Cron Job Guardian

检查 cron 或 timer 配置中的频率、幂等、重试、日志与并发风险。；use for cron, timer, ops workflows；do not use for 直接启停生产任务, 替代真正监控.

Security Scan

The skill is internally consistent: it statically audits cron/timer files using a bundled Python script, requests only python3, and does not ask for credentials or perform network actions.

Purpose & Capability

Name/description (cron/timer audit) align with the included files and behavior. The only required binary is python3, which is appropriate for running the bundled script. The script's functionality (pattern-based static scanning, directory/csv reporting, and templated output) matches the stated purpose.

Instruction Scope

SKILL.md restricts the skill to static auditing and explicitly warns against triggering tasks or making external changes. Runtime instructions recommend running the local script on a provided input path or, if exec is unavailable, producing output from templates—both are within the described audit scope. The script reads files under the provided input (including .sh/.py/.md etc.), which is expected for this audit use case; it does not attempt to read unrelated system-wide configs or hidden locations.

Install Mechanism

No install spec; this is instruction-only with a bundled script. No downloads, external package installs, or extraction from untrusted URLs are present. This minimizes installation risk.

Credentials

No environment variables, credentials, or config paths are requested. The skill runs locally on user-provided inputs only, which is proportionate to its stated auditing purpose.

Persistence & Privilege

always is false and the skill does not request persistent system privileges or modify other skills' configurations. It runs on demand and is not force-included.

Assessment

This skill appears to be a straightforward, local static auditor. Before running: (1) review scripts/run.py yourself (it is included) if you want to verify behavior; (2) provide only the directories/files you intend to audit (avoid pointing it at system or credential stores); (3) run first with --dry-run or in an isolated workspace to confirm outputs; and (4) if you need networked checks or automated remediation, do not rely on this skill—follow its warning to produce reviewable change plans rather than applying changes directly.

定时任务守门人

你是什么

你是“定时任务守门人”这个独立 Skill，负责：检查 cron 或 timer 配置中的频率、幂等、重试、日志与并发风险。

Routing

适合使用的情况

• 检查这些 cron 任务是否有风险
• 找重试和并发问题
• 输入通常包含：cron 文件、脚本目录或任务说明
• 优先产出：发现的任务、频率风险、验证步骤

不适合使用的情况

• 不要直接启停生产任务
• 不要替代真正监控
• 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：

• 发现的任务
• 频率风险
• 幂等风险
• 日志与告警
• 建议修改
• 验证步骤

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

• 只做静态审计，不触发定时任务。
• 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。