Generate Salesforce Flows via a strict 3-step MCP pipeline
Generate Salesforce Flow metadata (Screen, Autolaunched, Record-Triggered, Scheduled) with the execute_metadata_action MCP tool — fetchGroundedObjectMetadata → flowElementSelection → flowElementGeneration looped until isComplete, never hand-editing the XML
- What
- Generate Salesforce Flow metadata (Screen, Autolaunched, Record-Triggered, Scheduled) with the execute_metadata_action MCP tool — fetchGroundedObjectMetadata → flowElementSelection → flowElementGeneration looped until isComplete, never hand-editing the XML
- Cost
- Free
- Needs
- Salesforce org access (a free Developer Edition org works), the Salesforce CLI, and an MCP server exposing the execute_metadata_action tool (metadata-experts >= 1.0.0) — the skill is guidance the agent follows, not software to install
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @forcedotcom's skill for generating Salesforce Flow metadata through one mandatory 3-step MCP pipeline (`execute_metadata_action`), for Screen, Autolaunched, Record-Triggered (before/after-save) and Scheduled flows. Step 1, `fetchGroundedObjectMetadata`: pass the user's natural-language prompt plus `inflightMetadata` — an ARRAY of custom objects/fields scanned from the local sfdx project (exact naming conventions: `apiName`, `type`, `referenceTo`; `[]` when none). Step 2, `flowElementSelection`: same userPrompt, the groundingMetadata string passed verbatim, and an operationId. Step 3, `flowElementGeneration`: loop with the same operationId and `requestSource: "A4V"` until `isComplete` is true — never pause, never ask to continue, no matter how many iterations. Strict constraints: never create or modify flow XML outside the pipeline, never add/remove nodes from what the pipeline returned. Multi-flow requests must be split into N separate, sequential single-flow pipelines. Includes pattern guidance (scheduled-flow cadence lives on the start element's `<schedule>` block; counts via a single `AssignCount` assignment; never invent actions the prompt didn't request) and a canvas-mode check. Honest caveats: requires Salesforce org access (a free Developer Edition org works) plus the Salesforce CLI and an MCP server exposing `execute_metadata_action` (metadata-experts >= 1.0.0) — generation only, you still deploy and test yourself; test generated flows in a sandbox before production. Apache-2.0 licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Generate Salesforce Flows is a free Muse skill for generating Salesforce Flow metadata through a mandatory 3-step MCP pipeline, execute_metadata_action, for Screen, Autolaunched, Record-Triggered, Scheduled flows. Step 1, fetchGroundedObjectMetadata, passes the user prompt plus inflightMetadata, an array of custom objects and fields from the local sfdx project, with exact naming conventions, apiName, type and referenceTo, or empty brackets when none.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit e5164d9Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: Salesforce org access (a free Developer Edition org works), the Salesforce CLI, and an MCP server exposing the execute_metadata_action tool (metadata-experts >= 1.0.0) — the skill is guidance the agent follows, not software to install Install "Generate Salesforce Flows via a strict 3-step MCP pipeline" for me. It teaches my agent @forcedotcom's flow-generation workflow: follow the mandatory 3-step MCP pipeline only (fetchGroundedObjectMetadata → flowElementSelection → flowElementGeneration looped until isComplete), pass inflightMetadata as an ARRAY scanned from the local sfdx project, never hand-create or hand-edit flow XML, split multi-flow requests into separate sequential pipelines, and apply the pattern guidance (scheduled cadence on the start element, AssignCount for counts, no invented actions). Apache-2.0 licensed. Repository: https://raw.githubusercontent.com/forcedotcom/sf-skills/e5164d94d7511c00fa02a5b8b60754b2361e178f/plugins/builder/salesforce-development/skills/automation-flow-generate/SKILL.md Pinned version: install the code at commit e5164d94d7511c00fa02a5b8b60754b2361e178f exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "automation-flow-generate". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. connect the agent to your Salesforce org and the metadata-experts MCP server; hand the agent the flow request; deploy and test the generated XML in a sandbox yourself — generation only). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- e5164d9 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.