Platform Deploy Validate logo

Platform Deploy Validate

OrganizationPopular
forcedotcom
platform-deploy-validate

Validate Salesforce metadata before deploying. TRIGGER when the user asks to validate a deploy, do a dry-run, check before deploying, or targets a Production org for any deploy operation. Routes prod targets to `sf project deploy validate` (returns a 10-day quick-deploy job ID) and sandbox/scratch targets to `sf project deploy start --dry-run`. DO NOT TRIGGER for actual deploys (use platform-metadata-deploy) or destructive changes (use platform-destructive-deploy).

Overview

Publisherforcedotcom
Repositorysf-skills
Skill nameplatform-deploy-validate
Stars
1.1K
Forks
351
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by forcedotcom on GitHub. Read the source before you install it.

Installation

Install the Platform Deploy Validate AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/forcedotcom/sf-skills/tree/main/plugins/builder/salesforce-development/skills/platform-deploy-validate
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/forcedotcom/sf-skills.git /tmp/sf-skills
mkdir -p .claude/skills
cp -r /tmp/sf-skills/plugins/builder/salesforce-development/skills/platform-deploy-validate .claude/skills/platform-deploy-validate
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Platform Deploy Validate in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Platform Deploy Validate on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Platform Deploy Validate is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Validating Deployment

Run a server-side validation before deploying metadata. Validation surfaces errors without modifying the org and — for production targets — produces a job ID usable with platform-quick-deploy for a fast, test-free deploy.

Capability Resolution

Always prefer sf project deploy validate (prod) or sf project deploy start --dry-run (sandbox/scratch) over the Tooling API directly.

Workflow

Step 1 — Confirm the target org

Classify the org with the gate's classifier — it is the authoritative source of truth (it handles sandbox/scratch markers, trial and Developer Edition hosts, and dev hubs, and returns one of production|sandbox|scratch|trial|devhub|unknown):

bash
sf org display --target-org <alias> --json | "${CLAUDE_PLUGIN_ROOT}/scripts/sf-deploy-gate" classify

Only production takes the production path (Step 2b); every other result takes the sandbox/scratch path (Step 2a).

Step 2a — Sandbox/Scratch path (dry-run)

bash
sf project deploy start --dry-run --target-org <alias> --json [scope flags]

Scope flags (use exactly one, not all):

  • --source-dir <path> — deploy a directory
  • --metadata <Type:Name> — deploy specific components
  • --manifest manifest/package.xml — deploy from manifest

Default test level: omit --test-level for sandboxes (defers to org default). Add --test-level RunLocalTests only if the user asks.

Report back: success/failure, components attempted, any errors. No job ID is returned for dry-runs (this is expected).

Step 2b — Production path (validate)

bash
sf project deploy validate --target-org <alias> --json [scope flags] --test-level RunLocalTests

Production validations REQUIRE a test level. Use RunLocalTests by default; switch to RunSpecifiedTests --tests <ClassName>... if the user has explicitly listed tests.

The response returns a job ID (result.id) valid for 10 days. Persist it for platform-quick-deploy:

bash
mkdir -p .sfdx
echo '{"jobId":"<id>","createdAt":"<iso8601>","targetOrg":"<alias>","testLevel":"RunLocalTests"}' > .sfdx/last-validation.json

Report:

  • Validation result (passed / failed)
  • Job ID and 10-day expiry date
  • Test results summary (run / passed / failed)
  • Recommended next step: platform-quick-deploy with this job ID

Step 3 — Failure triage

If validation fails, parse result.details.componentFailures and result.details.runTestResult.failures and surface:

  • Top 5 component errors with full message
  • Top 5 test failures with stack
  • Suggested fix (component name → likely cause: missing dependency, FLS, syntax, etc.)

Do NOT propose fixes that change unrelated metadata. Stay scoped to what the validation reported.

Rules

  • ALWAYS use --json on every CLI call
  • NEVER skip validation when targeting Production (do not run sf project deploy start against prod from this skill)
  • NEVER use --ignore-errors or --ignore-warnings during validation; those flags belong to actual deploys, not validation
  • If the user asks to "deploy to prod" without prior validation, FIRST run validation, THEN hand off to platform-quick-deploy (do not start a regular deploy against prod)
  • Persist the validation job ID to .sfdx/last-validation.json so the quick-deploy skill can find it

Output

Always end with:

  • ✅ Validation passed → next-step pointer to platform-quick-deploy (with job ID + expiry) OR to platform-metadata-deploy for non-prod
  • ❌ Validation failed → categorized error list and suggested next iteration

Frequently asked questions

What does the Platform Deploy Validate AI skill do?

Validate Salesforce metadata before deploying. TRIGGER when the user asks to validate a deploy, do a dry-run, check before deploying, or targets a Production org for any deploy operation. Routes prod targets to `sf project deploy validate` (returns a 10-day quick-deploy job ID) and sandbox/scratch targets to `sf project deploy start --dry-run`. DO NOT TRIGGER for actual deploys (use platform-metadata-deploy) or destructive changes (use platform-destructive-deploy).

Why use Platform Deploy Validate on TypingMind?

Because you install it once and use it with any model. Platform Deploy Validate is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Platform Deploy Validate in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/forcedotcom/sf-skills/tree/main/plugins/builder/salesforce-development/skills/platform-deploy-validate. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Platform Deploy Validate?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Platform Deploy Validate?

As many as you like. As long as a model supports skills, you can use Platform Deploy Validate with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Platform Deploy Validate AI skill free?

Yes. It is published on GitHub by forcedotcom under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇