Skill Routing Benchmark — 技能 — openclaw中文资讯站

技能详情（站内镜像，无评论）

测试多个 Skill 描述是否会路由冲突，并生成正例、反例与负向触发语句。；use for skills, routing, benchmark workflows；do not use for 只给模糊建议, 忽略高度相近的 skill.

综合技能

作者：vx：17605205782 @52YuanChangXing

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 · 23 · 0 current installs · 0 all-time installs

⭐ 0

安装量（当前） 0

🛡 VirusTotal：Pending · OpenClaw ：良性

Package：52yuanchangxing/skill-routing-benchmark

安全扫描（ClawHub）

VirusTotal：Pending
OpenClaw ：良性

OpenClaw 评估

The skill's code, instructions, and requirements are consistent with its stated purpose (local analysis of skill descriptions and generating example prompts); it requires only python3 and does not request unrelated credentials or network access.

目的

Name/description, SKILL.md, README, resources/spec.json, template, and scripts/run.py all align: the bundle is a local tool to analyze skill descriptions, find routing conflicts, and generate example prompts. Required binary is only python3 and no credentials/config paths are requested — this is proportionate for the stated purpose.

说明范围

SKILL.md explicitly tells the agent to either run the included script (python3 scripts/run.py) or synthesize output using the local spec/template. The script reads files from the provided input path (scanning many text file types) and produces structured reports. This stays within the described scope, but it does read arbitrary files from the supplied directory/input: avoid passing directories containing sensitive data or system configuration.…

安装机制

No install spec; this is an instruction-only skill with an included Python script that runs under the system python3. There are no downloads, external package installs, or archive extraction steps in the bundle — low install risk.

证书

The skill declares no required environment variables, no credentials, and no config paths. The runtime script operates on files supplied as input and does not embed network endpoints or request secrets.

持久

always is false and the skill does not request persistent system-level presence or modify other skills. It does not include steps to permanently change agent configuration. Autonomous invocation is allowed (platform default) but not combined with broad privileges.

综合结论

This skill appears coherent and low-risk: it runs a local Python script to analyze skill descriptions and produce structured reports. Before running: (1) review scripts/run.py yourself (it is included and readable); (2) avoid pointing the tool at directories or files that contain secrets or sensitive system configs — it will read and sample text files; (3) use the --dry-run and/or run in a sandboxed environment the first time; (4) verify outpu…

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「Skill Routing Benchmark」。简介：测试多个 Skill 描述是否会路由冲突，并生成正例、反例与负向触发语句。；use for skills, routing, benchmark workfl…。
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/52yuanchangxing/skill-routing-benchmark/SKILL.md
（来源：yingzhi8.cn 技能库）

SKILL.md

打开原始 SKILL.md（GitHub raw）

---
name: skill-routing-benchmark
version: 1.0.0
description: "测试多个 Skill 描述是否会路由冲突，并生成正例、反例与负向触发语句。；use for skills, routing, benchmark workflows；do not use for 只给模糊建议, 忽略高度相近的 skill."
author: OpenClaw Skill Bundle
homepage: https://example.invalid/skills/skill-routing-benchmark
tags: [skills, routing, benchmark, quality]
user-invocable: true
metadata: {"openclaw":{"emoji":"🚦","requires":{"bins":["python3"]},"os":["darwin","linux","win32"]}}
---
# Skill 路由基准测试器

## 你是什么
你是“Skill 路由基准测试器”这个独立 Skill，负责：测试多个 Skill 描述是否会路由冲突，并生成正例、反例与负向触发语句。

## Routing
### 适合使用的情况
- 帮我测试这些 Skill 会不会路由冲突
- 给我 negative examples
- 输入通常包含：多个 skill 描述与目标任务
- 优先产出：潜在冲突、正向例句、回归测试集

### 不适合使用的情况
- 不要只给模糊建议
- 不要忽略高度相近的 skill
- 如果用户想直接执行外部系统写入、发送、删除、发布、变更配置，先明确边界，再只给审阅版内容或 dry-run 方案。

## 工作规则
1. 先把用户提供的信息重组成任务书，再输出结构化结果。
2. 缺信息时，优先显式列出“待确认项”，而不是直接编造。
3. 默认先给“可审阅草案”，再给“可执行清单”。
4. 遇到高风险、隐私、权限或合规问题，必须加上边界说明。
5. 如运行环境允许 shell / exec，可使用：
   - `python3 "{baseDir}/scripts/run.py" --input <输入文件> --output <输出文件>`
6. 如当前环境不能执行脚本，仍要基于 `{baseDir}/resources/template.md` 与 `{baseDir}/resources/spec.json` 的结构直接产出文本。

## 标准输出结构
请尽量按以下结构组织结果：
- 潜在冲突
- 正向例句
- 反向例句
- 描述修改建议
- 优先级
- 回归测试集

## 本地资源
- 规范文件：`{baseDir}/resources/spec.json`
- 输出模板：`{baseDir}/resources/template.md`
- 示例输入输出：`{baseDir}/examples/`
- 冒烟测试：`{baseDir}/tests/smoke-test.md`

## 安全边界
- 适合 Skill 设计阶段使用。
- 默认只读、可审计、可回滚。
- 不执行高风险命令，不隐藏依赖，不伪造事实或结果。