More screenshots
Works with the AI tools you already use
Salesforce api Retirement Surgeon
Find and fix every legacy Salesforce API version before the Summer '27/'28 retirements break your integrations — scan, phased plan, CIO-ready report. Audits, reports, and upgrades legacy Salesforce API versions to prevent integration failures and 410 GONE errors.
$12
· or 60 creditsSecure checkout via Stripe
About this skill
Find and fix every legacy Salesforce API version before the Summer '27/'28 retirements break your integrations — scan, phased plan, CIO-ready report. THE PROBLEM Salesforce API versions 21.0-30.0 are already retired — calls fail today with REST 410 GONE, SOAP 500 UNSUPPORTED_API_VERSION, and Bulk 400 InvalidVersion. The next wave (v31.0-v40.0) is deprecated in Summer '27 and fully retired in Summer '28. Finding every hidden version reference across code, metadata, WSDLs, and hardcoded URLs is manual, error-prone work that risks production downtime. WHAT IT DOES - Scans your entire repository for REST, SOAP, and Bulk API version references across code and config: /services/data/vXX.X URLs, apiVersion in Apex/LWC/Aura meta.xml, package.xml, sfdx-project.json, and cached WSDLs. - Tiers every finding into RETIRED (failing now), RETIRING, AGING, and CURRENT against the official Salesforce retirement timeline. - Generates a CIO-ready HTML Retirement Exposure Report (prints to PDF) with every affected file and line number — including an "ALREADY FAILING" incident banner when retired versions are found. - Executes staged, surgical upgrades: version bumps with response-shape review, WSDL and stub regeneration, meta.xml updates gated behind the v67.0 Apex security-defaults check. - Flags hardcoded instance URLs that break at My Domain enforcement (Winter '27) — a second, independent deadline. WHY THIS BEATS PROMPTING IT YOURSELF Generic prompting misses nested references in WSDL stubs and package.xml files and can hallucinate retirement dates. This skill uses a deterministic read-only scanner plus a strict playbook: no retired version missed, no code modified until you approve the risk-tiered plan, and dates always deferred to Salesforce's official Product & Feature Retirements list. USE CASES - Audit a legacy codebase to find out why Salesforce integrations are throwing 410 or 400 errors. - Prepare for the Summer '27/'28 retirement wave by upgrading v31.0-v40.0 references. - Generate professional exposure reports for clients or management before starting a migration. - Convert hardcoded instance URLs to My Domain URLs before enforcement. WORKS WITH Salesforce REST/SOAP/Bulk APIs, Apex, LWC, SFDX projects, WSDL/metadata XML. Scanner requires only Python 3.8+ (standard library). KNOWN LIMITATIONS Static scanning covers visible code in the repo only. Callers outside it — middleware, Data Loader installs, AppExchange packages — need org-side verification via Salesforce API event logs, which the skill walks you through. Includes: scanner script, retirement timeline & risk tiers, upgrade playbook, report spec, and a full sample Retirement Exposure Report.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Details
Reviews
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Be the first to review this skill.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
Allowed Hosts
File Scopes
Creator
Frequently Asked Questions
More Premium Skills
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.
Multi-Agent Orchestration Master Library
Transform Claude Code into a coordinated multi-agent system. Battle-tested tmux orchestration patterns, YAML task queues, event-driven communication, and parallel worker management for 8+ agents.
diagnosing-rag-failure-modes
RAG fails quietly. It retrieves documents, returns confident-looking answers, and misses the question entirely — because the question required connecting facts across documents, reasoning about sequence, or tracing causation. This skill gives you a five-question diagnostic checklist that classifies any failing query as either RAG-safe or structurally RAG-incompatible, then maps it to the specific failure pattern and the architectural fix that resolves it.
endless-loop
Autonomous research and task loop that builds on previous findings to solve complex objectives while you sleep.