Farming Planner

Plan yield farming and CAKE staking on PancakeSwap. Use when user says "farm on pancakeswap", "stake CAKE", "unstake CAKE", "stake LP", "unstake LP", "yield...

Things to check before installing: - Telemetry: SKILL.md runs a background curl to https://pancakeswap.ai with your agent name, OS and arch. If you care about leaking this metadata, ask the maintainer to remove or make it opt-in. - Missing env declarations: fetch-solana.cjs requires SOL_WALLET (a Solana public key) and other scripts honor CHAIN_FILTER/PROTOCOL_FILTER via env — the registry should list these. Don’t provide private keys; prefer hardware wallets or keystore approaches as the skill recommends. - Network behavior: the skill performs many network calls (CoinGecko, DexScreener, PancakeSwap explorer/infinity/configs, public RPCs). Confirm you’re comfortable with those external requests and verify the domains (e.g., pancakeswap.ai) point to legitimate project infrastructure. - Execution risk: the skill allows running cast/node/python commands and includes examples that could be used to send transactions if misused. Ensure the agent and environment won’t inadvertently run transaction-sending commands or receive private keys. - Audit & sandbox: review the included scripts yourself or run the skill in an isolated environment first. If you need Solana position checks, expect to supply SOL_WALLET (public key) explicitly and confirm the skill documents that. If you want, I can list the exact lines where SOL_WALLET is referenced, extract the Step 0 curl command for review, or propose a minimal safe invocation plan (network restrictions, no telemetry) you can ask the maintainer to adopt.

Type: OpenClaw Skill Name: pcs-farming-planner Version: 1.2.0 The skill bundle is a functional yield farming planner for PancakeSwap that aggregates APR and liquidity data from official APIs and on-chain RPC providers. It includes a telemetry ping in `SKILL.md` that sends basic system metadata (OS and architecture) to `pancakeswap.ai` for usage tracking, and the helper scripts (`fetch-farms.py`, `fetch-syrup-pools.py`) utilize `pip` for dependency management. While these behaviors involve network and shell activity, they are transparently documented, include explicit security warnings for the AI agent regarding private key safety, and lack any evidence of malicious intent or unauthorized data exfiltration.