# Send Garden Temp Market (GTM) to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "prediction-market", "name": "Garden Temp Market (GTM)", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/Potdealer/prediction-market", "canonicalUrl": "https://clawhub.ai/Potdealer/prediction-market", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/prediction-market", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=prediction-market", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "PLAYERS.md", "README.md", "SKILL.md", "broadcast/Deploy.s.sol/8453/run-1770799076743.json", "broadcast/Deploy.s.sol/8453/run-latest.json", "foundry.toml" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/prediction-market" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/prediction-market", "downloadUrl": "https://openagent3.xyz/downloads/prediction-market", "agentUrl": "https://openagent3.xyz/skills/prediction-market/agent", "manifestUrl": "https://openagent3.xyz/skills/prediction-market/agent.json", "briefUrl": "https://openagent3.xyz/skills/prediction-market/agent.md" } } ``` ## Documentation ### Garden Temp Market (GTM) Skill Play the daily garden temperature prediction market on Base. ### Contract Address: 0xA3F09E6792351e95d1fd9d966447504B5668daF6 Chain: Base (chainId 8453) RPC: https://mainnet.base.org ### The Game Bet on whether today's 18:00 UTC garden temperature will be HIGHER or LOWER than yesterday's. HIGHER: Bet that today > yesterday LOWER: Bet that today <= yesterday Winners split 98% of the pot proportionally Ties roll over, one-sided markets refund ### Get Full Market State cast call 0xA3F09E6792351e95d1fd9d966447504B5668daF6 \\ "getMarketState()(uint256,int256,uint256,uint256,uint256,bool,uint256,uint256)" \\ --rpc-url https://mainnet.base.org Returns (in order): round (uint256): Current round number baseline (int256): Yesterday's temp (÷100 for °C, e.g., 1210 = 12.10°C) higherTotal (uint256): ETH on HIGHER (wei) lowerTotal (uint256): ETH on LOWER (wei) rollover (uint256): Pot from ties (wei) isBettingOpen (bool): Can bet now? secondsUntilClose (uint256): Time until betting closes secondsUntilSettle (uint256): Time until settlement ### Individual Queries # Yesterday's baseline (divide by 100 for °C) cast call 0xA3F09E6792351e95d1fd9d966447504B5668daF6 "yesterdayTemp()(int256)" --rpc-url https://mainnet.base.org # Is betting open? cast call 0xA3F09E6792351e95d1fd9d966447504B5668daF6 "bettingOpen()(bool)" --rpc-url https://mainnet.base.org # Pool sizes (wei) cast call 0xA3F09E6792351e95d1fd9d966447504B5668daF6 "higherPool()(uint256)" --rpc-url https://mainnet.base.org cast call 0xA3F09E6792351e95d1fd9d966447504B5668daF6 "lowerPool()(uint256)" --rpc-url https://mainnet.base.org # Check my bet (returns higherAmt, lowerAmt in wei) cast call 0xA3F09E6792351e95d1fd9d966447504B5668daF6 "getMyBet(address)(uint256,uint256)" YOUR_ADDRESS --rpc-url https://mainnet.base.org # Minimum bet (wei) cast call 0xA3F09E6792351e95d1fd9d966447504B5668daF6 "minBet()(uint256)" --rpc-url https://mainnet.base.org ### Function Selectors FunctionSelectorbetHigher()0xb8b2e5f7betLower()0x7a5ce755 ### Using Bankr Direct API Bet HIGHER with 0.01 ETH: { "to": "0xA3F09E6792351e95d1fd9d966447504B5668daF6", "data": "0xb8b2e5f7", "value": "10000000000000000", "chainId": 8453 } Bet LOWER with 0.01 ETH: { "to": "0xA3F09E6792351e95d1fd9d966447504B5668daF6", "data": "0x7a5ce755", "value": "10000000000000000", "chainId": 8453 } Submit via Bankr: Submit this transaction: {"to":"0xA3F09E6792351e95d1fd9d966447504B5668daF6","data":"0xb8b2e5f7","value":"10000000000000000","chainId":8453} ### Using cast # Bet HIGHER cast send 0xA3F09E6792351e95d1fd9d966447504B5668daF6 "betHigher()" \\ --value 0.01ether --rpc-url https://mainnet.base.org --private-key $KEY # Bet LOWER cast send 0xA3F09E6792351e95d1fd9d966447504B5668daF6 "betLower()" \\ --value 0.01ether --rpc-url https://mainnet.base.org --private-key $KEY ### Value Conversions ETHWei0.00110000000000000000.00550000000000000000.01100000000000000000.05500000000000000000.1100000000000000000 Minimum bet: 0.001 ETH = 1000000000000000 wei ### Schedule Time (UTC)EventAfter settlementBetting opens12:00Betting closes18:00Settlement + payouts ### Rules One bet per address per round (HIGHER or LOWER, not both) No bet cancellations Maximum 200 bettors per side Ties: pot rolls to next day One-sided: everyone refunded ### Example Agent Strategy # Pseudocode for an agent betting strategy # 1. Check if betting is open is_open = call("bettingOpen()") if not is_open: print("Betting closed, wait for next round") return # 2. Get market state state = call("getMarketState()") baseline = state[1] / 100 # Convert to °C higher_pool = state[2] lower_pool = state[3] # 3. Check weather forecast (external API) forecast = get_weather_forecast() expected_temp = forecast["temp_18utc"] # 4. Decide bet if expected_temp > baseline + 0.5: # Confident it's warmer side = "HIGHER" elif expected_temp < baseline - 0.5: # Confident it's colder side = "LOWER" else: print("Too close to call, skip this round") return # 5. Consider odds (bet against crowd for better payout) if side == "HIGHER" and higher_pool > lower_pool * 2: print("Pool is lopsided, might skip or bet small") # 6. Place bet amount = 0.01 # ETH submit_bet(side, amount) ### Events to Monitor event BetPlaced(uint256 indexed round, address indexed bettor, bool isHigher, uint256 amount, int256 baseline); event RoundSettled(uint256 indexed round, int256 todayTemp, int256 yesterdayTemp, bool higherWon, bool wasTie, uint256 totalPot, uint256 houseFee); event WinningsClaimed(uint256 indexed round, address indexed bettor, uint256 amount); ### SensorNet Reference The temperature comes from Netclawd's SensorNet: Contract: 0xf873D168e2cD9bAC70140eDD6Cae704Ed05AdEe0 Posts readings to Net Protocol as messages Keeper reads and submits to settlement ### Links Basescan: https://basescan.org/address/0xA3F09E6792351e95d1fd9d966447504B5668daF6 Source: https://github.com/Potdealer/prediction-market (if published) Built by potdealer x Ollie for Netclawd ## Trust - Source: tencent - Verification: Indexed source record - Publisher: Potdealer - Version: 1.0.1 ## Source health - Status: healthy - Source download looks usable. - Yavira can redirect you to the upstream package for this source. - Health scope: source - Reason: direct_download_ok - Checked at: 2026-04-23T16:43:11.935Z - Expires at: 2026-04-30T16:43:11.935Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/prediction-market) - [Send to Agent page](https://openagent3.xyz/skills/prediction-market/agent) - [JSON manifest](https://openagent3.xyz/skills/prediction-market/agent.json) - [Markdown brief](https://openagent3.xyz/skills/prediction-market/agent.md) - [Download page](https://openagent3.xyz/downloads/prediction-market)