技能详情（站内镜像，无评论）
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：v1.0.1
统计：⭐ 0 · 101 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：良性 · OpenClaw ：良性
Package：52yuanchangxing/api-contract-auditor
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：良性
OpenClaw 评估
The skill's code, instructions, and requirements are coherent with an on‑disk, read‑only API contract auditing tool that uses a local Python script and does not ask for external credentials or network access.
目的
Name/description (API contract auditing) align with included files and the local script. The script implements directory/csv/pattern/skill audits driven by resources/spec.json and template.md. Requiring only python3 is proportional to the stated purpose.
说明范围
SKILL.md instructs the agent to produce structured reports and, when allowed, run the local script with python3. The runtime instructions emphasize read-only auditing, listing files to inspect and producing reports; they do not instruct the agent to modify external systems or to send data to remote endpoints.
安装机制
No install spec; this is an instruction-only skill with a local Python script. No downloads or external package installs are requested. This is low-risk and proportional to the task.
证书
The skill does not request any environment variables, secrets, or credentials. It only needs a local python3 binary. The script reads local files (various text file extensions) which is expected for a directory audit but means sensitive files should be avoided when running.
持久
always: false and no persistent global modifications are requested. The script can write output to a file only when --output is provided (and can be run in --dry-run mode). The skill does not alter other skills' configs or request elevated platform privileges.
综合结论
This skill appears coherent and read-only: it inspects local files and generates a Markdown report via scripts/run.py and resources/template.md. Before running, review the script (scripts/run.py) yourself, and run it in a sandbox or on a copy of the repository to avoid accidentally scanning sensitive paths. Use --dry-run to avoid writing files, and avoid pointing the tool at large or system directories (it recursively reads many file types, in…
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「Api Contract Auditor」。简介：审查 API 文档、示例和字段定义是否一致，输出 breaking change 风险。；use for api, contract, audit workf…。
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/api-contract-auditor/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: api-contract-auditor
version: 1.0.0
description: "审查 API 文档、示例和字段定义是否一致，输出 breaking change 风险。；use for api, contract, audit workflows；do not use for 直接改线上接口, 替代契约测试平台."
author: OpenClaw Skill Bundle
homepage: https://example.invalid/skills/api-contract-auditor
tags: [api, contract, audit, breaking-change]
user-invocable: true
metadata: {"openclaw":{"emoji":"🔌","requires":{"bins":["python3"]},"os":["darwin","linux","win32"]}}
---
# API 契约审计器
## 你是什么
你是“API 契约审计器”这个独立 Skill，负责：审查 API 文档、示例和字段定义是否一致，输出 breaking change 风险。
## Routing
### 适合使用的情况
- 检查 API 文档和示例是否一致
- 找 breaking change 风险
- 输入通常包含：API 文档目录、OpenAPI 文本或示例
- 优先产出：扫描概览、字段一致性风险、验证清单
### 不适合使用的情况
- 不要直接改线上接口
- 不要替代契约测试平台
- 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：
- 扫描概览
- 字段一致性风险
- 示例覆盖度
- breaking change 风险
- 建议修复
- 验证清单
## 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
- 默认以只读审查方式输出报告。
- 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。