yield - After installation, invoke the skill by name or use
/find-yield - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
Initial release of find-yield skill.
- Finds highest-yield Uniswap LP pools filtered by user-specified risk tolerance and minimum TVL.
- Delegates LP yield scanning to the opportunity-scanner agent with relevant filters.
- Presents results as a ranked yield table, including APY, TVL, and risk.
- Supports risk adjustment, TVL threshold, optional capital input, and multi-chain queries.
- Provides clear user-facing error handling for empty results or chain scan failures.
Metadata
Frequently Asked Questions
What is Uniswap Find Yield?
Find the highest-yield LP pools on Uniswap filtered by risk tolerance and minimum TVL. Use when the user asks about the best yields, highest APY pools, or where to earn fees. It is an AI Agent Skill for Claude Code / OpenClaw, with 793 downloads so far.
How do I install Uniswap Find Yield?
Run "/install find-yield" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Uniswap Find Yield free?
Yes, Uniswap Find Yield is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Uniswap Find Yield support?
Uniswap Find Yield is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Uniswap Find Yield?
It is built and maintained by wpank (@wpank); the current version is v0.1.0.
More Skills