formula-authoring
Author TOML-based Formula workflow templates that become Protomolecules and active Molecules in Gas Town's durable workflow system.
Best use case
formula-authoring is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Author TOML-based Formula workflow templates that become Protomolecules and active Molecules in Gas Town's durable workflow system.
Teams using formula-authoring should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/formula-authoring/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How formula-authoring Compares
| Feature / Agent | formula-authoring | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Author TOML-based Formula workflow templates that become Protomolecules and active Molecules in Gas Town's durable workflow system.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Formula Authoring ## Overview Create and manage TOML-based Formula templates that define repeatable multi-step workflows. Formulas are cooked into Protomolecules (frozen, ready to instantiate) and then activated as Molecules (durable, checkpoint-able workflows). ## When to Use - Defining repeatable workflow templates - Creating multi-step processes with variable binding - Building workflows that must survive restarts - When NDI (Nondeterministic Idempotence) is needed ## Process 1. **Define** formula steps and variables in TOML format 2. **Validate** formula structure and dependencies 3. **Cook** into protomolecule (resolve variables, freeze) 4. **Test** by instantiating a trial molecule 5. **Register** in the formula library for reuse ## Formula Lifecycle ``` Formula (TOML template) -> Protomolecule (frozen) -> Molecule (active, durable) ``` ## Key Concepts - **Formula**: TOML-based workflow template with variables - **Protomolecule**: Frozen template ready to instantiate - **Molecule**: Active durable workflow surviving restarts - **NDI**: Nondeterministic Idempotence - useful outcomes from unreliable processes ## Tool Use Invoke via babysitter process: `methodologies/gastown/gastown-molecule`
Related Skills
qubo-formulator
QUBO (Quadratic Unconstrained Binary Optimization) formulation skill for optimization problems
homebrew-formula-generator
Generate Homebrew formula for CLI distribution on macOS and Linux.
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
babysitter
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
yolo
Run Babysitter autonomously with minimal manual interruption.
user-install
Install the user-level Babysitter Codex setup.
team-install
Install the team-pinned Babysitter Codex workspace setup.
retrospect
Summarize or retrospect on a completed Babysitter run.
resume
Resume an existing Babysitter run from Codex.
project-install
Install the Babysitter Codex workspace integration into the current project.
plan
Plan a Babysitter workflow without executing the run.
observe
Observe, inspect, or monitor a Babysitter run.