💙 Community-powered agentic coding knowledge, shared by a Salesforce Certified Technical Architect (CTA)
A collection of reusable skills for Agentic Salesforce Development, enabling AI-powered code generation, validation, testing, debugging, and deployment. Built for Claude Code with planned support for other agentic coding tools.
16 skills • 60+ templates • 520+ validation points • LSP integration
Skills are portable knowledge packs that supercharge AI coding agents with domain expertise.
Think of skills as "installable superpowers" for your agentic coding tool. Instead of repeatedly explaining Salesforce best practices to your AI assistant, a skill pre-loads that knowledge so the AI becomes an instant expert.
sf-apex/
├── SKILL.md # 🧠 The brain - prompts & instructions
├── templates/ # 📁 Code templates & patterns
├── hooks/ # ✅ Validation scripts
└── examples/ # 📖 Usage examples
💡 Tip: Skills are open-source and composable. You can fork, customize, or create your own!
🚀 Stop explaining Salesforce patterns. Start building.
1. Instant Expertise — AI knows Trigger Actions Framework, Flow bulkification, deployment best practices from the first message.
2. Automatic Validation — Every Apex class, Flow, and agent script is scored against 100-150 point rubrics. Catch anti-patterns before deployment.
3. Built-in Templates — 50+ production-ready templates across Apex, Flow, Metadata, Agentforce, and more.
4. Tool Orchestration — "Deploy to production" becomes a single command. Skills handle sf CLI complexity.
5. Context Efficiency — Skills load only when invoked, saving ~2000 tokens per conversation vs. pasting prompts.
| Before | After |
|---|---|
| ❌ Prompt engineering every conversation | ✅ Skill(skill="sf-apex") |
| ❌ 10+ messages to explain requirements | ✅ 1 message, skill fills the gaps |
| ❌ Review code manually for issues | ✅ Hooks validate on every save |
Agent Skills Open Standard: These skills follow the Agent Skills specification for cross-CLI compatibility.
🤝 Call for Volunteers! This repo is community-driven, sharing knowledge to strengthen the Salesforce ecosystem. We need volunteers to test skills on different CLIs (OpenCode, Codex, Gemini, Cursor, etc.). You'll learn a ton about agentic workflows while helping the community! Open an issue to get started.
Claude Code (Anthropic) — Full Native Support
Claude Code is the recommended platform for sf-skills with full native support for all features.
# Install via marketplace
/plugin marketplace add Jaganpro/sf-skills- Install Path:
.claude-plugin/(per-skill plugin structure) - Format: Native SKILL.md with hooks, templates, and examples
- Hooks: ✅ Automatic validation on Write/Edit operations
- LSP: ✅ Real-time syntax validation with auto-fix loops
- Templates: ✅ Referenced dynamically (no duplication)
- Tool Execution: Local tools (Read, Write, Edit, Bash, Grep, Glob) — no MCP overhead
- Docs: claude.ai/code
Why Claude Code for sf-skills:
- Zero-latency tools — Local execution vs. MCP JSON-RPC roundtrips
- Automatic hooks — Validation runs on every file save without manual invocation
- Context efficiency — Skills load on-demand, saving ~2000 tokens per conversation
- LSP integration — Apex, Agent Script, and LWC syntax errors caught in real-time
OpenCode CLI — Open-Source Claude Code Alternative
OpenCode is an open-source alternative to Claude Code with skill support.
# Install all skills for OpenCode
python tools/installer.py --cli opencode --all- Install Path:
.opencode/skill/(project) or~/.opencode/skill/(global) - Format: SKILL.md with scripts and templates
- Hooks:
⚠️ Manual execution (runscripts/validate_*.py) - Claude Compatibility: Also reads
.claude/skills/directory - Docs: github.com/opencode-ai/opencode
Codex CLI (OpenAI) — GPT-Powered Coding Agent
Codex CLI is OpenAI's terminal-based coding agent.
# Install all skills for Codex
python tools/installer.py --cli codex --all- Install Path:
.codex/skills/(project) or~/.codex/skills/(global) - Format: SKILL.md with
assets/(templates) andreferences/(docs) - Hooks:
⚠️ Manual execution (runscripts/validate_*.py) - Enable Skills:
codex --enable skills - Docs: github.com/openai/codex
Gemini CLI (Google) — 1M+ Token Context
Gemini CLI is Google's Gemini-powered terminal agent with massive context window.
# Install all skills for Gemini
python tools/installer.py --cli gemini --all- Install Path:
~/.gemini/skills/(user scope by default) - Format: SKILL.md with scripts and templates
- Hooks:
⚠️ Manual execution (runscripts/validate_*.py) - Context: 1M+ tokens — can load entire codebases
- Symlink:
ln -s ~/.gemini/skills/sf-apex ~/.claude/skills/sf-apex - Docs: github.com/google-gemini/gemini-cli
Amp CLI (Sourcegraph) — Claude Code Compatible
Amp is Sourcegraph's agentic coding tool, fully compatible with Claude Code skills.
# No installer needed — Amp reads Claude Code skills directly
# Place skills in .claude/skills/ directory- Install Path:
.claude/skills/(same as Claude Code) - Format: Native Claude Code format (SKILL.md + hooks + templates)
- Hooks: ✅ Compatible with Claude Code hooks
- Codebase Search: Powered by Sourcegraph's code intelligence
- Docs: sourcegraph.com/amp
Droid CLI (Factory.ai) — Claude Code Compatible
Droid CLI (v0.26.0+) natively supports Claude Code skills format. Use the installer or import directly:
# Install via installer
python tools/installer.py --cli droid --all
# Or Droid auto-discovers skills from .claude/skills/ directory
# Use the /skills command within Droid to manage skills- Install Path:
.factory/skills/or~/.factory/skills/ - Format: Claude Code compatible (SKILL.md + scripts/)
- Prerequisite: Enable Custom Droids in
/settings → Experimental - Docs: docs.factory.ai/cli/configuration/skills
Cursor CLI — Installer with MDC Transformation
Cursor CLI uses its own rules system (.cursor/rules/ with MDC format). The installer transforms skills to Cursor's native format:
# Install skills transformed to MDC format
python tools/installer.py --cli cursor --all- Install Path:
.cursor/rules/{name}.mdc - Format: MDC (Markdown with YAML frontmatter: description, globs, alwaysApply)
- Templates: Copied to
assets/, docs toreferences/ - Alternative: SkillPort MCP bridge for runtime skill access
- Docs: docs.cursor.com/context/rules-for-ai
Agentforce Vibes (Salesforce) — Enterprise Vibe-Coding Tool
Agentforce Vibes is Salesforce's enterprise vibe-coding tool with strong Model Context Protocol (MCP) support.
# Install all skills for Agentforce Vibes
python tools/installer.py --cli agentforce-vibes --all- Install Path:
.clinerules/(project directory) - Format: Pure markdown files with numeric prefixes (
01-sf-apex.md,02-sf-flow.md, etc.) - Templates: Inlined directly into markdown rules (self-contained)
- Includes:
/newrulecommand references, Salesforce DX MCP Server tips - Docs: Agentforce Vibes Blog
Output Structure:
.clinerules/
├── 01-sf-apex.md
├── 02-sf-flow.md
├── 03-sf-lwc.md
└── ... (16 skills total)
Why Agentforce Vibes: Strong MCP support enables integration with Salesforce DX MCP Server (20+ tools) for org connectivity, metadata operations, and deployment.
| Feature | Claude Code | Agentforce Vibes |
|---|---|---|
| Platform | Terminal CLI | VS Code Extension |
| Skills System | ✅ Native (SKILL.md + hooks + templates) |
❌ No skills — uses .clinerules markdown |
| Automatic Hooks | ✅ Validation on Write/Edit (150+ point rubrics) | ❌ No hooks — manual validation only |
| LSP Integration | ✅ Agentic auto-fix loops (detect → fix → validate) | ✅ Via VS Code (manual fixes only) |
| Tool Execution | ✅ Local tools (zero latency) | ⚡ MCP-based (JSON-RPC overhead) |
| Salesforce Tools | sf CLI + pre-templated skill scripts |
Salesforce DX MCP (20+ tools) |
| Templates | ✅ Dynamic references (50+ templates) | 📄 Inlined in markdown |
| Models | Claude Sonnet 4, Opus 4.5 | GPT-4.1, SFR (Salesforce Research) |
| Context Window | 200K (Sonnet) or 1M (extended) | Varies by model |
| Enterprise Features | Community-driven | Trust Layer, audit logging |
Bottom line: Claude Code offers deeper integration (hooks, agentic LSP auto-fix, local tools) for Salesforce development. Agentforce Vibes provides enterprise compliance and native Salesforce ecosystem integration via MCP.
| Skill | Description | Category | Points | Status | |
|---|---|---|---|---|---|
| ⚡ | sf-apex | Apex generation, TAF patterns, LSP validation | 💻 Development | 150 | 🔬 Alpha |
| 🔄 | sf-flow | Flow creation & bulk validation | 💻 Development | 110 | 🔬 Alpha |
| ⚡ | sf-lwc | Lightning Web Components, Jest tests, LMS | 💻 Development | 140 | 🔬 Alpha |
| 🔍 | sf-soql | Natural language → SOQL, query optimization | 💻 Development | 100 | 🔬 Alpha |
| 🧪 | sf-testing | Apex test runner, coverage, bulk testing | 🧪 Quality | 100 | 🔬 Alpha |
| 🐛 | sf-debug | Debug log analysis, governor limit fixes | 🧪 Quality | 90 | 🔬 Alpha |
| 📋 | sf-metadata | Metadata gen & org queries | 📦 Foundation | 120 | 🔬 Alpha |
| 💾 | sf-data | SOQL & test data factories | 📦 Foundation | — | 🔬 Alpha |
| 🔐 | sf-connected-apps | OAuth apps & ECAs | 🔌 Integration | 120 | 🔬 Alpha |
| 🔗 | sf-integration | Callouts, Events, CDC | 🔌 Integration | 120 | 🔬 Alpha |
| 🤖 | sf-ai-agentforce | Agent Script, Topics, Actions (API v64+) | 🤖 AI & Automation | 150 | 🔬 Alpha |
| 🧪 | sf-ai-agentforce-testing | Agent test specs, agentic fix loops | 🤖 AI & Automation | 100 | 🔬 Alpha |
| 🚀 | sf-deploy | CI/CD automation (sf CLI v2) | 🚀 DevOps | — | 🔬 Alpha |
| 📊 | sf-diagram | Mermaid diagrams & ERD | 🛠️ Tooling | — | 🔬 Alpha |
| 📸 | sf-imagen | Visual ERD, LWC mockups, Gemini sub-agent | 🛠️ Tooling | — | 🔬 Alpha |
| 🛠️ | skill-builder | Skill creation wizard | 🛠️ Tooling | — | ✅ Stable |
Add the marketplace to Claude Code:
/plugin marketplace add Jaganpro/sf-skillsUse the installer script to transform and install skills for other agentic CLIs:
# Clone the repository
git clone https://github.com/Jaganpro/sf-skills
cd sf-skills
# Install all skills for a specific CLI
python tools/installer.py --cli opencode --all # OpenCode
python tools/installer.py --cli codex --all # Codex (OpenAI)
python tools/installer.py --cli gemini --all # Gemini (Google)
python tools/installer.py --cli droid --all # Droid (Factory.ai)
python tools/installer.py --cli cursor --all # Cursor (MDC format)
python tools/installer.py --cli agentforce-vibes --all # Agentforce Vibes (Salesforce)
# Install specific skills
python tools/installer.py --cli gemini --skills sf-apex sf-flow sf-deploy
# Auto-detect installed CLIs and install all skills
python tools/installer.py --detect --all
# List available skills and CLIs
python tools/installer.py --list
python tools/installer.py --list-clisThe installer:
- Transforms SKILL.md for CLI compatibility (MDC for Cursor, markdown for Agentforce Vibes)
- Bundles shared modules for self-contained installation
- Exports validation hooks as standalone scripts (where supported)
- Inlines templates for Agentforce Vibes (self-contained rules)
- Generates README with manual validation instructions
See tools/README.md for detailed installer documentation.
| Video | Description |
|---|---|
| How to Add/Install Skills | Install the sf-skills marketplace and add skills to Claude Code |
| Skills Demo & Walkthrough | Live demo of Apex, Flow, Metadata, and Agentforce skills in action |
%%{init: {"flowchart": {"nodeSpacing": 80, "rankSpacing": 70}} }%%
flowchart TB
subgraph ai["🤖 AI & AGENTS"]
agentforce["🤖 sf-ai-agentforce"]
agentforcetesting["🧪 sf-ai-agentforce-testing"]
end
subgraph integration["🔌 INTEGRATION & SECURITY"]
connectedapps["🔐 sf-connected-apps"]
sfintegration["🔗 sf-integration"]
diagram["📊 sf-diagram"]
end
subgraph development["💻 DEVELOPMENT"]
apex["⚡ sf-apex"]
flow["🔄 sf-flow"]
lwc["⚡ sf-lwc"]
soql["🔍 sf-soql"]
end
subgraph quality["🧪 QUALITY"]
testing["🧪 sf-testing"]
debug["🐛 sf-debug"]
end
subgraph foundation["📦 FOUNDATION"]
metadata["📋 sf-metadata"]
data["💾 sf-data"]
end
subgraph devops["🚀 DEVOPS"]
deploy["🚀 sf-deploy"]
end
subgraph tooling["🔧 TOOLING"]
skillbuilder["🛠️ skill-builder"]
imagen["📸 sf-imagen"]
end
%% AI & Agent relationships
agentforce -->|"flow actions"| flow
agentforce -->|"API actions"| sfintegration
agentforce -->|"GenAiFunction"| apex
agentforcetesting -->|"validates"| agentforce
%% Integration relationships
sfintegration -->|"OAuth apps"| connectedapps
sfintegration -->|"callouts"| apex
sfintegration -->|"HTTP Callout"| flow
connectedapps -->|"permissions"| metadata
diagram -->|"schema"| metadata
diagram -.->|"documents"| connectedapps
diagram -.->|"documents"| sfintegration
imagen -->|"renders"| diagram
imagen -->|"mockups"| lwc
%% Development relationships
apex -->|"schema"| metadata
flow -->|"schema"| metadata
lwc -->|"@wire"| apex
lwc -->|"schema"| metadata
soql -->|"queries"| data
apex -.->|"test data"| data
flow -.->|"test data"| data
%% Quality relationships
testing -->|"validates"| apex
testing -.->|"test data"| data
debug -->|"fixes"| apex
%% Foundation relationships
data -->|"structure"| metadata
%% Deployment - all skills can deploy via sf-deploy
apex -->|"deploy"| deploy
flow -->|"deploy"| deploy
lwc -->|"deploy"| deploy
metadata -->|"deploy"| deploy
sfintegration -->|"deploy"| deploy
connectedapps -->|"deploy"| deploy
agentforce -->|"deploy"| deploy
%% Styling - AI (pink-200)
style agentforce fill:#fbcfe8,stroke:#be185d,color:#1f2937
style agentforcetesting fill:#fce7f3,stroke:#be185d,color:#1f2937
%% Styling - Integration (orange-200/teal-200/sky-200)
style connectedapps fill:#fed7aa,stroke:#c2410c,color:#1f2937
style sfintegration fill:#99f6e4,stroke:#0f766e,color:#1f2937
style diagram fill:#bae6fd,stroke:#0369a1,color:#1f2937
%% Styling - Development (violet-200/indigo-200)
style apex fill:#ddd6fe,stroke:#6d28d9,color:#1f2937
style flow fill:#c7d2fe,stroke:#4338ca,color:#1f2937
style lwc fill:#e9d5ff,stroke:#7c3aed,color:#1f2937
style soql fill:#c4b5fd,stroke:#5b21b6,color:#1f2937
%% Styling - Quality (lime-200)
style testing fill:#d9f99d,stroke:#65a30d,color:#1f2937
style debug fill:#bef264,stroke:#4d7c0f,color:#1f2937
%% Styling - Foundation (cyan-200/amber-200)
style metadata fill:#a5f3fc,stroke:#0e7490,color:#1f2937
style data fill:#fde68a,stroke:#b45309,color:#1f2937
%% Styling - DevOps (emerald-200)
style deploy fill:#a7f3d0,stroke:#047857,color:#1f2937
%% Styling - Tooling (slate-200)
style skillbuilder fill:#e2e8f0,stroke:#334155,color:#1f2937
style imagen fill:#fef3c7,stroke:#d97706,color:#1f2937
%% Subgraph styling
style ai fill:#fdf2f8,stroke:#be185d,stroke-dasharray:5
style integration fill:#fff7ed,stroke:#c2410c,stroke-dasharray:5
style development fill:#f5f3ff,stroke:#6d28d9,stroke-dasharray:5
style quality fill:#f7fee7,stroke:#65a30d,stroke-dasharray:5
style foundation fill:#ecfeff,stroke:#0e7490,stroke-dasharray:5
style devops fill:#ecfdf5,stroke:#047857,stroke-dasharray:5
style tooling fill:#f8fafc,stroke:#334155,stroke-dasharray:5
Use the sf-deploy skill for all Salesforce deployments:
Skill(skill="sf-deploy", args="Deploy to [org]")
Skills now automatically suggest themselves based on your prompts! No need to remember skill names.
How It Works:
You: "I need to create an apex trigger for Account"
↓
🔍 UserPromptSubmit hook analyzes your prompt
↓
💡 Relevant Skills Detected
⭐ /sf-apex (relevance: 7) - Apex code development with validation
▸ /sf-metadata (relevance: 3) - Salesforce metadata configuration
↓
You can invoke the suggested skill or let Claude help directly
Matching System:
| Match Type | Score | Example |
|---|---|---|
| Keyword match | +2 per keyword | "apex", "trigger", "batch" |
| Intent pattern | +3 | "create.*apex", "build.*flow" |
| File pattern | +2 | Working on *.cls files |
Supported Triggers (all 16 skills):
- High Priority: sf-apex, sf-flow, sf-lwc, sf-ai-agentforce
- Medium Priority: sf-metadata, sf-deploy, sf-testing, sf-soql, sf-data, sf-integration
- Low Priority: sf-connected-apps, sf-debug, sf-diagram, sf-imagen, sf-ai-agentforce-testing, skill-builder
Configuration: Auto-activation is powered by shared/hooks/skill-rules.json and shared/hooks/skill-activation-prompt.py.
Each skill includes validation hooks that run automatically on Write and Edit operations:
| Skill | File Type | Validation | |
|---|---|---|---|
| ⚡ | sf-apex | *.cls, *.trigger |
150-pt scoring + Code Analyzer + LSP + Live Query Plan |
| 🔄 | sf-flow | *.flow-meta.xml |
110-pt scoring + Flow Scanner |
| ⚡ | sf-lwc | *.js, *.html (LWC) |
140-pt scoring + Code Analyzer + LSP |
| 🔍 | sf-soql | *.soql |
100-pt scoring + Live Query Plan API |
| 🧪 | sf-testing | *Test.cls |
100-pt scoring + coverage analysis |
| 🐛 | sf-debug | Debug logs | 90-pt scoring + governor analysis |
| 📋 | sf-metadata | *.object-meta.xml, *.field-meta.xml |
Metadata best practices |
| 💾 | sf-data | *.apex, *.soql |
SOQL patterns + Live Query Plan |
| 🤖 | sf-ai-agentforce | *.agent, *.genAiFunction-meta.xml |
Agent Script syntax + LSP |
| 🧪 | sf-ai-agentforce-testing | Test spec YAML | 100-pt scoring + fix loops |
| 🔐 | sf-connected-apps | *.connectedApp-meta.xml |
OAuth security |
| 🔗 | sf-integration | *.namedCredential-meta.xml |
Callout patterns |
| 📸 | sf-imagen | Generated images | Prerequisites check |
| 🛠️ | skill-builder | SKILL.md |
YAML frontmatter |
Hooks integrate Salesforce Code Analyzer V5 for OOTB linting alongside custom scoring:
| Engine | What It Checks | Dependency |
|---|---|---|
| PMD | 55 Apex rules (85% coverage) — security, bulkification, complexity, testing | Java 11+ |
| SFGE | Data flow analysis, path-based security | Java 11+ |
| Regex | Trailing whitespace, hardcoded patterns | None |
| ESLint | JavaScript/LWC linting | Node.js |
| Flow Scanner | Flow best practices | Python 3.10+ |
Custom Validation Coverage:
| Validator | Total Checks | Categories |
|---|---|---|
| Apex (150-pt) | PMD 55 rules + Python 8 checks | Security (100%), Bulkification, Testing, Architecture, Clean Code, Error Handling, Performance, Documentation |
| Flow (110-pt) | 32+ checks (21/24 LFS rules) | Design/Naming, Logic/Structure, Error Handling, Architecture, Security, Performance |
| LWC (140-pt) | ESLint + retire-js + SLDS Linter | SLDS 2 Compliance, Naming, Accessibility, Component Patterns, Lightning Message Service, Security |
Graceful Degradation: If dependencies are missing, hooks run custom validation only and show which engines were skipped.
Skills integrate with Salesforce's REST API explain endpoint to provide real-time query plan analysis:
| Metric | Description | Threshold |
|---|---|---|
| relativeCost | Query selectivity score | ≤1.0 = selective ✅, >1.0 = non-selective |
| leadingOperationType | How Salesforce executes the query | Index, TableScan, Sharing |
| cardinality | Estimated rows returned | vs. total records in object |
| notes[] | WHY optimizations aren't being used | Index suggestions, filter issues |
How It Works:
- When you write a
.soql,.cls, or.triggerfile, the hook extracts SOQL queries - Calls
sf data query --planto invoke the Salesforce explain API - Returns actual query execution plan from your connected org
- Provides optimization suggestions based on plan notes
Sample Output:
🌐 Live Query Plan Analysis (Org: my-dev-org)
L42: ✅ Cost 0.3 (Index)
L78: ⚠️ Cost 2.1 (TableScan) ⚠️ IN LOOP
📝 Field Status__c is not indexed
Skills with Live Query Plan:
- sf-soql —
.soqlfiles (entire file analyzed) - sf-apex —
.cls,.triggerfiles (extracts inline[SELECT...]andDatabase.query()) - sf-data —
.soqlfiles for data operations
Prerequisites: Connected Salesforce org (sf org login web). Falls back to static analysis if no org connected.
Skills leverage official Salesforce LSP servers for real-time syntax validation with auto-fix loops:
| Skill | File Type | LSP Server | Runtime | |
|---|---|---|---|---|
| 🤖 | sf-ai-agentforce | *.agent |
Agent Script Language Server | Node.js 18+ |
| ⚡ | sf-apex | *.cls, *.trigger |
apex-jorje-lsp.jar | Java 11+ |
| ⚡ | sf-lwc | *.js, *.html |
@salesforce/lwc-language-server | Node.js 18+ |
How Auto-Fix Loops Work:
- Claude writes/edits a file
- LSP hook validates syntax (~500ms)
- If errors found → Claude receives diagnostics and auto-fixes
- Repeat up to 3 attempts
Prerequisites: VS Code with Salesforce extensions installed (LSP servers are bundled with the extensions).
Sample Output:
🔍 Apex Validation: AccountService.cls
════════════════════════════════════════════════════════════════════════════════
📊 Score: 138/150 ⭐⭐⭐⭐ Very Good
(Custom: 145, CA deductions: -7)
📋 Category Breakdown:
✅ Security: 25/25
✅ Bulkification: 25/25
⚠️ Testing: 20/25 (-5)
✅ Architecture: 20/20
🔬 Code Analyzer: pmd, regex (2847ms)
❗ Issues Found (3):
🟠 HIGH [CA:pmd] L30: Validate CRUD permission before DML
🟠 HIGH [CA:pmd] L45: Avoid empty catch blocks
🔵 INFO [CA:regex] L12: Trailing whitespace
════════════════════════════════════════════════════════════════════════════════
Hooks provide advisory feedback — they inform but don't block operations.
Required:
- Claude Code (latest version)
- Salesforce CLI v2.x (
sfcommand) —npm install -g @salesforce/cli - Python 3.10+ (for validation hooks)
- Authenticated Salesforce Org — DevHub, Sandbox, or Scratch Org
- sfdx-project.json — Standard DX project structure
API Version Requirements:
| Skills | Minimum API | Notes |
|---|---|---|
| Most skills | 62.0 (Winter '25) | sf-apex, sf-flow, sf-lwc, sf-metadata |
| sf-connected-apps, sf-integration | 61.0 | External Client Apps |
| sf-ai-agentforce | 65.0 (Winter '26) | Full agent deployment |
Optional (enables additional features):
Code Analyzer V5 engines:
- Java 11+ — Enables PMD, CPD, SFGE engines (
brew install openjdk@11) - Node.js 18+ — Enables ESLint, RetireJS for LWC (
brew install node) - Code Analyzer plugin —
sf plugins install @salesforce/sfdx-code-analyzer
LWC Testing & Linting:
- @salesforce/sfdx-lwc-jest — Jest testing for LWC (
npm install @salesforce/sfdx-lwc-jest --save-dev) - @salesforce-ux/slds-linter — SLDS validation (
npm install -g @salesforce-ux/slds-linter)
LSP real-time validation (auto-fix loops):
- VS Code with Salesforce Extensions — LSP servers are bundled with VS Code extensions
- Apex: Install "Salesforce Extension Pack"
- LWC: Install "Salesforce Extension Pack" (includes LWC Language Server)
- Agent Script: Install "Salesforce Agent Script" extension
- Java 11+ — Required for Apex LSP (same as Code Analyzer)
- Node.js 18+ — Required for Agent Script and LWC LSP
Apex Development:
- Trigger Actions Framework (TAF) — Optional package for sf-apex trigger patterns
- Package ID:
04tKZ000000gUEFYA2or GitHub repo
- Package ID:
"Generate an Apex trigger for Account using Trigger Actions Framework"
"Review my AccountService class for best practices"
"Create a batch job to process millions of records"
"Generate a test class with 90%+ coverage"
"Create a screen flow for account creation with validation"
"Build a record-triggered flow for opportunity stage changes"
"Generate a scheduled flow for data cleanup"
"Create a custom object called Invoice with auto-number name field"
"Add a lookup field from Contact to Account"
"Generate a permission set for invoice managers with full CRUD"
"Create a validation rule to require close date when status is Closed"
"Describe the Account object in my org and list all custom fields"
"Query all Accounts with related Contacts and Opportunities"
"Create 251 test Account records for trigger bulk testing"
"Insert 500 records from accounts.csv using Bulk API"
"Generate test data hierarchy: 10 Accounts with 3 Contacts each"
"Clean up all test records created today"
"Create a datatable component to display Accounts with sorting"
"Build a form component for creating new Contacts"
"Generate a Jest test for my accountCard component"
"Create an Apex controller with @AuraEnabled methods for my LWC"
"Set up Lightning Message Service for cross-component communication"
"Query all Accounts with more than 5 Contacts"
"Get Opportunities by Stage with total Amount per Stage"
"Find Contacts without Email addresses"
"Optimize this query: SELECT * FROM Account WHERE Name LIKE '%Corp%'"
"Generate a SOQL query to find duplicate Leads by Email"
"Run all Apex tests in my org and show coverage"
"Generate a test class for my AccountTriggerHandler"
"Create a bulk test with 251 records for trigger testing"
"Generate mock classes for HTTP callouts"
"Run tests for a specific class and show failures"
"Analyze this debug log for performance issues"
"Find governor limit violations in my log"
"What's causing this SOQL in loop error?"
"Show me how to fix this null pointer exception"
"Optimize my Apex for CPU time limits"
"Create a Connected App for API integration with JWT Bearer flow"
"Generate an External Client App for our mobile application with PKCE"
"Review my Connected Apps for security best practices"
"Migrate MyConnectedApp to an External Client App"
"Create a Named Credential for Stripe API with OAuth client credentials"
"Generate a REST callout service with retry and error handling"
"Create a Platform Event for order synchronization"
"Build a CDC subscriber trigger for Account changes"
"Set up an External Service from an OpenAPI spec"
"Create an Agentforce agent for customer support triage"
"Build a FAQ agent with topic-based routing"
"Generate an agent that calls my Apex service via Flow wrapper"
"Create a GenAiFunction for my @InvocableMethod Apex class"
"Build an agent action that calls the Stripe API"
"Generate a PromptTemplate for case summaries"
"Create a JWT Bearer OAuth flow diagram"
"Generate an ERD for Account, Contact, Opportunity, and Case"
"Diagram our Salesforce to SAP integration flow"
"Create a system landscape diagram for our Sales Cloud implementation"
"Generate a role hierarchy diagram for our sales org"
"Deploy my Apex classes to sandbox with tests"
"Validate my metadata changes before deploying to production"
"Create a new Claude Code skill for code analysis"
sf-{capability} # Cross-cutting (apex, flow, admin)
sf-ai-{name} # AI features (agentforce, copilot)
sf-product-{name} # Products (datacloud, omnistudio)
sf-cloud-{name} # Clouds (sales, service)
sf-industry-{name} # Industries (healthcare, finserv)
| Skill | Description | Status | |
|---|---|---|---|
| 🔐 | sf-connected-apps |
Connected Apps, ECAs, OAuth configuration | ✅ Live |
| 🔗 | sf-integration |
Named Credentials, External Services, REST/SOAP, Platform Events, CDC | ✅ Live |
| 📊 | sf-diagram |
Mermaid diagrams for OAuth, ERD, integrations, architecture | ✅ Live |
| ⚡ | sf-lwc |
Lightning Web Components, Jest, LMS | ✅ Live |
| 🔍 | sf-soql |
Natural language to SOQL, optimization | ✅ Live |
| 🧪 | sf-testing |
Test execution, coverage, bulk testing | ✅ Live |
| 🐛 | sf-debug |
Debug log analysis, governor fixes | ✅ Live |
| 📸 | sf-imagen |
Visual ERD, LWC mockups, Gemini sub-agent | ✅ Live |
| 🔒 | sf-security |
Sharing rules, org-wide defaults, encryption | 📋 Planned |
| 📦 | sf-migration |
Org-to-org, metadata comparison | 📋 Planned |
| Skill | Description | Status | |
|---|---|---|---|
| 🤖 | sf-ai-agentforce |
Agent Script, Topics, Actions (API v64+) | ✅ Live |
| 🧪 | sf-ai-agentforce-testing |
Agent test specs, agentic fix loops | ✅ Live |
| 🧠 | sf-ai-copilot |
Einstein Copilot, Prompts | 📋 Planned |
| 🔮 | sf-ai-einstein |
Prediction Builder, NBA | 📋 Planned |
| Skill | Description | Status | |
|---|---|---|---|
| ☁️ | sf-product-datacloud |
Unified profiles, segments | 📋 Planned |
| 🎨 | sf-product-omnistudio |
FlexCards, DataRaptors | 📋 Planned |
| Skill | Description | Status | |
|---|---|---|---|
| 💰 | sf-cloud-sales |
Opportunities, Quotes, Forecasting | 📋 Planned |
| 🎧 | sf-cloud-service |
Cases, Omni-Channel, Knowledge | 📋 Planned |
| 🌐 | sf-cloud-experience |
Communities, Portals | 📋 Planned |
| Skill | Description | Status | |
|---|---|---|---|
| 🏥 | sf-industry-healthcare |
FHIR, Care Plans, Compliance | 📋 Planned |
| 🏦 | sf-industry-finserv |
KYC, AML, Wealth Management | 📋 Planned |
| 💵 | sf-industry-revenue |
CPQ, Billing, Revenue Lifecycle | 📋 Planned |
Total: 26 skills (16 skills ✅ live, 10 planned 📋)
- Fork the repository
- Create a feature branch
- Make your changes
- Test with
/plugin install ./your-skill - Open a Pull Request
See CONTRIBUTING.md for detailed guidelines.
MIT License - Copyright (c) 2024-2025 Jag Valaiyapathy