sf-docs

What problem does it solve?

Many official Salesforce documentation pages are difficult to fetch reliably because they are client-rendered, use nested shadow DOMs, or present shell/placeholder content; this skill provides a deterministic playbook and tools to find and extract the real article content so answers can be grounded in authoritative sources.

Core Features & Use Cases

• Provides targeted retrieval heuristics for developer.salesforce.com, help.salesforce.com, architect.salesforce.com, admin.salesforce.com, and lightningdesignsystem.com.
• Includes a Help-specific extractor that performs browser-rendered extraction with deep shadow DOM traversal and heuristics to detect and reject shell pages.
• Supplies a lightweight wrapper script for other official Salesforce doc hosts, optional stealth mode, child-link awareness to follow relevant child pages, and structured JSON output with title, URL, host type, cleaned article text, and content links.
• Use cases: grounding API or Apex answers in official reference pages, extracting setup guidance from Help articles, and retrieving design system docs for UI guidance.

Quick Start

Use the sf-docs extractor to fetch a Salesforce doc URL, extract the article title and cleaned body text, and return the exact official URL and source type.