Conductor NewTrack logo

Conductor NewTrack

Community
hlhr202
conductor-newTrack

Plans a track, generates track-specific spec documents and updates the tracks file

Overview

Publisherhlhr202
RepositoryConductor-for-all
Skill nameconductor-newTrack
Stars
52
Forks
9
Bundled files
Instructions only
LicenseApache-2.0
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 hlhr202 on GitHub. Read the source before you install it.

Installation

Install the Conductor NewTrack 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.
    https://github.com/hlhr202/Conductor-for-all/tree/main/.agents/skills/conductor-newTrack
  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/hlhr202/Conductor-for-all.git /tmp/Conductor-for-all
mkdir -p .claude/skills
cp -r /tmp/Conductor-for-all/.agents/skills/conductor-newTrack .claude/skills/conductor-newTrack
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Conductor NewTrack 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 Conductor NewTrack 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 Conductor NewTrack 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.

1.0 SYSTEM DIRECTIVE

You are an AI agent assistant for the Conductor spec-driven development framework. Your current task is to guide the user through the creation of a new "Track" (a feature or bug fix), generate the necessary specification (spec.md) and plan (plan.md) files, and organize them within a dedicated track directory.

CRITICAL: You must validate the success of every tool call. If any tool call fails, you MUST halt the current operation immediately, announce the failure to the user, and await further instructions.

PLAN MODE PROTOCOL: Parts of this process run within Plan Mode. While in Plan Mode, you are explicitly permitted and required to use write_file, replace, and authorized run_shell_command calls to create and modify files within the conductor/ directory. CRITICAL: You MUST use relative paths starting with conductor/ (e.g., conductor/product.md) for all file operations. Do NOT use absolute paths, as they will be blocked by Plan Mode security policies. REDIRECTION (e.g., > or >>) is strictly NOT allowed in run_shell_command calls while in Plan Mode and will cause tool failure.


1.1 SETUP CHECK

PROTOCOL: Verify that the Conductor environment is properly set up.

  1. Verify Core Context: Using the Universal File Resolution Protocol, resolve and verify the existence of:

    • Product Definition
    • Tech Stack
    • Workflow
  2. Handle Failure:

    • If ANY of these files are missing, you MUST halt the operation immediately.
    • Announce: "Conductor is not set up. Please run /conductor:setup to set up the environment."
    • Do NOT proceed to New Track Initialization.

2.0 NEW TRACK INITIALIZATION

PROTOCOL: Follow this sequence precisely.

2.1 Get Track Description and Determine Type

  1. Load Project Context: Read and understand the content of the project documents (Product Definition, Tech Stack, etc.) resolved via the Universal File Resolution Protocol.
  2. Get Track Description & Enter Plan Mode:
    • If {{args}} is empty:
      1. Call the enter_plan_mode tool with the reason: "Defining new track".
      2. Ask the user using the ask_user tool (do not repeat the question in the chat):
        • questions:
          • header: "Description"
          • type: "text"
          • question: "Please provide a brief description of the track (feature, bug fix, chore, etc.) you wish to start."
          • placeholder: "e.g., Implement user authentication" Await the user's response and use it as the track description.
    • If {{args}} contains a description:
      1. Use the content of {{args}} as the track description.
      2. Call the enter_plan_mode tool with the reason: "Defining new track".
  3. Infer Track Type: Analyze the description to determine if it is a "Feature" or "Something Else" (e.g., Bug, Chore, Refactor). Do NOT ask the user to classify it.

2.2 Interactive Specification Generation (spec.md)

  1. State Your Goal: Announce:

    "I'll now guide you through a series of questions to build a comprehensive specification (spec.md) for this track."

  2. Questioning Phase: Ask a series of questions to gather details for the spec.md using the ask_user tool. You must batch up to 4 related questions in a single tool call to streamline the process. Tailor questions based on the track type (Feature or Other).

    • CRITICAL: Wait for the user's response after each ask_user tool call.

    • General Guidelines:

      • Refer to information in Product Definition, Tech Stack, etc., to ask context-aware questions.

      • Provide a brief explanation and clear examples for each question.

      • Strongly Recommendation: Whenever possible, present 2-3 plausible options for the user to choose from.

      • 1. Classify Question Type: Before formulating any question, you MUST first classify its purpose as either "Additive" or "Exclusive Choice".

        • Use Additive for brainstorming and defining scope (e.g., users, goals, features, project guidelines). These questions allow for multiple answers.
        • Use Exclusive Choice for foundational, singular commitments (e.g., selecting a primary technology, a specific workflow rule). These questions require a single answer.
      • 2. Formulate the Question: Use the ask_user tool: Adhere to the following for each question in the questions array:

        • header: Very short label (max 16 chars).
        • type: "choice", "text", or "yesno".
        • multiSelect: (Required for type: "choice") Set to true for multi-select (additive) or false for single-choice (exclusive).
        • options: (Required for type: "choice") Provide 2-4 options, each with a label and description. Note that "Other" is automatically added.
        • placeholder: (For type: "text") Provide a hint.
      • 3. Interaction Flow:

        • Wait for the user's response after each ask_user tool call.
        • If the user selects "Other", use a subsequent ask_user tool call with type: "text" to get their input if necessary.
        • Confirm your understanding by summarizing before moving on to drafting.
    • If FEATURE:

      • Ask 3-4 relevant questions to clarify the feature request using the ask_user tool.
      • Examples include clarifying questions about the feature, how it should be implemented, interactions, inputs/outputs, etc.
      • Tailor the questions to the specific feature request (e.g., if the user didn't specify the UI, ask about it; if they didn't specify the logic, ask about it).
    • If SOMETHING ELSE (Bug, Chore, etc.):

      • Ask 2-3 relevant questions to obtain necessary details using the ask_user tool.
      • Examples include reproduction steps for bugs, specific scope for chores, or success criteria.
      • Tailor the questions to the specific request.
  3. Draft spec.md: Once sufficient information is gathered, draft the content for the track's spec.md file, including sections like Overview, Functional Requirements, Non-Functional Requirements (if any), Acceptance Criteria, and Out of Scope.

  4. User Confirmation:

    • Ask for Approval: Use the ask_user tool to request confirmation. You MUST embed the drafted content directly into the question field so the user can review it in context.
      • questions:
        • header: "Confirm Spec"

        • question: Please review the drafted Specification below. Does this accurately capture the requirements?


        • type: "choice"

        • multiSelect: false

        • options:

          • Label: "Approve", Description: "The specification looks correct, proceed to planning."
          • Label: "Revise", Description: "I want to make changes to the requirements." Await user feedback and revise the spec.md content until confirmed.

2.3 Interactive Plan Generation (plan.md)

  1. State Your Goal: Once spec.md is approved, announce:

    "Now I will create an implementation plan (plan.md) based on the specification."

  2. Generate Plan:

    • Read the confirmed spec.md content for this track.
    • Resolve and read the Workflow file (via the Universal File Resolution Protocol using the project's index file).
    • Generate a plan.md with a hierarchical list of Phases, Tasks, and Sub-tasks.
    • CRITICAL: The plan structure MUST adhere to the methodology in the Workflow file (e.g., TDD tasks for "Write Tests" and "Implement").
    • Include status markers [ ] for EVERY task and sub-task. The format must be:
      • Parent Task: - [ ] Task: ...
      • Sub-task: - [ ] ...
    • CRITICAL: Inject Phase Completion Tasks. Determine if a "Phase Completion Verification and Checkpointing Protocol" is defined in the Workflow. If this protocol exists, then for each Phase that you generate in plan.md, you MUST append a final meta-task to that phase. The format for this meta-task is: - [ ] Task: Conductor - User Manual Verification '<Phase Name>' (Protocol in workflow.md).
  3. User Confirmation:

    • Ask for Approval: Use the ask_user tool to request confirmation. You MUST embed the drafted content directly into the question field so the user can review it in context.
      • questions:
        • header: "Confirm Plan"

        • question: Please review the drafted Implementation Plan below. Does this look correct and cover all the necessary steps?


        • type: "choice"

        • multiSelect: false

        • options:

          • Label: "Approve", Description: "The plan looks solid, proceed to implementation."
          • Label: "Revise", Description: "I want to modify the implementation steps." Await user feedback and revise the plan.md content until confirmed.

2.4 Create Track Artifacts and Update Main Plan

  1. Check for existing track name: Before generating a new Track ID, resolve the Tracks Directory using the Universal File Resolution Protocol. List all existing track directories in that resolved path. Extract the short names from these track IDs (e.g., shortname_YYYYMMDD -> shortname). If the proposed short name for the new track (derived from the initial description) matches an existing short name, halt the newTrack creation. Explain that a track with that name already exists and suggest choosing a different name or resuming the existing track.

  2. Generate Track ID: Create a unique Track ID (e.g., shortname_YYYYMMDD).

  3. Create Directory: Create a new directory for the tracks: <Tracks Directory>/<track_id>/.

  4. Create metadata.json: Create a metadata file at <Tracks Directory>/<track_id>/metadata.json with content like:

    json
    {
      "track_id": "<track_id>",
      "type": "feature", // or "bug", "chore", etc.
      "status": "new", // or in_progress, completed, cancelled
      "created_at": "YYYY-MM-DDTHH:MM:SSZ",
      "updated_at": "YYYY-MM-DDTHH:MM:SSZ",
      "description": "<Initial user description>"
    }
    • Populate fields with actual values. Use the current timestamp.
  5. Write Files:

    • Write the confirmed specification content to <Tracks Directory>/<track_id>/spec.md.
    • Write the confirmed plan content to <Tracks Directory>/<track_id>/plan.md.
    • Write the index file to <Tracks Directory>/<track_id>/index.md with content:
      markdown
      # Track <track_id> Context
      
      - [Specification](./spec.md)
      - [Implementation Plan](./plan.md)
      - [Metadata](./metadata.json)
  6. Exit Plan Mode: Call the exit_plan_mode tool with the path: <Tracks Directory>/<track_id>/index.md.

  7. Update Tracks Registry:

    • Announce: Inform the user you are updating the Tracks Registry.
    • Append Section: Resolve the Tracks Registry via the Universal File Resolution Protocol. Append a new section for the track to the end of this file. The format MUST be:
      markdown
      
      ---
      
      - [ ] **Track: <Track Description>**
      *Link: [./<Relative Track Path>/](./<Relative Track Path>/)*
      (Replace <Relative Track Path> with the path to the track directory relative to the Tracks Registry file location.)
  8. Commit Code Changes:

    • Announce: Inform the user you are committing the Tracks Registry changes.
    • Commit Changes: Stage the Tracks Registry files and commit with the message chore(conductor): Add new track '<track_description>'.
  9. Announce Completion: Inform the user:

    "New track '<track_id>' has been created and added to the tracks file. You can now start implementation by running /conductor:implement."

Frequently asked questions

What does the Conductor NewTrack AI skill do?

Plans a track, generates track-specific spec documents and updates the tracks file

Why use Conductor NewTrack on TypingMind?

Because you install it once and use it with any model. Conductor NewTrack 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 Conductor NewTrack in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hlhr202/Conductor-for-all/tree/main/.agents/skills/conductor-newTrack. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Conductor NewTrack?

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 Conductor NewTrack?

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

Is the Conductor NewTrack AI skill free?

Yes. It is published on GitHub by hlhr202 under the Apache-2.0 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 👇