Case Study Factory

把项目材料转成案例文章，提炼起点、动作、结果和复用价值。；use for case-study, content, storytelling workflows；do not use for 伪造客户背书, 公开敏感数据.

Security Scan

The skill is internally consistent with its stated purpose (turning project material into structured case-study drafts); it contains a local Python script and templates, no network calls or extra credentials, but you should avoid pointing it at directories with sensitive files before reviewing output.

Purpose & Capability

Name/description match the included artifacts: resources/spec.json, resources/template.md, examples, and a Python script that generates structured Markdown reports. Requiring python3 is proportional and expected.

Instruction Scope

SKILL.md confines behavior to generating drafts and audit reports and explicitly warns against fabricating endorsements or exposing sensitive data. It instructs the agent to run the bundled scripts/run.py when execution is allowed and to fall back to the templates otherwise — this matches the skill purpose. Caution: the script will read files under any directory you point it at and include extracted text in reports, so the agent should not be given a path that exposes unrelated secrets or private data.

Install Mechanism

No install spec; the skill is instruction-only plus a local script. No downloads or third-party package installs are present. This is low-risk and coherent for the described functionality.

Credentials

The skill requests no environment variables or credentials. It only requires python3. No secrets or external tokens are requested, which is proportionate to a document-processing skill.

Persistence & Privilege

always is false and the skill does not request persistent/privileged system presence. It does not modify other skills or system configuration. The agent can invoke the bundled script, which is normal given the skill's purpose.

Assessment

This skill appears to be what it says: a local case-study generator that uses the provided template and a Python script. Before running it: (1) review scripts/run.py yourself (it only uses the standard library, reads files, and produces Markdown); (2) avoid passing a top-level or home directory as the input path — the script will recursively read many text files and could include sensitive content in its report; (3) prefer --dry-run or run against the provided example input first; (4) anonymize or redact sensitive customer data before processing; (5) if you need guarantees about not writing files, run with --dry-run or inspect the output destination before allowing writes. If you want extra assurance, run the script in a sandboxed environment or review the rest of the (truncated) main() logic to confirm no unexpected behavior.

案例研究工厂

你是什么

你是“案例研究工厂”这个独立 Skill，负责：把项目材料转成案例文章，提炼起点、动作、结果和复用价值。

Routing

适合使用的情况

• 把这个项目写成案例文章
• 整理成可复用案例模板
• 输入通常包含：项目背景、动作、结果、证据
• 优先产出：项目背景、关键动作、对外版本注意事项

不适合使用的情况

• 不要伪造客户背书
• 不要公开敏感数据
• 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：

• 项目背景
• 关键动作
• 结果与指标
• 经验总结
• 可复用方法
• 对外版本注意事项

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

• 默认保留匿名化与保密提醒。
• 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。