whatsapp-faq-bot_skill

This skill builds and queries a Markdown-based FAQ knowledge base for WhatsApp, enabling automatic answer retrieval via fuzzy matching.
  • Python

2.5k

GitHub Stars

3

Bundled Files

2 months ago

Catalog Refreshed

3 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill openclaw/skills --skill whatsapp-faq-bot

  • _meta.json287 B
  • README.md1.6 KB
  • SKILL.md2.7 KB

Overview

This skill builds and queries a FAQ knowledge base from markdown files to power automatic answers for WhatsApp business bots. It provides import, add, search, export, and management commands so you can maintain a concise, searchable FAQ repository. The tool focuses on fast fuzzy matching and easy integration into messaging workflows.

How this skill works

The skill reads FAQ entries from markdown (H2 headings become questions; the following text becomes answers) or accepts manual additions. It indexes question text using a TF-IDF-like fuzzy matcher and returns ranked answers with confidence scores. Commands let you import, search with adjustable threshold/top results, list, export to markdown or JSON, and remove entries.

When to use it

  • You need automated answers for common customer questions on WhatsApp.
  • You want to import an existing FAQ from markdown into a searchable KB.
  • You need quick fuzzy matching to map user questions to prepared answers.
  • You want to export or back up FAQs as markdown or JSON.
  • You need a lightweight FAQ layer to integrate into a cron-driven agent or webhook.

Best practices

  • Structure source markdown with H2 headings for questions and clear answer bodies.
  • Keep questions concise and representative of how users ask them (include variants).
  • Tag or categorize entries if you expect similar questions but need manual filtering.
  • Tune the search threshold and top-N returned to balance precision vs recall.
  • Regularly export and backup the knowledge base to track changes.

Example use cases

  • Import a product FAQ markdown and serve automatic replies for order and shipping queries.
  • Add new entries from customer support logs to reduce repetitive answers.
  • Use the search command in an agent pipeline to respond with the top match and confidence score.
  • Export FAQs to JSON for integration with other services or analytics.
  • Run periodic stats to monitor KB growth and identify coverage gaps.

FAQ

It uses a TF-IDF-like fuzzy matcher on question text and returns confidence scores between 0.0 and 1.0; you can adjust the matching threshold and number of top results.

What markdown format is required to import FAQs?

Each FAQ must be an H2 heading (## Question) followed by the answer text; lists and paragraphs in the answer are supported.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational