Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问clear审计未展示

faq-builder常见问题解答生成器

Agent Skill

faq-builder 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

14,572

周安装

380

GitHub Stars

公开资料未说明

下载量

3,357
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:faq-builder(常见问题解答生成器)
来源仓库:https://github.com/eddiebe147/claude-settings
仓库路径:skills/faq-builder
安装命令:
npx skills add https://github.com/eddiebe147/claude-settings --skill 'FAQ Builder'
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/eddiebe147/claude-settings --skill 'FAQ Builder'

简介

faq-builder 将客服工单与文档转化为结构化常见问题数据库,提升自助服务能力。

  • 自动识别高频问题聚类并生成标准化问答对,支持层级化组织与关键词全文检索。
  • 内置新鲜度管理机制定期提示更新过期条目,确保 FAQ 内容与产品演进同步发展。
  • 输出格式兼容多种 CMS 系统导入要求,避免过度营销语气保持中立客观的服务口吻风格。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

FAQ Builder

Expert FAQ database creation system that transforms support tickets, documentation, and user interactions into comprehensive, searchable FAQ content. This skill provides structured workflows for identifying common questions, crafting clear answers, organizing content hierarchically, and maintaining FAQ freshness over time.

FAQs are the foundation of customer self-service. Well-built FAQ databases deflect support tickets, reduce customer frustration, and free up support teams for complex issues. This skill helps you build FAQs that actually get used and answer questions customers actually ask.

Built on best practices from support operations and content strategy, this skill combines data mining, content writing, and continuous improvement to create FAQs that scale with your product.

Core Workflows

Workflow 1: Question Discovery

Mine support data to identify what customers actually ask

  1. Support Ticket Analysis

- Export recent tickets (90 days recommended) - Categorize by topic/feature area - Identify recurring questions (3+ occurrences) - Note exact phrasing customers use - Track question frequency and trends

  1. Search Query Mining

- Analyze help center search queries - Identify zero-result searches (questions without answers) - Track most common search terms - Note failed search patterns - Map search queries to existing content gaps

  1. Customer Interaction Sources

- Live chat transcripts - Community forum posts - Social media mentions - Sales call objections - Onboarding call questions - NPS/CSAT survey comments

  1. Internal Knowledge Sources

- Support team tribal knowledge - Sales FAQ documents - Product documentation gaps - Engineering known issues - Feature release notes

Workflow 2: FAQ Structure Design

Organize questions into logical, navigable hierarchy

  1. Category Architecture

- Getting Started: Account setup, first steps, basic concepts - Features & Usage: How to use specific functionality - Billing & Payments: Pricing, invoices, upgrades - Account Management: Settings, security, data - Troubleshooting: Common issues and fixes - Integrations: Third-party connections

  1. Question Hierarchy

- Top-level categories (5-8 maximum) - Subcategories (3-7 per category) - Individual questions (5-15 per subcategory) - Related questions linking

  1. Navigation Design

- Search functionality (primary) - Category browsing (secondary) - Popular questions section - Recently updated section - Contextual FAQs (in-app placement)

Workflow 3: Answer Crafting

Write clear, helpful answers that resolve questions

  1. Answer Structure Template [Direct Answer] - 1-2 sentences answering the question directly [Explanation] - Why/how, if needed for context [Steps] - Numbered steps if action required [Screenshot/Visual] - If helpful [Related Questions] - Links to related content [Still Need Help?] - Escalation path
  2. Writing Guidelines

- Lead with the answer (no preamble) - Use customer language, not internal jargon - Keep answers scannable (bullets, headers) - Include visuals for complex processes - Provide concrete examples - Link to detailed docs for deep dives

  1. Answer Quality Checklist

- Answers the question directly in first sentence - Uses language customers use - Includes necessary steps/actions - Has visual aid if process is complex - Links to related content - Provides escalation path - Tested by non-expert

Workflow 4: FAQ Maintenance

Keep content accurate and fresh

  1. Update Triggers

- Product feature changes - UI/UX updates - Pricing changes - Policy updates - New common questions emerge - Answer quality issues flagged

  1. Review Cadence

- Weekly: Check for outdated screenshots/steps - Monthly: Review question frequency data - Quarterly: Full content audit - On Release: Update affected FAQs

  1. Quality Monitoring

- Track "Was this helpful?" feedback - Monitor escalation rates from FAQs - Analyze search-to-ticket correlation - Review support ticket references to FAQs

  1. Retirement Process

- Archive deprecated feature FAQs - Redirect old URLs - Update cross-references - Remove from search index

Workflow 5: FAQ Analytics & Optimization

Measure effectiveness and improve continuously

  1. Key Metrics

- Deflection Rate: % of visitors who don't create tickets - Search Success Rate: % finding answers via search - Helpful Ratings: % marked as helpful - Time on Page: Engagement indicator - Exit to Ticket: FAQs that fail to resolve

  1. Optimization Actions

- Low helpful rating → Rewrite answer - High exit-to-ticket → Answer incomplete - Low views but high ticket volume → Discovery problem - Zero-result searches → Content gap - High search but low click → Title/description mismatch

  1. A/B Testing

- Test answer formats (video vs. text) - Test question phrasing - Test category organization - Test CTA placement

Quick Reference

ActionCommand/Trigger
Analyze tickets for FAQs"Mine tickets for FAQ opportunities"
Generate FAQ from topic"Create FAQ for [feature]"
Audit FAQ coverage"Audit FAQ completeness"
Review FAQ metrics"Show FAQ performance"
Find content gaps"Identify FAQ gaps"
Rewrite poor FAQ"Improve FAQ for [question]"
Structure FAQ hierarchy"Design FAQ categories"
Check FAQ freshness"Audit FAQ currency"
Generate FAQ from docs"Convert docs to FAQ"
Merge duplicate FAQs"Consolidate FAQ duplicates"

Best Practices

Question Writing

  • Use the exact words customers use
  • Start with action verbs: "How do I...", "What is...", "Can I..."
  • Be specific: "How do I reset my password?" not "Password help"
  • Match search intent: question should match what users type
  • Avoid internal terminology

Answer Writing

  • Answer in the first sentence - no lead-up
  • Use second person ("you") not passive voice
  • Break complex answers into numbered steps
  • Include screenshots for UI-related answers
  • Keep answers concise (target under 300 words)
  • Link to detailed docs for comprehensive coverage

Organization

  • Limit top-level categories to 5-8
  • Most popular questions should be 2 clicks maximum
  • Cross-link related questions
  • Use consistent naming conventions
  • Enable robust search functionality

Maintenance

  • Assign ownership for each FAQ section
  • Create alerts for product changes affecting FAQs
  • Track "Was this helpful?" religiously
  • Archive rather than delete old content
  • Keep version history

Integration

  • Embed contextual FAQs in product UI
  • Surface FAQs in chatbot/support flow
  • Include in onboarding sequences
  • Reference in support macros
  • Add to knowledge base search

FAQ Templates

Simple Question Template

## [Question in customer language]

[Direct answer in 1-2 sentences.]

[Additional context if needed.]

**Related questions:**
- [Related FAQ 1]
- [Related FAQ 2]

*Last updated: [Date]*

Process Question Template

## How do I [action]?

[Brief explanation of what this does.]

### Steps

1. [First step]
   ![Screenshot if helpful]
2. [Second step]
3. [Third step]

### Notes
- [Any important considerations]
- [Common gotchas]

**Need help?** [Contact support link]

*Last updated: [Date]*

Troubleshooting Template

## [Problem statement as customer would phrase it]

This usually happens when [common cause].

### Quick fixes

1. **Try this first**: [Most common solution]
2. **If that doesn't work**: [Second option]
3. **Still having issues**: [Third option]

### When to contact support
If none of the above work, [contact support] with:
- [Information to include]
- [Error messages/screenshots]

*Last updated: [Date]*

Red Flags

  • High exit-to-ticket rate: Answer isn't resolving the question
  • Low search success: Content doesn't match search terms
  • Outdated screenshots: Product has changed
  • Internal jargon: Customers can't understand
  • No escalation path: Dead ends frustrate users
  • Duplicate content: Confuses and dilutes SEO
  • Orphaned FAQs: No navigation path to content

Integration Points

  • Support Ticketing: Auto-suggest FAQs before ticket creation
  • Chatbot: FAQ as first-line response source
  • In-App Help: Contextual FAQ widgets
  • Search: Unified search across FAQ and docs
  • Analytics: Track deflection and engagement
  • CMS: Structured content management

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Claude Code

26.88%
按下载量换算902

OpenCode

22.59%
按下载量换算758

Gemini CLI

19.38%
按下载量换算651

Antigravity

12.13%
按下载量换算407

Cursor

8.28%
按下载量换算278

windsurf

3.9%
按下载量换算131

安全审计

暂无安全审计结果可展示。

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源字段存在多来源差异,先按来源优先级自动处理,无法消解时进入异常复核队列。

来源信息

继续浏览同类 Skills