← Back to Skills Marketplace
zhangbin2025

围棋实战选点

by tokener · GitHub ↗ · v1.1.0 · MIT-0
cross-platform ✓ Security Clean
120
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install weiqi-move
Description
智能提取并生成围棋实战选点题,支持恶手检测、实战对比、交互答题、试下演练及保存SGF功能。
Usage Guidance
This package appears to do what it claims and runs entirely locally. Before running: (1) ensure you trust the SGF files you feed it (they can include player metadata), (2) inspect the included Python files if you want extra assurance (they use only the standard library and perform parsing/writing), and (3) run it in a normal user account (no special privileges required). If you plan to run many or untrusted SGF files, consider rate-limiting or running in an isolated environment to avoid resource exhaustion from extremely large or malformed inputs.
Capability Analysis
Type: OpenClaw Skill Name: weiqi-move Version: 1.1.0 The weiqi-move skill bundle is a legitimate tool designed to extract Go (Weiqi) problems from SGF files and generate interactive HTML quizzes. The Python scripts (scripts/quiz.py and scripts/sgf_parser.py) implement a custom SGF tree parser and logic for identifying 'blunders' based on AI win-rate data without using any high-risk libraries or network calls. The generated HTML (templates/quiz.html) is self-contained, providing a canvas-based Go board and game logic for offline use. No evidence of data exfiltration, malicious execution, or prompt injection was found.
Capability Assessment
Purpose & Capability
The name/description (generate selection-questions from SGF with AI winrates, blunder detection, save SGF, produce an interactive HTML) matches the included scripts (SGF parser and quiz generator) and the HTML template. No unrelated capabilities (cloud, system admin, telemetry) are requested.
Instruction Scope
SKILL.md instructs running the local Python script on a provided SGF file to produce a single-file HTML; the runtime actions described (parse SGF, extract variations, create quiz HTML, save SGF) are consistent with the code. The instructions do not ask the agent to read unrelated system files, environment variables, or send data externally.
Install Mechanism
No install spec is provided and the code is pure Python using only the standard library, so nothing is downloaded or written to system-wide locations during install. This is the lowest-risk install model.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The code operates on an input SGF and writes an HTML output — required access is limited and proportionate.
Persistence & Privilege
The skill is not marked always:true and does not request persistent system privileges. It is user-invocable and will execute only when the user provides an SGF and runs the script/template generation.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install weiqi-move
  3. After installation, invoke the skill by name or use /weiqi-move
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
新增变化图提示引导功能; 控制按钮支持可展开面板; 输出增加胜负结果; 优化ABCD选点显示; 试下功能增加打劫和禁入点检测; 限制试下功能只能在当前答题局面对使用; 修复变化图描述准确性; 全面优化小屏幕适配和按钮间距; 优化做题页面布局和交互体验; 使用确定性随机种子确保结果一致性
v1.0.0
围棋实战选点 - 从AI分析棋谱中学习和练习;核心功能:智能选点题提取、恶手题检测、实战对比、交互式做题、试下模式、保存SGF、音效反馈
Metadata
Slug weiqi-move
Version 1.1.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is 围棋实战选点?

智能提取并生成围棋实战选点题,支持恶手检测、实战对比、交互答题、试下演练及保存SGF功能。 It is an AI Agent Skill for Claude Code / OpenClaw, with 120 downloads so far.

How do I install 围棋实战选点?

Run "/install weiqi-move" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is 围棋实战选点 free?

Yes, 围棋实战选点 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does 围棋实战选点 support?

围棋实战选点 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created 围棋实战选点?

It is built and maintained by tokener (@zhangbin2025); the current version is v1.1.0.

💬 Comments