fsm-builder
Skill1 starsChanged 49 days agoMITView on GitHub
Scaffolds Finite State Machine (FSM) patterns for multi-step conversational flows and wizards.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- create-db-schemaSkill
- i18n-builderSkill
- keyboard-navigatorSkill
- mini-app-builderSkill
- payment-gateway-setupSkill
- setup-webhookSkill
- tg-api-navigatorSkill
- tg-copywriterSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Follow these constraints when building conversation state machines:
- Distinctive: line 19
Use in-memory storage for local test setups.
- Distinctive: line 20
Use Redis storage for production deployments to survive process restarts and enable horizontal worker scaling.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Finite State Machine Protocol
Follow these constraints when building conversation state machines:
- State Definition:
- Group related states into typed enums or state groups (e.g.,
RegistrationState: [name, email, confirmation]). - Define an explicit exit/cancel state at every step.
- Group related states into typed enums or state groups (e.g.,
- Handler Structure:
- Register an entry handler triggered by commands or inline buttons.
- Register isolated handlers for every distinct state.
- Register a universal fallback handler to capture invalid inputs without resetting context.
- Storage Backend:
- Use in-memory storage for local test setups.
- Use Redis storage for production deployments to survive process restarts and enable horizontal worker scaling.
- Validation and Transition:
- Validate incoming payloads before mutating state.
- Clear state upon successful flow completion or explicit
/cancel.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.