Agent skill · software engineering · aradotso
fabro-workflow-factory
Skill for using Fabro, the open source AI coding workflow orchestrator that lets you define agent pipelines as Graphviz DOT graphs with human gates, multi-model routing, and cloud sandboxes.
Why this skill is useful
Adds executable scripts for managing AI workflows and human-in-the-loop processes that are not widely known.
What it needs
Requires fabro installed locally. About 7k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
Fabro Workflow Factory Skill by ara.so — Daily 2026 Skills collection. Fabro is an open source AI coding workflow orchestrator written in Rust. It lets you define agent pipelines as Graphviz DOT graphs — with branching, loops, human approval gates, multi-model routing, and cloud sandbox execution — then run them as a persistent service. You define the process; agents execute it; you intervene only where it matters. --- Installation After installation, run one-time setup and per-project initialization: --- Key CLI Commands --- Workflow Definition (Graphviz DOT) Workflows are .dot files using the Graphviz DOT language with Fabro-specific attributes. Node Types Shape Meaning --- --- Mdiamond Start node Msquare Exit node rectangle (default) Agent node (LLM turn) hexagon Human gate (pauses for approval) Minimal Hello World --- Multi-Model Routing with Stylesheets Fabro uses CSS-like modelstylesheet declarations on the graph to route nodes to models. Use classes to target groups of nodes. Supported Model Stylesheet Properties --- Human Gates (Approval Nodes) Use shape=hexagon to pause execution for human approval. Transitions are labeled with [A] (approve) and [R] (revise/reject). Approve or reject from the CLI: --- Loops and Fix Cycles Use labeled transitions to build automatic retry/fix loops: --- Parallel Nodes Run multiple agent nodes concurrently by forking edges from a single source: --- Variables and Dynamic Prompts Use {variable} interpolation in prompts. Pass variables at run time: --- Cloud Sandboxes (Daytona) To run agents in isolated cloud VMs instead of locally, configure a Daytona sandbox: Then add sandbox config to your workflow graph: --- Git Checkpointing Fabro automatically commits code changes and execution metadata to Git branches at each stage. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/fabro-workflow-factory