Doc Gap Finder

扫描文档目录、标题结构与文件分布，找缺失章节、重复内容和过时区域。；use for docs, audit, knowledge workflows；do not use for 读取无权限目录, 直接修改原文档.

Security Scan

The skill's code, instructions, and requirements are coherent with a read-only documentation-audit tool: it only needs python3, runs a local scanner script, and does not request unrelated credentials or install remote code.

Purpose & Capability

Name/description (document gap finder) align with the provided files and the included scripts: the repo contains a template, spec.json, examples and a Python script that performs directory/csv/pattern/skill audits. Requiring only python3 is proportionate.

Instruction Scope

SKILL.md correctly instructs running the local script and also supports producing output from the bundled template when execution isn't possible. The script legitimately reads files under a supplied input directory and extracts headings and file lists. Caution: if given an arbitrary root path (e.g., /), the script will read many file types (.md, .py, .sh, .json, etc.) — which is expected for a directory audit but could expose sensitive files if the user supplies paths they don't own. The SKILL.md warns about not scanning unauthorized directories; that warning should be followed.

Install Mechanism

No install spec; this is instruction/script-based and only requires python3 on PATH. No network downloads or external package installs are present.

Credentials

The skill requests no environment variables or credentials. The script includes heuristics to detect secret-like patterns and redacts matched secret substrings in its findings (limiting accidental disclosure in output). There is no unexplained access to unrelated services.

Persistence & Privilege

Skill is not always-enabled and does not request persistent privileges or modify other skills/system configs. It is user-invocable and runs locally when invoked.

Assessment

This appears to be a coherent local, read-only documentation-audit skill. Before running: (1) run it against a limited test directory or use --dry-run to verify output, (2) avoid pointing it at system or production roots (e.g., /, home of other users, or repos containing secrets), (3) review outputs before sharing (the tool redacts obvious secret-like strings but you should still verify), and (4) prefer running in a least-privileged environment (separate container or workspace) when scanning unknown repositories.

文档缺口发现器

你是什么

你是“文档缺口发现器”这个独立 Skill，负责：扫描文档目录、标题结构与文件分布，找缺失章节、重复内容和过时区域。

Routing

适合使用的情况

• 扫描 docs 目录找缺口
• 帮我看哪些文档可能过期或重复
• 输入通常包含：文档目录或文件夹路径
• 优先产出：目录概览、疑似缺口、优先级

不适合使用的情况

• 不要用来读取无权限目录
• 不要直接修改原文档
• 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：

• 目录概览
• 疑似缺口
• 重复与近似章节
• 建议补写内容
• 建议删除内容
• 优先级

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

• 默认只读扫描，不会删除或改写文件。
• 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。