agentleFS
hlhr202hlhr202/Conductor-for-all/.agents/skills/conductor-newTrack/SKILL.md

conductor-newTrack

Skill52 starsChanged 8 months agoApache-2.0View on GitHub

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

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. airclear/skills★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository7 other files it gives its agents.

The file

Show its rules and text

We split this skill into the rules it gives an agent

23 rules. About 0 are common, 6 are distinctive, and 17 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 17

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If ANY of these files are missing, you MUST halt the operation immediately.

    line 24
  2. Distinctive:

    Do NOT proceed to New Track Initialization.

    line 26
  3. Distinctive:

    Load Project Context: Read and understand the content of the project documents (Product Definition, Tech Stack, etc.) resolved via the …

    line 35
  4. Very specific:

    Call the enter_plan_mode tool with the reason: "Defining new track".

    line 38
  5. Very specific:

    Ask the user using the ask_user tool (do not repeat the question in the chat):

    line 39
  6. Very specific:

    Use the content of {{args}} as the track description.

    line 47
  7. Very specific:

    Questioning Phase: Ask a series of questions to gather details for the spec.md using the ask_user tool.

    line 56
  8. Very specific:

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

    line 57
  9. Distinctive:

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

    line 63
  10. Distinctive:

    Use Additive for brainstorming and defining scope (e.g., users, goals, features, project guidelines).

    line 64
  11. Distinctive:

    Use Exclusive Choice for foundational, singular commitments (e.g., selecting a primary technology, a specific workflow rule).

    line 65
  12. Very specific:

    2. Formulate the Question: Use the ask_user tool: Adhere to the following for each question in the questions array:

    line 67
  13. Very specific:

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

    line 75
  14. Very specific:

    If the user selects "Other", use a subsequent ask_user tool call with type: "text" to get their input if necessary.

    line 76
  15. Very specific:

    Ask for Approval: Use the ask_user tool to request confirmation.

    line 92
  16. Very specific:

    Read the confirmed spec.md content for this track.

    line 114
  17. Very specific:

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

    line 143
  18. Very specific:

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

    line 144
  19. Very specific:

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

    line 145
  20. Very specific:

    Write the confirmed specification content to <Tracks Directory>/<track_id>/spec.md.

    line 158
  21. Very specific:

    Write the confirmed plan content to <Tracks Directory>/<track_id>/plan.md.

    line 159
  22. Very specific:

    Write the index file to <Tracks Directory>/<track_id>/index.md with content:

    line 160
  23. Very specific:

    Exit Plan Mode: Call the exit_plan_mode tool with the path: <Tracks Directory>/<track_id>/index.md.

    line 168

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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?


          <Insert Drafted spec.md Content Here>
        • 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?


          <Insert Drafted plan.md Content Here>
        • 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:
    {
      "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:
      # 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:
      
      ---
      
      - [ ] **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."

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.