platform-docs-get

Extract article content from official Salesforce documentation pages using browser-rendered retrieval.

Updated Jul 2, 2026
One-click install
npx skills add https://github.com/padjei/SF_Build --skill platform-docs-get-padjei
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: platform-docs-get
Source: https://github.com/padjei/SF_Build/tree/main/.claude/skills/platform-docs-get
Command: npx skills add https://github.com/padjei/SF_Build --skill platform-docs-get-padjei

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, playwright-stealth, and includes scripts (resource) components.

What problem does it solve? Official Salesforce documentation pages on developer.salesforce.com, help.salesforce.com, and lightningdesignsystem.com are often JavaScript-heavy or return shell content, so naive fetching fails to retrieve the real article body needed to ground answers in authoritative sources. ## Core Features & Use Cases - Browser-rendered extraction: Uses Playwright with deep shadow DOM traversal to hydrate client-rendered Salesforce Help and developer doc pages. - Shell and soft-404 detection: Rejects pages containing tokens like "Loading", "Sorry to interrupt", or "CSS Error" instead of treating them as evidence. - Structured output: Returns JSON with title, cleaned article text, intro, body, metadata blocks, sections, and official child links for follow-up retrieval. - Use Case: When asked how to configure Messaging for In-App and Web allowed domains, run the extractor against the official help.salesforce.com article URL to get the real article body instead of a shell page. ## Quick Start Ask the assistant to retrieve the official Salesforce documentation for a specific feature such as Lightning Message Service and ground the answer in the exact developer.salesforce.com or help.salesforce.com page.

Frequently Asked Questions about platform-docs-get

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract article text from help.salesforce.com pages?▼

Run the extract_help_salesforce.py script with the article URL, which renders the page in headless Chromium, waits for the Help app to hydrate, and traverses shadow roots to find the real article body. It returns structured JSON with cleaned text, sections, and metadata.

How to fetch JavaScript-heavy Salesforce developer documentation?▼

Use the extract_salesforce_doc.py wrapper with the official doc URL. It routes help.salesforce.com links to the dedicated Help extractor and uses browser-rendered extraction with content-selector scoring for developer, architect, admin, and Lightning Design System pages.

Does this work with lightningdesignsystem.com and architect.salesforce.com?▼

Yes, the wrapper supports official Salesforce-owned hosts including lightningdesignsystem.com, architect.salesforce.com, and admin.salesforce.com. URLs on unsupported hosts are rejected with an error.

Why does fetching a Salesforce Help article return only shell content?▼

Help pages are client-rendered, so plain HTTP fetches return tokens like "Loading" or "Sorry to interrupt" instead of the article. The extractor detects these shell signatures, marks the result as failed, and requires browser rendering to reach the real body.

What dependencies are required to run the extraction scripts?▼

The scripts require the Python packages playwright and playwright-stealth, listed in requirements.txt, plus the Playwright Chromium browser. An isolated runtime is installed under the user's home directory during setup.