This is the skill you reach for when you need to generate Salesforce Flow metadata without writing XML by hand. It handles Screen Flows, Autolaunched Flows, Record-Triggered Flows, and Scheduled Flows by running a strict three-step pipeline: fetch your org's schema metadata, select the flow elements, then generate the XML piece by piece until complete. The pipeline is mandatory and runs through the execute_metadata_action MCP tool. No shortcuts, no manual XML editing. One practical detail worth knowing: the final generation step loops element by element, so a flow with fifteen components means fifteen calls. It keeps going automatically until isComplete returns true. If you're automating Salesforce business processes declaratively, this handles the metadata generation grunt work.

skills.sh installs
1.6K
GitHub stars
705
last updated
Jul 14, 2026

Install

$ npx -y skills add forcedotcom/afv-library --skill generating-flow --agent claude-code

Installs into .claude/skills of the current project.

Files

This is the skill you reach for when you need to generate Salesforce Flow metadata without writing XML by hand. It handles Screen Flows, Autolaunched Flows, Record-Triggered Flows, and Scheduled Flows by running a strict three-step pipeline: fetch your org's schema metadata, select the flow elements, then generate the XML piece by piece until complete. The pipeline is mandatory and runs through the execute_metadata_action MCP tool. No shortcuts, no manual XML editing. One practical detail worth knowing: the final generation step loops element by element, so a flow with fifteen components means fifteen calls. It keeps going automatically until isComplete returns true. If you're automating Salesforce business processes declaratively, this handles the metadata generation grunt work.

Browse the repository on GitHub

Sponsors

Details

Repository
github.com/forcedotcom/afv-library
First seen
May 16, 2026

More from forcedotcom/afv-library

All 58

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs