sf-flow
Creates and validates Salesforce Flows with 110-point scoring. TRIGGER when: user builds or edits record-triggered, screen, autolaunched, or scheduled flows, or touches .flow-meta.xml files. DO NOT TRIGGER when: Apex automation (use sf-apex), process builder migration questions only, or non-Flow declarative config (use sf-metadata).
- Installs
- 1.5K
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/jaganpro/sf-skills --skill sf-flow- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads sf-flow automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
sf-flow: Salesforce Flow Creation and Validation
Use this skill when the user needs Flow design or Flow XML work: record-triggered, screen, autolaunched, scheduled, or platform-event Flows, including validation, architecture choices, and safe deployment sequencing.
When This Skill Owns the Task
Use sf-flow when the work involves:
.flow-meta.xmlfiles- Flow Builder architecture and XML generation
- record-triggered, screen, scheduled, autolaunched, or platform-event flows
- Flow-specific bulk safety, fault paths, and subflow orchestration
Delegate elsewhere when the user is:
- writing Apex-first automation → sf-apex
- creating objects / fields first → sf-metadata
- deploying metadata → sf-deploy
- seeding post-deploy test data → sf-data
Required Context to Gather First
Ask for or infer:
- flow type
- trigger object / entry conditions
- core business goal
- whether this is new, refactor, or repair
- target org alias if deployment or validation is needed
- whether related objects / fields already exist
Recommended Workflow
1. Choose the right automation tool
Before building, confirm Flow is the right answer rather than:
- formula field
- validation rule
- roll-up summary
- Apex
2. Choose the right Flow type
| Need | Default flow type |
|---|---|
| same-record update before save | before-save record-triggered |
| related-record work / emails / callouts | after-save record-triggered |
| guided UI | screen flow |
| reusable background logic | autolaunched / subflow |
| scheduled processing | scheduled flow |
| event-driven declarative response | platform-event flow |
| AI-evaluated routing (sentiment, intent, tone) | autolaunched with AI Decision element |
3. Start from a template
Prefer the provided assets:
assets/record-triggered-before-save.xmlassets/record-triggered-after-save.xmlassets/screen-flow-template.xmlassets/autolaunched-flow-template.xmlassets/scheduled-flow-template.xmlassets/platform-event-flow-template.xmlassets/ai-decision-template.xmlassets/subflows/
4. Validate against Flow guardrails
Focus on:
- no DML in loops
- no Get Records inside loops
- proper fault paths
- correct trigger conditions
- safe subflow composition
- AI Decision elements not placed inside loops (credit cost per iteration)
- AI Decision prompts include merge field references for data context
5. Hand off deployment and testing
Use:
- sf-deploy for deploy / dry-run
- sf-data for high-volume test data
High-Signal Rules
Flow architecture
- before-save for same-record field updates
- after-save for related records, emails, and callouts
- do not loop over
$Record - use subflows when logic becomes wide or repetitive
Bulk safety
- no DML in loops
- no Get Records in loops
- test with 251+ records when bulk behavior matters
- prefer Transform when the job is shaping data, not per-record branching
Error handling
- every data-changing path should have fault handling
- avoid self-referencing fault connectors
- deploy Flows as Draft first when activation risk is non-trivial
Output Format
When finishing, report in this order:
- Flow type and goal
- Files created or updated
- Architecture choices
- Bulk/error-handling notes
- Deploy/testing next steps
Suggested shape:
Flow: <name>
Type: <flow type>
Files: <paths>
Design: <trigger choice, subflows, key decisions>
Risks: <bulk safety, fault paths, dependencies>
Next step: <dry-run deploy, activate, or test>
Flow Testing (CLI)
Run Flow tests from the command line without VS Code:
# Run all flow tests
sf flow run test --target-org <alias> --json
# Run tests for a specific flow
sf flow run test --class-names MyFlow --target-org <alias> --json
# Get results for an asynchronous run
sf flow get test --test-run-id <id> --target-org <alias> --json
Flow tests execute in the org and can take 1-5 minutes. sf flow run test returns a test run ID for asynchronous runs; use sf flow get test to retrieve results later. Always run with --json and use background execution for longer runs.
Cross-Skill Integration
| Need | Delegate to | Reason |
|---|---|---|
| create objects / fields first | sf-metadata | schema readiness |
| deploy / activate flow | sf-deploy | safe deployment sequence |
| create realistic bulk test data | sf-data | post-deploy verification |
| create Apex actions / invocables | sf-apex | imperative logic |
| embed LWC in a screen flow | sf-lwc | custom UI components |
| expose Flow to Agentforce | sf-ai-agentscript | agent action orchestration |
Reference Map
Start here
- references/flow-best-practices.md
- references/flow-quick-reference.md
- references/orchestration.md
- references/testing-guide.md
Design / orchestration
- references/subflow-library.md
- references/governance-checklist.md
- references/transform-vs-loop-guide.md
- references/orchestration-guide.md
- references/orchestration-parent-child.md
- references/orchestration-sequential.md
- references/orchestration-conditional.md
AI Decision
- references/ai-decision-guide.md
Screen / integration / troubleshooting
- references/form-building-guide.md
- references/integration-patterns.md
- references/lwc-integration-guide.md
- references/agentforce-flow-integration.md
- references/xml-gotchas.md
- references/testing-checklist.md
- references/wait-patterns.md
- assets/
Score Guide
| Score | Meaning |
|---|---|
| 88+ | production-ready Flow |
| 75–87 | good Flow with some review items |
| 60–74 | functional but needs stronger guardrails |
| < 60 | unsafe / incomplete for deployment |
FAQ
What does the sf-flow skill do?
Creates and validates Salesforce Flows with 110-point scoring. TRIGGER when: user builds or edits record-triggered, screen, autolaunched, or scheduled flows, or touches .flow-meta.xml files. DO NOT TRIGGER when: Apex automation (use sf-apex), process builder migration questions only, or non-Flow declarative config (use sf-metadata).
How do I install sf-flow?
Run npx skills add https://github.com/jaganpro/sf-skills --skill sf-flow in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/sf-flow/ (personal) or .claude/skills/sf-flow/ (project).
Which AI agents can use sf-flow?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is sf-flow safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains sf-flow?
It is published by jaganpro in jaganpro/sf-skills. It has 1,505 recorded installs.
More from jaganpro/sf-skills
sf-apex
jaganpro/sf-skills
Generates and reviews Salesforce Apex code with 150-point scoring. TRIGGER when: user writes, reviews, or fixes Apex classes, triggers, test classes, batch/queueable/schedulable jobs, or touches .cls/.trigger files. DO NOT TRIGGER when: LWC JavaScript (use sf-lwc), Flow XML (use sf-flow), SOQL-only queries (use sf-soql), or non-Salesforce code.
sf-lwc
jaganpro/sf-skills
Lightning Web Components with PICKLES methodology and 165-point scoring. TRIGGER when: user creates/edits LWC components, touches lwc//.js, .html, .css, .js-meta.xml files, or asks about wire service, SLDS, or Jest LWC tests. DO NOT TRIGGER when: Apex classes (use sf-apex), Aura components, or Visualforce.
sf-metadata
jaganpro/sf-skills
Salesforce metadata generation and querying with 120-point scoring. TRIGGER when: user creates custom objects, fields, validation rules, or touches .object-meta.xml, .field-meta.xml, .profile-meta.xml files. DO NOT TRIGGER when: permission set analysis (use sf-permissions), deploying metadata (use sf-deploy), or Flow XML (use sf-flow).
sf-soql
jaganpro/sf-skills
SOQL query generation, optimization, and analysis with 100-point scoring. TRIGGER when: user writes, optimizes, or debugs SOQL/SOSL queries, touches .soql files, or asks about relationship queries, aggregates, or query performance. DO NOT TRIGGER when: bulk data operations (use sf-data), Apex DML logic (use sf-apex), or report/dashboard queries.
sf-debug
jaganpro/sf-skills
Salesforce debug log analysis and troubleshooting with 100-point scoring. TRIGGER when: user analyzes debug logs, hits governor limits, reads stack traces, or touches .log files from Salesforce orgs. DO NOT TRIGGER when: running Apex tests (use sf-testing), fixing Apex code (use sf-apex), or Agentforce session tracing (use sf-ai-agentforce-observability).
sf-deploy
jaganpro/sf-skills
Salesforce DevOps automation using sf CLI v2. TRIGGER when: user deploys metadata, creates/manages scratch orgs or sandboxes, sets up CI/CD pipelines, or troubleshoots deployment errors with sf project deploy. DO NOT TRIGGER when: writing Apex/LWC code (use sf-apex/sf-lwc), creating metadata XML (use sf-metadata), or querying org data (use sf-data).
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.