← Back to Skills Marketplace
Faq Distiller
by
vx：17605205782
· GitHub ↗
· v1.0.0
· MIT-0
168
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install faq-distiller
Description
从客服对话、评论、工单或聊天记录中提炼 FAQ，并按用户阶段分类。；use for faq, support, knowledge workflows；do not use for 暴露用户隐私, 替代工单系统.
README (SKILL.md)
FAQ 蒸馏器
你是什么
你是“FAQ 蒸馏器”这个独立 Skill，负责：从客服对话、评论、工单或聊天记录中提炼 FAQ，并按用户阶段分类。
Routing
适合使用的情况
- 从这些客服记录提炼 FAQ
- 按新手和进阶用户分类
- 输入通常包含：工单文本、问答记录、评论
- 优先产出：高频问题、按阶段分类、后续维护建议
不适合使用的情况
- 不要暴露用户隐私
- 不要替代工单系统
- 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
- 先把用户提供的信息重组成任务书，再输出结构化结果。
- 缺信息时，优先显式列出“待确认项”，而不是直接编造。
- 默认先给“可审阅草案”，再给“可执行清单”。
- 遇到高风险、隐私、权限或合规问题，必须加上边界说明。
- 如运行环境允许 shell / exec，可使用：
python3 "{baseDir}/scripts/run.py" --input \x3C输入文件> --output \x3C输出文件>
- 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：
- 高频问题
- 按阶段分类
- 标准回答
- 需升级问题
- 缺失文档
- 后续维护建议
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
- 建议对个人信息做脱敏后再输入。
- 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。
Usage Guidance
This bundle appears coherent and low-risk for its stated purpose. Before running: (1) review scripts/run.py yourself (it will read files you point it at); (2) do not pass system or home directories or any path containing secrets or PII—sanitize inputs first; (3) run the smoke test with the provided example-input.md to verify behavior; (4) run the script in a sandboxed environment if you need to scan third-party archives; and (5) if you plan to automate it, add policy checks to ensure it never runs against sensitive paths.
Capability Analysis
Type: OpenClaw Skill
Name: faq-distiller
Version: 1.0.0
The faq-distiller skill is designed to extract structured FAQ content from conversation logs and includes a Python utility script (scripts/run.py) for processing text. While the script contains broader auditing capabilities—such as directory scanning and regex-based detection of security risks like hardcoded secrets or 'curl|bash' patterns—these functions are used for reporting and analysis rather than execution or exfiltration. The SKILL.md instructions provide clear safety boundaries, emphasizing privacy protection and manual review, and the bundle lacks any indicators of malicious intent, unauthorized network access, or persistence mechanisms.
Capability Assessment
Purpose & Capability
Name, description, SKILL.md, resources/spec.json, template, examples, and scripts/run.py all consistently implement an offline FAQ-distillation / audit workflow. The only declared runtime requirement is python3, which the included script uses. No unrelated credentials, binaries, or unusual install steps are requested.
Instruction Scope
SKILL.md directs the agent to produce structured drafts and—when available—run the included script; the script operates on files, directories, or inline text and can scan many file types (.md, .py, .sh, .csv, etc.). This behavior is coherent for directory-audit use cases, but it means the script will read any path the user supplies (so passing system or sensitive directories could expose secrets). The SKILL.md does recommend desensitizing PII before input.
Install Mechanism
No install spec is provided (instruction-only skill with an included helper script). No remote downloads or package installs are declared. This is low-risk and proportionate for the functionality.
Credentials
The skill declares no required environment variables or credentials. The script does include heuristic patterns to detect 'secret-like' strings in files (for auditing), which is appropriate for an audit/reporting tool and does not itself request secrets.
Persistence & Privilege
The skill is not always-enabled and does not request elevated or persistent system presence. It does not modify other skills or system-wide settings; it only reads files the user points it at and can write an output file when asked.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install faq-distiller - After installation, invoke the skill by name or use
/faq-distiller - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
faq-distiller 1.0.0 初始发布
- 新技能：从客服对话、评论、工单或聊天记录中自动提炼 FAQ，并按用户阶段分类。
- 支持优先识别高频问题、分阶段、给出维护建议。
- 明确安全边界：禁止暴露用户隐私、禁止替代工单系统。
- 结构化输出：高频问题、标准回答、缺失文档等维度展示。
- 提供本地资源范例与审核流程，支持 dry-run 安全操作。
Metadata
Frequently Asked Questions
What is Faq Distiller?
从客服对话、评论、工单或聊天记录中提炼 FAQ，并按用户阶段分类。；use for faq, support, knowledge workflows；do not use for 暴露用户隐私, 替代工单系统. It is an AI Agent Skill for Claude Code / OpenClaw, with 168 downloads so far.
How do I install Faq Distiller?
Run "/install faq-distiller" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Faq Distiller free?
Yes, Faq Distiller is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Faq Distiller support?
Faq Distiller is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux, win32).
Who created Faq Distiller?
It is built and maintained by vx：17605205782 (@52yuanchangxing); the current version is v1.0.0.
More Skills