Track Manager logo

Track Manager

Community
Ibrahim-3d
track-manager

Manage Conductor tracks, phases, and tasks. Use when working with track status, updating task markers, or navigating between tracks. Enforces the Evaluate-Loop workflow.

Overview

PublisherIbrahim-3d
Repositoryorchestrator-supaconductor
Skill nametrack-manager
Stars
378
Forks
38
Bundled files
Instructions only
LicenseAGPL-3.0
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 Ibrahim-3d on GitHub. Read the source before you install it.

Installation

Install the Track Manager 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/Ibrahim-3d/orchestrator-supaconductor.git /tmp/orchestrator-supaconductor
mkdir -p .claude/skills
cp -r /tmp/orchestrator-supaconductor/skills/track-manager .claude/skills/track-manager
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Track Manager 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 Track Manager 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 Track Manager 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.

Track Manager Skill

Manage the lifecycle of Conductor tracks including status updates, task completion, and phase transitions. All operations follow the Evaluate-Loop process defined in conductor/workflow.md.

MANDATORY: Evaluate-Loop Integration

Every track operation must follow the Evaluate-Loop:

PLAN → EVALUATE PLAN → EXECUTE → EVALUATE EXECUTION → COMPLETE/FIX

Key rules:

  1. ALWAYS update plan.md after completing any task (prevents duplicate work across sessions)
  2. ALWAYS evaluate before marking anything complete
  3. NEVER skip the pre-execution plan evaluation

Trigger Conditions

Use this skill when:

  • Checking track status or progress
  • Marking tasks as complete
  • Transitioning between phases
  • Running pre/post execution evaluations
  • User mentions: "track status", "mark complete", "next task", "update plan", "evaluate"

Track Structure

conductor/
├── tracks.md           # Master track list
├── authority-matrix.md # Lead Engineer decision boundaries
├── schemas/
│   └── track-metadata.v2.json  # Metadata schema definition
└── tracks/
    └── <track_id>/
        ├── spec.md         # Requirements
        ├── plan.md         # Phased tasks (MUST be kept updated)
        └── metadata.json   # v2 status with loop_state

Metadata v2 Protocol

All tracks use the v2 metadata schema with explicit loop state tracking.

Creating a New Track

Initialize metadata.json with v2 structure:

json
{
  "version": 2,
  "track_id": "feature-name_20260131",
  "type": "feature",
  "status": "new",
  "created_at": "2026-01-31T00:00:00Z",
  "updated_at": "2026-01-31T00:00:00Z",

  "loop_state": {
    "current_step": "PLAN",
    "step_status": "NOT_STARTED",
    "fix_cycle_count": 0,
    "max_fix_cycles": 5,
    "plan_revision_count": 0,
    "max_plan_revisions": 3,
    "checkpoints": {
      "PLAN": { "status": "NOT_STARTED" },
      "EVALUATE_PLAN": { "status": "NOT_STARTED" },
      "EXECUTE": { "status": "NOT_STARTED" },
      "EVALUATE_EXECUTION": { "status": "NOT_STARTED" },
      "FIX": { "status": "NOT_STARTED" },
      "BUSINESS_SYNC": { "status": "NOT_STARTED", "required": false }
    }
  },

  "lead_consultations": [],
  "discovered_work": [],
  "blockers": []
}

Updating Loop State

When a step completes, update the checkpoint:

json
{
  "loop_state": {
    "current_step": "EXECUTE",
    "step_status": "IN_PROGRESS",
    "checkpoints": {
      "PLAN": {
        "status": "PASSED",
        "completed_at": "2026-01-31T10:00:00Z",
        "agent": "loop-planner"
      },
      "EVALUATE_PLAN": {
        "status": "PASSED",
        "completed_at": "2026-01-31T10:30:00Z",
        "verdict": "PASS"
      },
      "EXECUTE": {
        "status": "IN_PROGRESS",
        "started_at": "2026-01-31T11:00:00Z",
        "tasks_completed": 3,
        "tasks_total": 10,
        "last_task": "Task 1.3"
      }
    }
  }
}

Migrating v1 to v2

If a track has v1 metadata (no version field or loop_state):

  1. read_file current metadata fields
  2. Infer loop state from plan.md content
  3. Add v2 structure with inferred values
  4. write_file back to metadata.json

Task Status Markers

MarkerStatusDescription
[ ]PendingNot started
[~]In ProgressCurrently working
[x]CompletedDone (add commit SHA + summary)
[!]BlockedAdd note explaining why

Workflow Operations

Before Starting ANY Work

  1. read_file tracks.md to see what's already complete
  2. read_file the track's plan.md to see what tasks are done vs pending
  3. read_file spec.md to understand requirements
  4. Evaluate the plan — verify scope matches spec, no overlap with completed tracks

Start a Task

markdown
# Before
- [ ] Implement user authentication

# After (mark in progress)
- [~] Implement user authentication

Complete a Task (MANDATORY: update plan.md immediately)

markdown
# After completion (add commit SHA + summary of what was done)
- [x] Implement user authentication <!-- abc1234 -->
  - Created src/components/auth/signup-form.tsx
  - Added email/password validation
  - Integrated with mock API client

Update tracks.md

When completing a phase, update conductor/tracks.md:

markdown
## Active Tracks

| Track ID | Type    | Status      | Progress  |
| -------- | ------- | ----------- | --------- |
| auth-001 | feature | in_progress | Phase 2/3 |

Phase Transition Rules

  1. All tasks in phase must be [x] before moving to next phase
  2. Run post-execution evaluation (see Evaluate-Loop in conductor/workflow.md)
  3. If evaluation fails → create fix tasks → execute → re-evaluate (loop)
  4. If evaluation passes → update metadata.json with completion timestamp
  5. Create commit for phase completion
  6. Update tracks.md progress column
  7. Update conductor/index.md current status

Post-Execution Evaluation Checklist

Before marking a track complete, verify:

CheckQuestion
DeliverablesEvery deliverable in spec.md exists and is functional?
AlignmentImplementation matches what was planned (no scope drift)?
No RegressionsBuild passes? No console errors? Existing features work?
QualityUsability check passes on all user-facing copy?
plan.md UpdatedAll tasks marked [x] with summaries?
No LeftoverNo tasks skipped or left incomplete?

Response Format

After track operations:

## Track Update

**Track**: [track_id]
**Operation**: [started/completed/updated/evaluated]
**Phase**: [phase number] - [phase name]
**Progress**: [completed]/[total] tasks
**Evaluation**: [PASS / FAIL - describe issues]
**Next**: [next task description]

Frequently asked questions

What does the Track Manager AI skill do?

Manage Conductor tracks, phases, and tasks. Use when working with track status, updating task markers, or navigating between tracks. Enforces the Evaluate-Loop workflow.

Why use Track Manager on TypingMind?

Because you install it once and use it with any model. Track Manager 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 Track Manager in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Ibrahim-3d/orchestrator-supaconductor/tree/master/skills/track-manager. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Track Manager?

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 Track Manager?

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

Is the Track Manager AI skill free?

Yes. It is published on GitHub by Ibrahim-3d under the AGPL-3.0 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 👇