fetching-salesforce-docs
A retrieval skill for fetching and grounding AI agent responses in official Salesforce documentation. It provides a playbook for navigating developer, help, architect, and design system portals while handling JS-heavy or shell-rendered pages.
Is fetching-salesforce-docs safe to install?
Review the source first: our audit of fetching-salesforce-docs's source files found 0 shell commands, 5 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes Python scripts that perform network requests and utilize Playwright for browser-based rendering of external web pages.
How we audit skills: our security review methodology.
Who is this skill for?
AI agents requiring authoritative, grounded information from Salesforce-owned documentation domains.
What can you do with it?
- Retrieving Apex, API, and LWC documentation
- Fetching official Salesforce help articles for setup and configuration
- Accessing architect and admin best practices
- Extracting design tokens and component guidance from the Lightning Design System
- Grounding agent responses in official sources to avoid third-party summaries
How good is this skill?
Quality score: 5/10. The skill provides clear, actionable retrieval playbooks and specific rejection criteria for Salesforce documentation. It includes necessary scripts and dependency information.
What does the skill file contain?
# fetching-salesforce-docs Use this skill to retrieve and ground answers in **official Salesforce documentation on the public web**. This skill provides a **reliable online retrieval playbook** for Salesforce docs that are hard to fetch, especially `help.salesforce.com`, JS-heavy `developer.salesforce.com`, Lightning Design System docs on `lightningdesignsystem.com`, and other official Salesforce-owned doc pages such as `architect.salesforce.com` and `admin.salesforce.com`. Optional extraction scripts are available in `scripts/` — see the Reference File Index below. ## Scope | | | |---|--...
Frequently asked questions
Which Salesforce domains are supported?
The skill supports developer.salesforce.com, help.salesforce.com, architect.salesforce.com, admin.salesforce.com, and lightningdesignsystem.com.
How does the skill handle JS-heavy pages?
The skill uses Playwright-based extraction scripts to render and fetch content from pages that fail with naive fetching.
What should I do if a page is a shell or soft-404?
Reject the page as evidence. Look for the real article body or follow linked articles until the specific concept appears.
Are third-party blogs allowed as sources?
No. The skill requires official Salesforce-owned documentation unless the user explicitly requests otherwise.
Related skills
product-marketing
17.6KProduct managers, marketers, and founders who want to centralize their product positioning and audience information for AI-assisted marketing tasks
This skill creates and maintains a product marketing context document at .agents/product-marketing.md. It helps users define product positioning, target audiences, and messaging to ensure consistency across other marketing tasks.
firecrawl-lead-gen
12.8KSales professionals, recruiters, and researchers who need to compile prospect lists from public web sources
The firecrawl-lead-gen skill extracts prospect information from web directories and databases using the Firecrawl browser. It generates structured lead lists in JSON, CSV, or Markdown formats based on user-defined criteria.
firecrawl-seo-audit
12.8KSEO specialists, content marketers, and website owners who need automated, data-driven site audits
The firecrawl-seo-audit skill performs website SEO audits by mapping site structures, scraping key pages, and comparing content against target keywords and competitor search results.
meeting-minutes
9.2KTeams and individuals who need to document internal syncs, standups, design reviews, and planning meetings efficiently
The meeting-minutes skill generates structured, actionable meeting minutes from transcripts, recordings, or raw notes for internal meetings lasting 60 minutes or less. It enforces a strict schema that captures metadata, attendance, decisions, and action items with owners and due dates.