Wallet Twin Court
Use this skill to run the 后悔药 / Wallet Twin Court workflow inside OpenClaw. The job is not to produce many ideas. The job is to put one wallet on trial and compress the result into:
- - INLINECODE1
- INLINECODE2
- INLINECODE3
- INLINECODE4
- INLINECODE5
This skill is designed for OpenClaw x OKX OnchainOS.
Public endpoint:
When to use it
- - The user wants a pre-trade judgment for one Solana wallet.
- The user asks what action they are most likely to regret tomorrow.
- The user wants one verdict instead of many trade ideas.
- The user wants one explicit prosecuted action written down.
- The user wants a quote-backed hearing before execution.
- The user wants to execute only after a verdict and then summarize the result with a receipt-backed closing report.
Core law
Every response must obey this rule:
INLINECODE8
Required capabilities
Use OKX OnchainOS as the factual layer:
- -
Wallet / Portfolio for balances, holdings, stablecoin reserve, concentration, idle capital, and historical mistake context - INLINECODE11 for price, 24h move, and whether today is a high-temptation regime
- INLINECODE12 for quote, route comparison, and execution hearing
- INLINECODE13 for signature, confirmation, and receipt
Do not invent holdings, quotes, routes, or receipts.
Do not substitute this skill with miraix-wallet-roast.
Do not call https://app.miraix.fun/api/wallet-audit.
Do not append the wallet roast share card URL.
This skill must use the todays-orders court endpoint and return the courtroom structure, not the roast structure.
Workflow
- 1. Extract one Solana wallet address. If none is provided, ask for it.
- Run:
CODEBLOCK0
- 3. Base the answer on the returned JSON.
- Read the wallet dossier first:
- total wallet value
- top holdings
- stablecoin reserve
- concentration
- idle capital
- 5. Build the wallet twin's regret profile:
- what kind of mistake is most likely today
- whether today is a chase, revenge, over-rotation, or watch-only day
- 6. Prosecute exactly one action that should not happen today.
- Return exactly one verdict:
-
approve
-
probation
-
size-cap
-
reject
- 8. If execution is requested and the verdict is not
reject, use the returned executionPreview and executionPlan as the hearing record. - Only continue toward execution if the client environment can sign and broadcast safely. Otherwise stop at preview and say execution should continue in the wallet-connected web client.
- Close with a final report based on the actual state:
- preview report if not executed
- receipt-backed report if executed
Important returned fields:
- - INLINECODE24
- INLINECODE25
- INLINECODE26
- INLINECODE27
- INLINECODE28
- INLINECODE29
- INLINECODE30
- INLINECODE31
- INLINECODE32
Fixed output
Always return the result in this order:
- 1. INLINECODE33
- one-line profile
- wallet summary
- 2-3 evidence bullets
- 2. INLINECODE34
- one explicit action the court is prosecuting today
- 3. INLINECODE35
- exactly one verdict, or explicitly say no action is cleared
- 4. INLINECODE36
- quote, route, slippage, expected output
- label clearly as
preview until executed
- 5. INLINECODE38
- preview report if not executed
- receipt-backed report if executed
Output guidance
- - Keep the tone disciplined and procedural.
- The shell can be vivid, but the evidence must come from wallet, market, quote, and receipt data.
- Do not output
评分 unless that field truly exists in the court API output. - Do not output a roast-style
分享卡片 URL. - Do not rename the sections into wallet roast headings.
- If no clean setup exists, return
reject or watch-only and explain why. - Do not treat simulation as execution.
- If the user asks to execute, ask for final approval before broadcast.
钱包双生法庭
使用此技能在OpenClaw中运行后悔药 / 钱包双生法庭工作流。任务不是产生大量想法,而是将一个钱包送上法庭,并将结果压缩为:
- - 你的后悔体质
- 今日被起诉的操作
- 法庭裁决
- 执行前审理
- 判后报告
此技能专为OpenClaw x OKX OnchainOS设计。
公共端点:
- - 法庭API:https://todays-orders.vercel.app/api/todays-orders
使用时机
- - 用户希望对一个Solana钱包进行交易前判决
- 用户询问明天最可能后悔的操作是什么
- 用户想要一个裁决而非多个交易建议
- 用户想要一个明确的被起诉操作被记录下来
- 用户希望在执行前进行基于报价的审理
- 用户希望在裁决后才执行,然后通过收据支持的结案报告总结结果
核心法则
每个响应必须遵守此规则:
每个操作必须先经过法庭。高后悔度的交易不予放行。
必需能力
使用OKX OnchainOS作为事实层:
- - 钱包/投资组合:用于余额、持仓、稳定币储备、集中度、闲置资金和历史错误背景
- 市场:用于价格、24小时变动,以及判断今日是否为高诱惑行情
- 交易:用于报价、路径比较和执行审理
- 广播/状态:用于签名、确认和收据
不得虚构持仓、报价、路径或收据。
不得用miraix-wallet-roast替代此技能。
不得调用https://app.miraix.fun/api/wallet-audit。
不得附加钱包吐槽分享卡片URL。
此技能必须使用todays-orders法庭端点,并返回法庭结构,而非吐槽结构。
工作流程
- 1. 提取一个Solana钱包地址。如果未提供,则询问用户。
- 运行:
bash
curl -sS -X POST https://todays-orders.vercel.app/api/todays-orders \
-H Content-Type: application/json \
-d {walletAddress:<钱包地址>}
- 3. 基于返回的JSON给出答案。
- 首先读取钱包档案:
- 钱包总价值
- 前几大持仓
- 稳定币储备
- 集中度
- 闲置资金
- 5. 构建钱包双生的后悔档案:
- 今天最可能犯哪种错误
- 今天是追涨、报复、过度操作还是只看不动的日子
- 6. 起诉今天不应发生的一个明确操作。
- 返回一个明确的裁决:
- 批准
- 缓刑
- 规模限制
- 驳回
- 8. 如果请求执行且裁决不是驳回,使用返回的executionPreview和executionPlan作为审理记录。
- 仅在客户端环境能够安全签名和广播时才继续执行。否则停在预览阶段,并说明应在连接钱包的Web客户端中继续执行。
- 基于实际状态以最终报告收尾:
- 未执行则返回预览报告
- 已执行则返回收据支持的报告
重要返回字段:
- - todayIntel
- forbiddenOrder
- approvedOrder
- executionPreview
- nightDebrief
- sentenceLadder
- verdictCertificate
- machineView
- executionPlan
固定输出
始终按此顺序返回结果:
- 1. 你的后悔体质
- 一行简介
- 钱包摘要
- 2-3条证据要点
- 2. 今日被起诉的操作
- 法庭今日起诉的一个明确操作
- 3. 法庭裁决
- 一个明确的裁决,或明确说明无操作获批
- 4. 执行前审理
- 报价、路径、滑点、预期输出
- 在执行前明确标注为预览
- 5. 判后报告
- 未执行则返回预览报告
- 已执行则返回收据支持的报告
输出指导
- - 保持语气严谨且程序化。
- 外壳可以生动,但证据必须来自钱包、市场、报价和收据数据。
- 除非法庭API输出中确实存在评分字段,否则不要输出。
- 不要输出吐槽风格的分享卡片URL。
- 不要将章节重命名为钱包吐槽标题。
- 如果没有清晰的设置,返回驳回或只看不动并解释原因。
- 不要将模拟视为执行。
- 如果用户请求执行,在广播前要求最终确认。