← Back to Skills Marketplace
142
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install judge-3wan
Description
根据参谋官审核结果判定内容是否合格，输出“合格”或“不合格”两字作为最终结果
README (SKILL.md)
name: judge_3wan\r description: 三万裁判，最终判定内容是否合格\r version: 1.0.0\r \r
三万裁判\r
你是最终三万裁判，根据参谋官的审核结果做最终判定。\r 规则：\r
- 审核结论为【合格】→ 输出：合格\r
- 审核结论为【不合格】→ 输出：不合格\r 输出要求：\r
- 只输出两个字：合格 / 不合格\r
- 不允许加任何其他文字
Usage Guidance
This skill is simple and does what it says: convert an advisor's audit result into either 合格 or 不合格 and nothing else. Before installing, ensure the calling workflow always supplies an unambiguous audit result (so the skill can deterministically map it). Be aware the skill will not provide explanations, error messages, or logs — if you need justification/audit trail, add upstream checks or extend the instructions to handle missing or conflicting input and to surface errors for debugging.
Capability Analysis
Type: OpenClaw Skill
Name: judge-3wan
Version: 1.0.0
The skill bundle contains only metadata and instructions for an AI agent to act as a simple classifier. It maps audit results to a binary 'Qualified' or 'Unqualified' output in Chinese and lacks any executable code, network access, or malicious prompt instructions.
Capability Assessment
Purpose & Capability
Name, description, and runtime instructions all align: the skill's sole job is to make a final pass/fail decision and output 合格 or 不合格. There are no unrelated requirements or capabilities.
Instruction Scope
SKILL.md restricts output to only the two characters and specifies the mapping, which is scoped and low-risk. However it does not state how the '参谋官的审核结果' is provided, how to handle ambiguous/missing/conflicting inputs, or what to do on errors — this lack of context may cause unexpected behavior if upstream data is unclear.
Install Mechanism
Instruction-only skill with no install steps, downloads, or code files; nothing is written to disk or installed.
Credentials
No environment variables, credentials, or config paths are requested — proportional to the stated simple purpose.
Persistence & Privilege
Defaults used (not always:true). The skill does not request persistent presence or elevated privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install judge-3wan - After installation, invoke the skill by name or use
/judge-3wan - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of judge-3wan skill:
- Implements final content judgment based on reviewer conclusions.
- Outputs only “合格” or “不合格” with no additional text per decision rules.
Metadata
Frequently Asked Questions
What is 三万裁判?
根据参谋官审核结果判定内容是否合格，输出“合格”或“不合格”两字作为最终结果. It is an AI Agent Skill for Claude Code / OpenClaw, with 142 downloads so far.
How do I install 三万裁判?
Run "/install judge-3wan" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 三万裁判 free?
Yes, 三万裁判 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 三万裁判 support?
三万裁判 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 三万裁判?
It is built and maintained by Laton (@xiaozha87); the current version is v1.0.0.
More Skills