Uniswap Create Test Pool
v0.1.0Deploy a custom Uniswap pool on the local testnet with configurable parameters. Create pools with specific conditions (thin liquidity, wide spreads, exact tick ranges) to test agent behavior under controlled scenarios. Requires a running local testnet.
⭐ 0· 727·0 current·0 all-time
by@wpank
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (create local Uniswap test pools) align with the declared instructions and allowed tools (deploy_mock_pool, fund_test_account, get_pool_info, search_tokens). No unrelated environment variables, binaries, or config paths are requested.
Instruction Scope
SKILL.md stays on-topic: extract parameters, fund a test deployer, deploy a pool, and verify. One noteworthy behavior: it explicitly describes 'whale impersonation' / automatic funding of the deployer account. That is coherent for a local testnet but implies the skill (via the allowed tool) will perform account impersonation or node-level actions — expected for local test environments, but something to be aware of.
Install Mechanism
Instruction-only skill with no install spec or code files. Nothing is written to disk by the skill itself, so install risk is minimal.
Credentials
No environment variables, secrets, or external credentials are requested. The declared needs are proportionate to the described functionality.
Persistence & Privilege
The skill is not marked 'always' and has no explicit disableModelInvocation flag, so the model could invoke it autonomously when eligible. Because it performs actions on a local testnet rather than accessing external secrets, this is lower risk, but be aware it can trigger deployments/funding on your local testnet without additional manual confirmation unless your agent/platform enforces prompt-level approvals.
Assessment
This skill appears internally coherent for deploying Uniswap test pools on a local testnet. Before installing, ensure: (1) you run it only against an isolated local testnet (never mainnet); (2) you trust the platform-provided mcp__uniswap__* tools that will actually perform deployments and 'whale impersonation' (review those tool implementations if possible); (3) you accept that the model may autonomously call the allowed tools unless your agent enforces confirmation prompts; and (4) the skill has no published source/homepage in the metadata—if you need auditability, request or inspect the underlying tool implementations or the repository referenced in the README before use.Like a lobster shell, security has layers — review code before you run it.
latestvk977wj8524ktkddxv662wmz67h80wvb3
License
MIT-0
Free to use, modify, and redistribute. No attribution required.