MCP App StoreMCP App Store
from salesforce-claude-code8
Enforce safe Salesforce deployments: validation-first workflow, test-coverage gates, dependency ordering, pre-deploy snapshots, and rollback readiness.
This skill encodes a deployment safety checklist and gating rules for Salesforce metadata deployments. It guides agents to perform validation-only deploys, enforce appropriate test levels and code coverage, order metadata correctly, capture pre-deploy snapshots before destructive changes, and require rollback plans for production releases.
Activate this skill when preparing or executing deployments, promotions, or packaging of Salesforce metadata to shared sandboxes or production orgs. It's intended for pipeline/automation agents and engineers who must avoid partial or destructive deploys and maintain org stability. Do not use for simple local development pushes to scratch orgs.
Best for CI/CD and automation agents that orchestrate Salesforce CLI commands (sf), such as Claude-Code, Cursor, or custom CI runners that can run sf CLI and enforce policy checks.
Salesforce deployment constraints skill with no bundled scripts. Pure markdown-based guardrails for safe SF metadata deployments — validation-first workflow, test coverage gates, dependency ordering, and rollback readiness. Well-written with clear Never/Always sections and a comprehensive anti-pattern table. Only uses Read/Grep/Glob tools, no write or exec capabilities.
Clean skill — no security concerns. Restricted to read-only tools. Anti-pattern table explicitly warns against unsafe practices like --ignore-errors and hardcoded secrets. Well-structured for its niche.
Search-First (Research Before You Code)
Agent workflow to search for existing Salesforce tools, libraries, MCP servers, and packages before writing new code—helps decide whether to adopt, extend, or b
Sf Docs Lookup
Use when looking up official Salesforce documentation. Apex reference, LWC docs, platform guides, API references, and SF CLI commands via WebSearch.
SF Agentforce Development
Guides building Agentforce AI agents: agent script patterns, actions (Apex invocable), testing workflows, deployment and metadata best practices.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.
Spring Boot Migration
Guided, phased migration for existing Spring Boot apps to Boot 4 / Java 25 (including Modulith 2 and Testcontainers 2), with scanners and reference guides.
ArcKit Architecture Conformance
Run a systematic architecture conformance assessment that compares ADRs and principles against HLD/DLD artifacts to surface drift, violations, and technical deb
Speak Security Basics
Security best practices for integrating Speak: API key management, audio data privacy, student data protection, and COPPA/FERPA compliance for production deploy
Replit — Advanced Troubleshooting
Step-by-step diagnostics and debugging techniques for deep Replit issues: Nix build failures, container crash loops, memory leaks, and platform vs app isolation
Vercel Common Errors
Diagnose and fix common Vercel build, serverless runtime, and edge/routing errors with step-by-step checks and fixes.