← Back to Skills Marketplace
72
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install a-share-observation-loop
Description
把结论落成每日检查清单、观察时点、通过失败动作和场景切换条件。适用于用户要求把观察项落下来、每天去看、或希望把研究结论转成重复执行的盘中与收盘检查框架。
README (SKILL.md)
A Share Observation Loop
Overview
这个 skill 把研究结论改写成“每天怎么查、查什么、看到什么就做什么”。它每次都基于新数据重建观察表，不依赖前一次会话记忆。
Hard Rules
- 这是无状态观察框架，不默认继承昨天的观察结果。
- 观察项必须能被当天数据验证，不能写成空泛口号。
- 每个观察项都要有“通过动作”和“失败动作”。
- 必须区分盘前、盘中、尾盘、收盘后四类检查点。
- 若盘面已经变了，观察清单也要跟着重排优先级。
When To Use
- 用户说“把观察项落下来”
- 用户要每日复核框架
- 已经有了组合和市场判断，想转成执行清单
- 用户要知道明天、后天每天应该盯哪些变量
Workflow
Step 1: 确认当前主场景
先拿最新盘面确认今天市场处在哪个环境里，再决定观察顺序。不要直接复用上次的清单。
Step 2: 分层观察
至少拆成五层：
- 宏观或事件触发层
- 指数与广度层
- 主线板块层
- 持仓层
- 备用候选层
Step 3: 设定检查时点
默认四个观察窗口：
- 开盘后快速确认
- 上午中段
- 午后关键时段
- 收盘复核
Step 4: 写动作规则
每个观察项都写成：
- 看什么
- 看多久
- 通过时做什么
- 失败时做什么
Step 5: 输出次日延续条件
告诉用户哪些条件出现时，应重新调用：
- 市场扫描
- 组合校准
- 动作路由
- 假设拆解
Tool Rules
- 观察项依赖最新数据，优先当日盘面
- 与持仓相关的观察项要对准用户真实持仓，不做泛化监控
- 若缺实时数据，可给观察框架，但要明确“需在盘中补数”
Output Contract
默认输出：
今日观察主轴检查时点逐项观察表通过动作失败动作何时重开分析
Practical Notes
- 观察清单宁可少而关键，不要列成无法执行的长表
- 同一主线内，优先盯龙头、成交、承接，而不是盯所有跟风票
- 若用户有明确持仓，观察清单里必须单列持仓项
Usage Guidance
This skill is coherent and low-risk in itself, but it relies on accurate market data and the user's holdings. Before using: (1) Confirm where the agent will get 'latest market data' and ensure those data sources are trusted; (2) Do not provide sensitive credentials unless you intend the agent to access a secured data feed — the skill does not request any keys; (3) If you plan to wire outputs into automated trading systems, carefully review the '通过动作'/'失败动作' to avoid unintended orders; (4) Test outputs on sample or paper-trading scenarios first to verify the checklist behaves as you expect.
Capability Analysis
Type: OpenClaw Skill
Name: a-share-observation-loop
Version: 1.0.0
The skill bundle is a purely instructional framework designed to help an AI agent organize stock market research into daily checklists and observation loops. It contains no executable code, scripts, or external dependencies. The instructions in SKILL.md and the template in daily-loop-template.md are strictly aligned with the stated purpose of financial analysis and do not contain any evidence of prompt injection, data exfiltration, or malicious intent.
Capability Assessment
Purpose & Capability
Name/description (convert research into daily observation/checklist for A‑share trading) matches the SKILL.md: stepwise guidance, templates, and output contract. No unrelated credentials, binaries, or installs are requested.
Instruction Scope
Runtime instructions stay on scope: define observation items, checkpoints, pass/fail actions, and when to re-run analysis. They require 'latest market data' and knowledge of user holdings, which is reasonable for this task and explicitly described; instructions do not direct reading unrelated system files or sending data to external endpoints.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest-risk install profile. Nothing is downloaded or written to disk by the skill itself.
Credentials
No environment variables, credentials, or config paths are requested. The need for market data and user holdings is explicit and proportionate; users must supply data but no secret keys are required by the skill itself.
Persistence & Privilege
always:false (default) and autonomous invocation not disabled — standard for skills. The skill does not request persistent system-wide changes or access to other skills' configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install a-share-observation-loop - After installation, invoke the skill by name or use
/a-share-observation-loop - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of "a-share-observation-loop" skill.
- Transforms research conclusions into actionable daily checklists and observation points.
- Differentiates four key observation windows: pre-market, intraday, end-of-day, and post-market.
- Enforces clear pass/fail actions for each observation item, with real-time market priority.
- Designed for users needing reliable, repeatable execution frameworks from research or market views.
- Output includes a concise focus list, prioritized actions, and guidance for when to rerun analysis.
Metadata
Frequently Asked Questions
What is a-share-observation-loop?
把结论落成每日检查清单、观察时点、通过失败动作和场景切换条件。适用于用户要求把观察项落下来、每天去看、或希望把研究结论转成重复执行的盘中与收盘检查框架。 It is an AI Agent Skill for Claude Code / OpenClaw, with 72 downloads so far.
How do I install a-share-observation-loop?
Run "/install a-share-observation-loop" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is a-share-observation-loop free?
Yes, a-share-observation-loop is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does a-share-observation-loop support?
a-share-observation-loop is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created a-share-observation-loop?
It is built and maintained by minguncle (@minguncle); the current version is v1.0.0.
More Skills