Claude Marketplaces
SkillsMCP serversMarketplacesDigestTools
Submit

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP servers by category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control
Claude Marketplaces

An independent directory of skills, plugins and MCP servers for Claude Code. Not affiliated with Anthropic.

Browse

  • Skills
  • MCP servers
  • Marketplaces
  • Weekly digest
  • Skill index
  • MCP index
  • Marketplace index

Site

  • About
  • Tools
  • Submit
  • Feedback
  • Privacy
  • llms.txt
  • Plugins reference

Maker

  • Snug
  • Agent Caffeine
  • knobs
  • Wax
  • Vectoys
  • mertduzgun.com
Crafted at
Skills
jaganpro avatar

Sf Integration

jaganpro/sf-skills

This handles the architectural plumbing for Salesforce integrations: Named Credentials, External Services, REST/SOAP callouts, Platform Events, and Change Data Capture. It kicks in when you're wiring up external systems or event-driven patterns, not when you're configuring OAuth apps or writing Apex business logic. The 120-point scoring system evaluates six categories of integration safety, and the workflow pushes you toward runtime-managed auth and async patterns where they matter. It's opinionated about the dangerous stuff like synchronous trigger callouts and hardcoded credentials. Good for teams that need guardrails around integration architecture, especially when mixing declarative and code-based approaches.

installs
1.4K
GitHub stars
424
last updated
Jul 14, 2026
View on GitHubSave

Install

$ npx -y skills add jaganpro/sf-skills --skill sf-integration --agent claude-code

Installs into .claude/skills of the current project.

Files

sf-integration: Salesforce Integration Patterns Expert

Use this skill when the user needs integration architecture and runtime plumbing: Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, CDC, and event-driven integration design.

When This Skill Owns the Task

Use sf-integration when the work involves:

  • .namedCredential-meta.xml or External Credential metadata
  • outbound REST/SOAP callouts
  • External Service registration from OpenAPI specs
  • Platform Events, CDC, and event-driven architecture
  • choosing sync vs async integration patterns

Delegate elsewhere when the user is:

  • configuring the OAuth app itself → sf-connected-apps
  • writing Apex-only business logic → sf-apex
  • deploying metadata → sf-deploy
  • importing/exporting data → sf-data

Required Context to Gather First

Ask for or infer:

  • integration style: outbound callout, inbound event, External Service, CDC, platform event
  • auth method
  • sync vs async requirement
  • system endpoint / spec details
  • rate limits, retry expectations, and failure tolerance
  • whether this is net-new design or repair of an existing integration

Recommended Workflow

1. Choose the integration pattern

NeedDefault pattern
authenticated outbound API callNamed Credential / External Credential + Apex or Flow
spec-driven API clientExternal Service
trigger-originated calloutasync callout pattern
decoupled event publishingPlatform Events
change-stream consumptionCDC

2. Choose the auth model

Prefer secure runtime-managed auth:

  • Named Credentials / External Credentials
  • OAuth or JWT via the right credential model
  • no hardcoded secrets in code

3. Generate from the right templates

Use the provided assets under:

  • assets/named-credentials/
  • assets/external-credentials/
  • assets/external-services/
  • assets/callouts/
  • assets/platform-events/
  • assets/cdc/
  • assets/soap/

4. Validate operational safety

Check:

  • timeout and retry handling
  • async strategy for trigger-originated work
  • logging / observability
  • event retention and subscriber implications

5. Hand off deployment or implementation details

Use:

  • sf-deploy for deployment
  • sf-apex for deeper service / retry code
  • sf-flow for declarative HTTP callout orchestration

High-Signal Rules

  • never hardcode credentials
  • do not do synchronous callouts from triggers
  • define timeout behavior explicitly
  • plan retries for transient failures
  • use middleware / event-driven patterns when outbound volume is high
  • prefer External Credentials architecture for new development when supported

Common anti-patterns:

  • sync trigger callouts
  • no retry or dead-letter strategy
  • no request/response logging
  • mixing auth setup responsibilities with runtime integration design

Output Format

When finishing, report in this order:

  1. Integration pattern chosen
  2. Auth model chosen
  3. Files created or updated
  4. Operational safeguards
  5. Deployment / testing next step

Suggested shape:

Integration: <summary>
Pattern: <named credential / external service / event / cdc / callout>
Files: <paths>
Safety: <timeouts, retries, async, logging>
Next step: <deploy, register, test, or implement>

Cross-Skill Integration

NeedDelegate toReason
OAuth app setupsf-connected-appsconsumer key / cert / app config
advanced callout service codesf-apexApex implementation
declarative HTTP callout / Flow wrappersf-flowFlow orchestration
deploy integration metadatasf-deployvalidation and rollout
use integration from Agentforcesf-ai-agentscriptagent action composition

Reference Map

Start here

  • references/named-credentials-guide.md
  • references/external-services-guide.md
  • references/callout-patterns.md
  • references/security-best-practices.md

Event-driven / platform patterns

  • references/event-patterns.md
  • references/platform-events-guide.md
  • references/cdc-guide.md
  • references/event-driven-architecture-guide.md
  • references/messaging-api-v2.md

CLI / automation / scoring

  • references/cli-reference.md
  • references/named-credentials-automation.md
  • references/scoring-rubric.md
  • assets/

Score Guide

ScoreMeaning
108+strong production-ready integration design
90–107good design with some hardening left
72–89workable but needs architectural review
< 72unsafe / incomplete for deployment
SKILL.md on GitHub

Sponsors

SnugThe clipboard manager you and your agent can use, safelyAgent CaffeineClose your lid, come back to finished workWaxBlock anything with supervision, without erasing your iPhoneOpen StepsSponsoredFree and open-source skills that make AI coding agents easier to understand, verify, and control.

Details

Repository
github.com/jaganpro/sf-skills
First seen
Apr 16, 2026

More from jaganpro/sf-skills

All 37
  • Sf Diagram Mermaid1.4K
  • Sf Connected Apps1.4K
  • Sf Ai Agentscript1.4K
  • Sf Diagram Nanobananapro1.3K
  • Sf Ai Agentforce1.3K
  • Sf Ai Agentforce Testing1.3K
  • Sf Ai Agentforce Observability1.3K
  • Sf Docs1.2K
  • Sf Ai Agentforce Persona1.2K
  • Sf Datacloud1K
  • Sf Industry Commoncore Omniscript990
  • Sf Industry Commoncore Datamapper987
  • Sf Industry Commoncore Omnistudio Analyze986
  • Sf Industry Commoncore Flexcard984
  • Sf Datacloud Retrieve982
  • Sf Datacloud Connect980
  • Sf Industry Commoncore Integration Procedure980
  • Sf Datacloud Prepare979
  • Sf Datacloud Segment976
  • Sf Datacloud Harmonize973
  • Sf Datacloud Act972
  • Sf Industry Commoncore Callable Apex951
  • Sf Flex Estimator834
  • Sf Industry Cme Epc Model812

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels594.9Kinstalls
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.4Minstalls
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s37.9Kinstalls
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes309.2Kinstalls
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kinstalls
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.1Minstalls