技能详情(站内镜像,无评论)
许可证:MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本:v1.0.0
统计:⭐ 0 · 19 · 0当前安装次数· 0历史安装次数
⭐ 0
安装量(当前) 0
🛡 VirusTotal :良性 · OpenClaw :可疑
Package:canonxu/my-stock-decide-execute-skill
安全扫描(ClawHub)
- VirusTotal :良性
- OpenClaw :可疑
OpenClaw 评估
This instruction-only orchestration skill is coherent with a trading-orchestrator purpose but relies on other unnamed skills to perform real trades, contains few built-in safety/authorization controls, and could cause unintended live orders if used or invoked autonomously.
目的
The skill's name/description match an orchestrator that: decide -> execute -> log. It requests no env vars or binaries which is reasonable because it delegates strategy/auth to other skills. However the SKILL.md assumes the presence of three other skills (my_stock_decide_skill, my_stock_longbridge_skill, my_stock_log_skill) that are not included or documented here; without them the orchestration is non-functional. It also claims it will not ha…
说明范围
The runtime instructions explicitly direct the agent to execute real trades (via my_stock_longbridge_skill) and to produce and act on order parameters. The skill relies on exact trigger phrases to avoid accidental execution, but that enforcement is purely an instruction-level rule (not programmatically enforced). There are no internal verification/authentication steps described beyond parameter completeness checks, and no requirement for expli…
安装机制
Instruction-only skill with no install steps or downloads; nothing is written to disk and there's no install risk.
证书
The skill requires no credentials itself, which can be reasonable for an orchestrator. But because it triggers an external trading skill to perform real orders, sensitive credentials and authorization must exist elsewhere. The absence of any documented authentication/authorization checks or audit hooks in this SKILL.md is a proportionality and safety concern: orchestration without its own safeguards can enable order execution if other skills e…
持久
always:false and default autonomous invocation is unchanged. Autonomous invocation of a trade-orchestrator is inherently higher-risk, but this flag alone is not a misconfiguration. The skill does not request persistent system-level presence or modify other skills' configs.
安装(复制给龙虾 AI)
将下方整段复制到龙虾中文库对话中,由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库(龙虾 AI)执行:为本机安装 OpenClaw 技能「My Stock Decide Execute Skill」。简介:当且仅当用户明确要求“交易决策并执行”或提到“my_stock_decide_execute_skill”时触发。这是一个严格流程控制的编排型交易执行技能,强…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装:https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/canonxu/my-stock-decide-execute-skill/SKILL.md
(来源:yingzhi8.cn 技能库)
SKILL.md
---
name: my_stock_decide_execute_skill
description: 当且仅当用户明确要求“交易决策并执行”或提到“my_stock_decide_execute_skill”时触发。这是一个严格流程控制的编排型交易执行技能,强制按照“决策 -> 交易挂单 -> 日志记录”三步顺序执行,且每步都要求显式输出结果并由用户确认或自动串联。
---
# my_stock_decide_execute_skill
## Purpose (目的)
实现从“宏观/个股决策分析”到“长桥证券真实挂单”,再到“系统操作日志归档”的全自动化端到端闭环执行。
## Core Rules & Triggers (触发条件与核心规则)
1. **触发条件**:只有在用户输入中**明确包含**“交易决策并执行”字眼,或直接呼叫本技能名称“`my_stock_decide_execute_skill`”时,才允许启动本流程。严禁在常规闲聊或仅询问分析时触发实际交易。
2. **强制串行执行 (Sequential Execution)**:流程必须严格按照以下三步进行。任何一步失败,必须立即终止并向老大报告,禁止跳步。
3. **分步显式输出 (Explicit Output per Step)**:每一步执行完毕后,必须在返回给老大的消息中明确列出该步的输出结果。
## Execution Flow (执行流程)
### Step 1: 交易决策 (Decision Making)
* **动作**:调用 `my_stock_decide_skill`,根据老大提供的持仓列表或特定标的进行分析。
* **强制输出**:必须提取并向老大输出该技能的决策步骤及结论(包括:标的代码、操作方向买/卖、情绪、目标价格、目标仓位比例/股数,以及详尽的操作原因)。
* *等待确认/串联*:确认决策结论已生成且包含有效操作建议。
### Step 2: 交易操作 (Trade Execution)
* **动作**:提取 Step 1 中的交易参数(代码、方向、价格、股数),严格按照这些参数调用 `my_stock_longbridge_skill` 进行实际的长桥证券挂单操作。
* **强制输出**:必须向老大输出交易操作的**挂单结果**。这必须包括长桥返回的成功/失败状态,若是成功,需包含订单号(Order ID)或挂单回执;若是失败,需包含具体的错误原因(如余额不足、价格偏离过大等)。
### Step 3: 日志记录 (Log Archiving)
* **动作**:将 Step 1 的决策详情和 Step 2 的挂单结果(包含成功状态及订单号)整合,调用 `my_stock_log_skill` 写入系统的交易操作日志中。
* **强制输出**:必须向老大输出“完成日志记录的条数”及简要的记录摘要(确认已成功入库)。
## Security & Verification (安全与校验)
* 在执行 Step 2(实际交易)之前,智能体必须在内部逻辑上核实提取的参数完整且合法,绝不允许市价盲打(除非策略中明确要求市价单且参数正确)。
* 本技能作为编排控制器,不负责具体的策略计算、长桥 API 鉴权或数据库连接,只负责准确调度相关基础技能。