How does /go decide which agents to use?

The orchestrator checks the superpower_enhanced flag in metadata. If true, it dispatches superpowers (superpowers:writing-plans, superpowers:executing-plans, superpowers:systematic-debugging); otherwise it uses legacy loop agents (loop-planner, loop-executor, loop-fixer).

What happens if there is no matching track?

It creates a new track in conductor/tracks/{goal-slug}_{date}/, generates spec.md and plan.md, and metadata.json with superpower_enhanced: true by default.

How do I resume an existing track?

Run /go to continue the active track or /go continue; the system resumes from the track's current state.

go

Scanned

npx machina-cli add skill Ibrahim-3d/conductor-orchestrator-superpowers/go --openclaw

Files (1)

SKILL.md

2.3 KB

/go -- Goal-Driven Entry Point

The single entry point to the entire Conductor system.

Just state your goal. The system handles everything else.

Usage

/go <your goal>

Examples

/go Add Stripe payment integration
/go Fix the login bug where users get logged out
/go Build a dashboard with analytics
/go Refactor the asset generation to use caching

What Happens

When you invoke /go, follow this process:

1. Goal Analysis

Parse the user's goal from $ARGUMENTS:

Identify the type (feature, bugfix, refactor, etc.)
Estimate complexity
Extract key requirements

2. Track Detection

Check conductor/tracks.md for matching existing tracks:

If match found: Resume that track from its current state
If no match: Create a new track

3. For New Tracks

Create track directory: conductor/tracks/{goal-slug}_{date}/
Generate spec.md from the goal
Generate plan.md with DAG
Create metadata.json with v3 schema AND set superpower_enhanced: true (new tracks use superpowers by default)

Example metadata.json:

{
  "version": 3,
  "track_id": "goal-slug_20260213",
  "type": "feature",
  "status": "new",
  "superpower_enhanced": true,
  "loop_state": {
    "current_step": "NOT_STARTED",
    "step_status": "NOT_STARTED"
  }
}

4. Run the Evaluate-Loop

Invoke the conductor-orchestrator agent:

Use the conductor-orchestrator agent to run the evaluate-loop for this track.

The orchestrator will:

Detect current step from metadata
Check superpower_enhanced flag to determine which agents to use:
- If true (new tracks): Dispatch superpowers (superpowers:writing-plans, superpowers:executing-plans, superpowers:systematic-debugging)
- If false/missing (legacy): Dispatch legacy loop agents (loop-planner, loop-executor, loop-fixer)
Monitor progress and handle failures
Complete the track or escalate if blocked

Escalation Points

Stop and ask user when:

Goal is ambiguous
Multiple interpretations possible
Scope conflicts with existing tracks
Board rejects the plan
Fix cycle exceeds 3 iterations

Resume Existing Work

/go                    # Continues the active track
/go continue           # Same as above

Source

git clone https://github.com/Ibrahim-3d/conductor-orchestrator-superpowers/blob/master/skills/go/SKILL.mdView on GitHub

Overview

Go is the single entry point to the entire Conductor system. Just state your goal and the system handles everything else, from track creation to planning and execution. This brings end-to-end automation to complex workflows.

How This Skill Works

When you run /go <your goal>, the system analyzes the goal, detects matching tracks in conductor/tracks.md, and either resumes an existing track or creates a new one with a track directory, spec.md, plan.md, and metadata.json. It then runs the Evaluate-Loop via the conductor-orchestrator, using superpowers for new tracks (superpower_enhanced: true) and legacy agents for older tracks.

When to Use It

Kick off a new feature, bugfix, or refactor by stating your goal with /go
Resume an active track to continue work without redoing steps
Handle ambiguous goals that require clarification or multiple interpretations
When a plan is rejected or scope conflicts with existing tracks
Continue the active track using /go to keep momentum

Quick Start

Step 1: /go <your goal>
Step 2: System analyzes goal, matches or creates a track
Step 3: If new, track files are generated and the evaluate-loop is launched

Best Practices

Be explicit about the goal type (feature, bugfix, refactor) in /go
Check conductor/tracks.md for existing tracks before starting a new one
Provide clear, testable requirements and acceptance criteria in the goal
Use /go continue to resume the active track rather than starting a new one
For new tracks, verify the generated metadata has superpower_enhanced: true

Example Use Cases

Add Stripe payment integration
Fix the login bug where users get logged out
Build a dashboard with analytics
Refactor the asset generation to use caching
Kick off a goal with /go <your goal> to start automation

Frequently Asked Questions

Add this skill to your agents