State Machine logo

State Machine

Organization
MadAppGang
state-machine

Task lifecycle state transitions with validation gates. Defines states, triggers, and required proofs.

Overview

PublisherMadAppGang
Repositoryclaude-code
Skill namestate-machine
Stars
281
Forks
26
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by MadAppGang on GitHub. Read the source before you install it.

Installation

Install the State Machine AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/MadAppGang/claude-code.git /tmp/claude-code
mkdir -p .claude/skills
cp -r /tmp/claude-code/plugins/autopilot/skills/state-machine .claude/skills/state-machine
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable State Machine in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads State Machine on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so State Machine is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

plugin: autopilot updated: 2026-01-20

Task Lifecycle State Machine

Version: 0.1.0 Purpose: Manage task state transitions with validation gates Status: Phase 1

When to Use

Use this skill when you need to:

  • Understand valid state transitions for tasks
  • Implement validation gates before state changes
  • Handle iteration loops (In Review -> In Progress)
  • Manage escalation to blocked state
  • Enforce iteration limits

States

Todo ──→ In Progress ──→ In Review ──→ Done
                 ↑           │
                 └───────────┘
                 (iteration)

In Progress ──→ Blocked (escalation)

State Definitions

StateDescriptionEntry Condition
TodoTask queued for executionCreated with @autopilot label
In ProgressTask being executedPassed start gate
In ReviewAwaiting validationProof generated
DoneTask completedAuto-approved or user approved
BlockedCannot proceedDependency issue or escalation

Transition Triggers

FromToTriggerGate
TodoIn ProgressLabel @autopilot addedHas acceptance criteria
In ProgressIn ReviewWork completeProof >= 80% confidence
In ReviewDoneConfidence >= 95%Auto-approval
In ReviewDoneUser approvesUser feedback = APPROVAL
In ReviewIn ProgressConfidence < 80%Validation failed
In ReviewIn ProgressUser requests changesFeedback = REQUESTED_CHANGES
In ProgressBlockedMax iterationsEscalation
*BlockedUnresolvable blockerManual trigger

Validation Gates

Gate 1: Start Work (Todo -> In Progress)

typescript
async function canStartWork(issue: Issue): Promise<boolean> {
  const checks = [
    // Has acceptance criteria
    extractAcceptanceCriteria(issue.description).length > 0,

    // No blocking dependencies
    (await getBlockingIssues(issue)).length === 0,

    // Assigned to autopilot
    issue.assignee?.id === AUTOPILOT_BOT_USER_ID,
  ];

  return checks.every(c => c);
}

Gate 2: Submit for Review (In Progress -> In Review)

typescript
async function canSubmitForReview(proof: Proof): Promise<boolean> {
  const checks = [
    // All tests pass
    proof.testResults.passed === proof.testResults.total,

    // Build successful
    proof.buildSuccessful,

    // No lint errors
    proof.lintErrors === 0,

    // Has proof artifacts
    proof.screenshots.length > 0 || proof.deploymentUrl,
  ];

  return checks.every(c => c);
}

Gate 3: Complete (In Review -> Done)

typescript
async function canComplete(proof: Proof): Promise<{
  canProceed: boolean;
  autoApproved: boolean;
}> {
  if (proof.confidence >= 95) {
    return { canProceed: true, autoApproved: true };
  }

  if (proof.confidence >= 80) {
    return { canProceed: false, autoApproved: false };
    // Wait for user approval
  }

  return { canProceed: false, autoApproved: false };
  // Validation failed, should iterate
}

Iteration Limits

Loop TypeMax IterationsEscalation
Execution retry2Block task
Feedback rounds5Manual intervention
Quality check fixes2Report to user

Implementation

typescript
class StateMachine {
  async transition(
    issueId: string,
    targetState: string,
    proof?: Proof
  ): Promise<void> {
    const issue = await linear.issue(issueId);
    const currentState = issue.state.name;

    // Validate transition
    const isValid = this.validateTransition(currentState, targetState, proof);

    if (!isValid) {
      throw new Error(`Invalid transition: ${currentState} -> ${targetState}`);
    }

    // Execute transition
    await linear.issueUpdate(issueId, {
      stateId: await this.getStateId(issue.team.id, targetState),
    });

    // Log transition
    await this.logTransition(issueId, currentState, targetState, proof);
  }

  private validateTransition(
    from: string,
    to: string,
    proof?: Proof
  ): boolean {
    const validTransitions: Record<string, string[]> = {
      'Todo': ['In Progress', 'Blocked'],
      'In Progress': ['In Review', 'Blocked'],
      'In Review': ['Done', 'In Progress'],
      'Blocked': ['Todo', 'In Progress'],
    };

    return validTransitions[from]?.includes(to) ?? false;
  }
}

State Transition Diagram

                    ┌─────────────────────────────┐
                    │                             │
                    ▼                             │
┌──────┐       ┌─────────────┐       ┌───────────┴───┐       ┌──────┐
│ Todo │ ────► │ In Progress │ ────► │   In Review   │ ────► │ Done │
└──────┘       └─────────────┘       └───────────────┘       └──────┘
    │               │                        │
    │               │                        │
    │               ▼                        │
    │          ┌─────────┐                   │
    └────────► │ Blocked │ ◄─────────────────┘
               └─────────┘

Examples

Example 1: Happy Path

typescript
// Task created
await transitionState(issueId, 'In Progress');  // Gate: Has acceptance criteria

// Work complete, proof generated
await transitionState(issueId, 'In Review');    // Gate: Proof >= 80%

// High confidence auto-approval
await transitionState(issueId, 'Done');         // Gate: Confidence >= 95%

Example 2: Iteration Loop

typescript
// First attempt
await transitionState(issueId, 'In Progress');
await transitionState(issueId, 'In Review');    // Confidence: 85%

// User requests changes
await transitionState(issueId, 'In Progress');  // Feedback: REQUESTED_CHANGES

// Second attempt
await transitionState(issueId, 'In Review');    // Confidence: 97%
await transitionState(issueId, 'Done');         // Auto-approved

Example 3: Escalation

typescript
// After 5 feedback rounds
if (iterationCount >= MAX_FEEDBACK_ROUNDS) {
  await transitionState(issueId, 'Blocked');
  await addComment(issueId, "Escalated: Max iterations reached");
}

Best Practices

  • Always validate before transitioning
  • Log all transitions for audit trail
  • Include proof artifacts when transitioning to In Review
  • Enforce iteration limits to prevent infinite loops
  • Escalate gracefully rather than failing silently
  • Comment on Linear when state changes for visibility

Frequently asked questions

What does the State Machine AI skill do?

Task lifecycle state transitions with validation gates. Defines states, triggers, and required proofs.

Why use State Machine on TypingMind?

Because you install it once and use it with any model. State Machine is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install State Machine in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/MadAppGang/claude-code/tree/main/plugins/autopilot/skills/state-machine. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use State Machine?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with State Machine?

As many as you like. As long as a model supports skills, you can use State Machine with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the State Machine AI skill free?

Yes. It is published on GitHub by MadAppGang under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇