Agent skill

Sf Docs

by Jaganpro in Jaganpro/sf-skills

Official Salesforce documentation retrieval guidance. An agent skill from Jaganpro/sf-skills.

MITAuto-check passedSales & Support

Install Sf Docs

skills CLI
$ npx skills add Jaganpro/sf-skills --skill sf-docs -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Jaganpro/sf-skills sf-docs --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Jaganpro/sf-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/sf-docs .claude/skills/sf-docs && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sf-docs
GitHub stars
424
Token cost
~2.1k tokens
SKILL.md length
1,074 words
Files
6 (incl. scripts)
Skills in repo
36
Repo updated
First seen
Licence
MIT

At a glance

Official Salesforce documentation retrieval guidance. An agent skill from Jaganpro/sf-skills.

  • Works in 6 steps: Classify the request first → Identify the exact concept → Prefer targeted official retrieval → …
  • You need authoritative Salesforce docs from developer.salesforce.com
  • SKILL.md covers Core Goal, When to Use, Official Sources Only and Retrieval Workflow, plus 6 more sections
  • Runs Python scripts from its folder

What it does

Sf Docs is an agent skill from Jaganpro/sf-skills. Official Salesforce documentation retrieval guidance. Use when you need authoritative Salesforce docs from developer.salesforce.com or help.salesforce.com, especially when pages are JS-heavy, shell-rendered, or hard to extract with naive fetching.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts (for example `README.md`, `scripts/extract_help_salesforce.py` and `scripts/extract_salesforce_doc.py`).

It sits in Sales & Support, covering CRM management. It works with Salesforce. The repository describes itself as: [ARCHIVED — migrated to forcedotcom/afv-library] Salesforce Skills for Agentic Coding Tools — Apex, Flow, LWC, SOQL, Agentforce, Data Cloud, OmniStudio. Read-only archive; active… The licence is MIT.

When your agent uses it

  • You need authoritative Salesforce docs from developer.salesforce.com
  • Help.salesforce.com
  • Especially when pages are JS-heavy
  • Hard to extract with naive fetching

Example prompts

  • “/sf-docs”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Classify the request first
  2. Identify the exact concept
  3. Prefer targeted official retrieval
  4. Do not stop at broad landing pages
  5. For developer.salesforce.com
  6. For help.salesforce.com

What it can do on your machine

Read from SKILL.md and the folder at commit 53c9956. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 3 files in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sf Docs loads about 2.1k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 1,074 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from Jaganpro/sf-skills at commit 53c9956, republished under its MIT licence (© Jaganpro). 1,074 words, ~2,082 tokens.

Download SKILL.mdSave it as .claude/skills/sf-docs/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
sf-docs
description
Official Salesforce documentation retrieval guidance. Use when you need authoritative Salesforce docs from developer.salesforce.com or help.salesforce.com, especially when pages are JS-heavy, shell-rendered, or hard to extract with naive fetching.
license
MIT
metadata.version
0.4.0
metadata.author
Jag Valaiyapathy

sf-docs

Use this skill to retrieve and ground answers in official Salesforce documentation on the public web.

This skill is intentionally simple:

  • no local corpus
  • no indexing
  • no benchmark workflow
  • no helper CLI dependency
  • no PDF fallback

Its job is to provide 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.

An optional wrapper script is available at:

  • skills/sf-docs/scripts/extract_salesforce_doc.py

It automatically routes help.salesforce.com URLs into the dedicated Help extractor and supports other official documentation pages such as *.salesforce.com and lightningdesignsystem.com through a generic browser-rendered path. For bot-sensitive pages, it also supports best-effort optional stealth mode via --stealth when playwright-stealth is installed.

The dedicated Help extractor is also available directly at:

  • skills/sf-docs/scripts/extract_help_salesforce.py

Core Goal

Find the best official Salesforce HTML page online and extract enough real content to answer confidently.

If the evidence is weak, say so clearly instead of forcing a weak answer.

When to Use

Use sf-docs when a user asks for:

  • official Salesforce documentation
  • Apex, API, LWC, metadata, Agentforce, setup, or help articles
  • docs from developer.salesforce.com
  • docs from help.salesforce.com
  • pages that look JS-heavy, shell-rendered, or difficult to read with ordinary fetches

Official Sources Only

Prefer Salesforce-owned documentation sources:

  • developer.salesforce.com
  • help.salesforce.com
  • architect.salesforce.com
  • admin.salesforce.com
  • lightningdesignsystem.com
  • other relevant official Salesforce documentation pages when Salesforce uses them as the source of truth

Avoid third-party blogs, videos, or summary articles unless the user explicitly asks for them.

Do not fall back to PDFs.

Retrieval Workflow

1. Classify the request first

Before fetching anything, identify the likely doc family.

FamilyTypical SourceUse For
Developer docsdeveloper.salesforce.com/docs/...Apex, APIs, LWC, metadata, Agentforce developer docs
Help docshelp.salesforce.com/...setup, admin, product configuration
Architect/Admin docsarchitect.salesforce.com/..., admin.salesforce.com/...best practices, patterns, well-architected guidance, admin enablement
Design system docslightningdesignsystem.com/...SLDS, Cosmos, design tokens, component and styling guidance
Legacy atlas docsdeveloper.salesforce.com/docs/atlas.en-us.*older official guide and reference docs
2. Identify the exact concept

Extract the real target before you search:

  • exact API/class/method name
  • exact feature name
  • exact product phrase
  • exact setup concept

Examples:

  • Lightning Message Service
  • Wire Service
  • System.StubProvider
  • Agentforce Actions
  • Messaging for In-App and Web allowed domains
3. Prefer targeted official retrieval

Do not broad-crawl Salesforce docs.

Instead:

  1. identify the most likely official guide root or article
  2. if search is needed, restrict it to official Salesforce domains only
  3. fetch that official page
  4. check whether the exact concept actually appears on the page
  5. if not, inspect and follow the most relevant 1–3 official child links
  6. stop once you have grounded evidence
4. Do not stop at broad landing pages

A guide landing page is not enough unless it clearly contains the exact requested concept.

This is especially important for:

  • LWC docs
  • Agentforce docs
  • broad platform guide homepages
  • help landing pages that link to the real article
5. For developer.salesforce.com

Use this playbook:

  • start with the most likely official guide root
  • if the page is JS-heavy, prefer browser-rendered extraction
  • check whether the exact concept appears on the page
  • if the concept is missing, inspect official child links and follow the best matching 1–3 links
  • prefer exact concept pages over broad guide roots
  • legacy atlas pages are valid if they are the real official reference for the concept
6. For help.salesforce.com

Help pages often fail with naive fetching.

Use this playbook:

  • prefer exact articleView?id=... URLs when available
  • use browser-rendered extraction when plain fetch returns shell content
  • treat outputs like Loading, Sorry to interrupt, CSS Error, or mostly chrome/navigation text as failed extraction, not evidence
  • look for the real article body, not just header, nav, or footer text
  • reject shell pages and soft-404 pages such as:
    • "We looked high and low but couldn't find that page"
    • generic empty help shells
  • if starting from a nearby guide or hub page, follow linked Help articles until you reach the real article body
  • if extraction still fails after targeted retries, return the best official Help URLs you found and explicitly say that article-body extraction was unsuccessful
Show full SKILL.md (401 more words)Show less

Acceptance Rules

A page is good enough to answer from only when at least one of these is true:

  • the exact identifier appears on the page
  • the exact concept phrase appears on the page
  • multiple query-specific phrases appear in the correct official context

A page is not good enough when:

  • it is only a broad landing page
  • it is a shell page with little real article text
  • it is from the wrong product area
  • it does not contain the requested identifier or concept
  • it is a third-party explanation when an official page should exist

Rejection Rules

Reject these as final evidence:

  • broad guide homepages without the exact concept
  • release notes when a concept/reference page is expected
  • admin blog posts when developer docs are requested
  • third-party blogs when official docs are available
  • shell-rendered pages with no real article body
  • pages whose titles sound right but whose body does not contain the requested concept

Grounding Requirements

When answering, include:

  1. guide/article title
  2. exact official URL
  3. source type:
    • developer doc page
    • atlas reference page
    • help article page
  4. any caveat if extraction was partial or browser-rendered

If evidence is weak, say so plainly.

Examples

Example: Lightning Message Service

Do not stop at the general LWC guide root. Find the exact LWC page for Lightning Message Service or follow the most relevant child links from the LWC docs until the exact concept appears.

Example: Wire Service

Do not answer from the LWC homepage unless Wire Service is actually present there. Follow the relevant child doc page for wire service or wire adapters.

Example: Agentforce Actions

Do not answer from a broad Agentforce landing page or a blog post. Find the official Agentforce developer page for actions, or follow the best matching child pages from the official Agentforce docs.

Example: Messaging for In-App and Web allowed domains

Prefer official Help articles and browser-rendered extraction. Reject generic help shells. Follow linked Help articles from nearby official messaging docs if needed.

Example: System.StubProvider

Prefer the official Salesforce reference/developer page where the exact identifier appears. Do not substitute a broader Apex landing page if the identifier is absent.

Non-Goals

This skill should not:

  • maintain a local documentation corpus
  • rely on a local index
  • use PDF fallback
  • run benchmark workflows
  • depend on repo-specific scripts to be useful

Cross-Skill Role

Other sf-* skills should use sf-docs when they need authoritative Salesforce documentation instead of relying on generic search alone.

© Jaganpro, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts) in skills/sf-docs of Jaganpro/sf-skills.

  • SKILL.md
  • README.md
  • requirements.txt
  • scripts/extract_help_salesforce.py
  • scripts/extract_salesforce_doc.py
  • scripts/runtime_bootstrap.py

Open the folder on GitHubat commit 53c9956

Compare with similar skills

Sf Docs next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sf Docs compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sf Docs this skillJaganpro/sf-skills424—~2.1kAutomated safety check: PassMIT
Soql Lib Query Builderbeyond-the-cloud-dev/soql-lib154—~4.3kAutomated safety check: PassMIT
Soql Lib Selectorbeyond-the-cloud-dev/soql-lib154—~2kAutomated safety check: PassMIT
Dev SetupPortwood-Global-Solutions/Portwood125—~1.1kAutomated safety check: PassApache-2.0
Automation Sandbox Post Copy Configureforcedotcom/sf-skills1.1k—~5.3kAutomated safety check: NotesApache-2.0
Automation Sandbox Post Copy Configureforcedotcom/sf-skills1.1k—~5.4kAutomated safety check: NotesApache-2.0

Similar skills

  • Soql Lib Query Builder

    beyond-the-cloud-dev/soql-lib

    Builds Salesforce SOQL queries using the SOQL Lib fluent builder API (SOQL.cls).

    154 GitHub stars~4.3k tokensUpdated 5 days ago
    Sales & SupportAuto-check passed
  • Soql Lib Selector

    beyond-the-cloud-dev/soql-lib

    Creates Salesforce Apex selector classes using the SOQL Lib selector pattern.

    154 GitHub stars~2k tokensUpdated 5 days ago
    Sales & SupportAuto-check passed
  • Dev Setup

    Portwood-Global-Solutions/Portwood

    Get from a fresh clone of Portwood to a working, fully-tested Salesforce org.

    125 GitHub stars~1.1k tokensUpdated today
    Sales & SupportAuto-check passed
  • Apply a Salesforce sandbox post-copy automation JSON config against a target org.

    1.1k GitHub stars~5.3k tokensUpdated yesterday
    Sales & SupportAuto-check: notes
  • Apply a Salesforce sandbox post-copy automation JSON config against a target org.

    1.1k GitHub stars~5.4k tokensUpdated yesterday
    Sales & SupportAuto-check: notes
  • Google Maps Export

    gmapsscraper/google-maps-agent-skills

    Export Google Maps business data to CSV, JSON, or CRM format (HubSpot, Pipedrive, Salesforce).

    132 GitHub stars~1.2k tokensUpdated 4 mo ago
    Sales & SupportAuto-check passed

More from Jaganpro/sf-skills

All 36 skills in this repo
  • Agentforce session tracing extraction and analysis. An agent skill from Jaganpro/sf-skills.

    424 GitHub stars~1.8k tokensUpdated 5 mo ago
    Auto-check passed
  • Sf AI Agentscript

    Jaganpro/sf-skills

    Agent Script DSL for deterministic Agentforce agents. An agent skill from Jaganpro/sf-skills.

    424 GitHub stars~3.8k tokensUpdated 5 mo ago
    Auto-check passed
  • Sf Datacloud

    Jaganpro/sf-skills

    Salesforce Data Cloud product orchestrator for connect→prepare→harmonize→segment→act workflows.

    424 GitHub stars~2.7k tokensUpdated 5 mo ago
    Auto-check passed
  • Sf Diagram Mermaid

    Jaganpro/sf-skills

    Salesforce architecture diagrams using Mermaid with ASCII fallback.

    424 GitHub stars~1.4k tokensUpdated 5 mo ago
    Auto-check passed
  • Sf Diagram Nanobananapro

    Jaganpro/sf-skills

    AI-powered image generation for Salesforce visuals via Nano Banana Pro.

    424 GitHub stars~1.6k tokensUpdated 5 mo ago
    Auto-check passed
  • Sf Flow

    Jaganpro/sf-skills

    Creates and validates Salesforce Flows with 110-point scoring.

    424 GitHub stars~1.8k tokensUpdated 5 mo ago
    Auto-check passed

Works with

Categories

Questions about Sf Docs

What does Sf Docs do?

Official Salesforce documentation retrieval guidance. An agent skill from Jaganpro/sf-skills. Sf Docs is an agent skill from Jaganpro/sf-skills. Official Salesforce documentation retrieval guidance.

When should I use Sf Docs?

Sf Docs fits situations like: you need authoritative Salesforce docs from developer.salesforce.com; help.salesforce.com; especially when pages are JS-heavy; hard to extract with naive fetching.

How do I install Sf Docs in Claude Code?

Run `npx skills add Jaganpro/sf-skills --skill sf-docs -a claude-code`. Or copy the skill folder (skills/sf-docs in Jaganpro/sf-skills) into .claude/skills/sf-docs in your project. Claude Code loads it when a task matches its description.

How do I install Sf Docs in Codex?

Run `npx skills add Jaganpro/sf-skills --skill sf-docs -a codex`. Or copy the skill folder (skills/sf-docs in Jaganpro/sf-skills) into .agents/skills/sf-docs in your project. Codex loads it when a task matches its description.

Can I use Sf Docs in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Jaganpro/sf-skills --skill sf-docs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sf-docs, .gemini/skills/sf-docs, .github/skills/sf-docs and .opencode/skills/sf-docs in your project.

What does Sf Docs need to run?

Going by SKILL.md and its folder, Sf Docs needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Sf Docs access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sf Docs safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Sf Docs use?

Sf Docs is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sf Docs use?

About 2.1k tokens (SKILL.md is roughly 8.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Sf Docs?

Skills that share tags, products or a category with Sf Docs: Soql Lib Query Builder (beyond-the-cloud-dev/soql-lib, 154 stars), Soql Lib Selector (beyond-the-cloud-dev/soql-lib, 154 stars), Dev Setup (Portwood-Global-Solutions/Portwood, 125 stars) and Automation Sandbox Post Copy Configure (forcedotcom/sf-skills, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sf Docs?

Jaganpro (a GitHub user) maintains it in Jaganpro/sf-skills, which has 424 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on April 27, 2026.

Source: Jaganpro/sf-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.