agentleFS
endlessblinkendlessblink/master-plan/skills/next/SKILL.md

next

Skill26 starsChanged 9 months agoMITView on GitHub

Analyze and pick the next task to work on. Reads MASTER_PLAN.md, scores tasks by priority and status, and presents interactive selection. Use when starting a session or deciding what to tackle next.

40 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use quick, project and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • codebycoreySkill

    quick

    Quick start a change with minimal interaction. Use when fast-tracking a straightforward change that needs proposal, design, and tasks in one step.

    Also in 3 projects that use this

  • BugRogerSkill

    project

    Project lifecycle management. Dispatches to Ada.

    Also in 3 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 9 projects that use this

  • MicrosoftSkill

    cleanup

    Also in 4 projects that use this

  • ArvorCoSkill

    clarify

    Identify and resolve ambiguities in feature specifications. Use when spec has unclear requirements. Triggers on: clarify spec, resolve ambiguities, clarify requirements.

    Also in 3 projects that use this

  • genomewalkerSkill

    explore

    RLM-style recursive memory exploration - dynamically navigate the memory graph

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. 0 are common, 6 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 36 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search for the plan file in order:

    line 32
  2. Very specific:

    If not found, tell the user: "No MASTER_PLAN.md found.

    line 38
  3. Very specific:

    Read the file and extract tasks from ### headers matching this pattern:

    line 42
  4. Very specific:

    Priority: Look in the lines following the header for Priority: P0-P3.

    line 59
  5. Distinctive:

    Look for IN PROGRESS tasks first — these should be finished before starting new work.

    line 63
  6. Very specific:

    If uncommitted changes exist, mention: "You have uncommitted changes — consider committing or running /master-plan:save first."

    line 70
  7. Very specific:

    Use AskUserQuestion to let user pick from the top tasks:

    line 84
  8. Distinctive:

    If there are IN PROGRESS tasks, always show them first with a note: "You have N task(s) in progress."

    line 106
  9. Very specific:

    When user selects a task, show the full section from MASTER_PLAN.md:

    line 110
  10. Distinctive:

    After showing task details, ask:

    line 116
  11. Distinctive:

    If "Start working on this" is selected:

    line 133
  12. Very specific:

    Update the task's status to IN PROGRESS in MASTER_PLAN.md (all locations — see update rules below)

    line 134
  13. Distinctive:

    Always verify with a grep after updating.

    line 145

“Common” is measured: kept by at least 6 in 10 of the 36 edited versions of this file we could read. “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

What's Next?

Analyze MASTER_PLAN.md tasks, score by priority/status, and let the user pick interactively.

Triggers

  • /master-plan:next - Main command
  • "what should I work on", "pick a task", "next task", "what's next"

Arguments

ArgumentFilter
bugsOnly BUG-XXX tasks
progressOnly IN PROGRESS tasks
plannedOnly PLANNED (backlog) tasks
reviewOnly REVIEW tasks
activeIN PROGRESS + REVIEW
allInclude DONE tasks

Example: /master-plan:next bugs or /master-plan:next planned

Workflow

Step 1: Find MASTER_PLAN.md

Search for the plan file in order:

  1. docs/MASTER_PLAN.md
  2. MASTER_PLAN.md
  3. master-plan.md
  4. docs/master-plan.md

If not found, tell the user: "No MASTER_PLAN.md found. Run /master-plan:task to create your first task, or create one from the template."

Step 2: Parse Tasks

Read the file and extract tasks from ### headers matching this pattern:

### [optional ~~]TASK-123[optional ~~]: Title (STATUS)

Regex: ^###\s+(~~)?((TASK|BUG|FEATURE|ROAD|IDEA|ISSUE|INQUIRY)-\d+)(~~)?:\s*(.+?)\s*\(([^)]+)\)

For each match, extract:

  • ID: e.g., TASK-123, BUG-456
  • Title: The text after : and before (
  • Status: Text in parentheses. Normalize:
    • Contains "DONE", "COMPLETE", "FIXED", "✅", or has strikethrough → DONE
    • Contains "IN PROGRESS", "🔄" → IN PROGRESS
    • Contains "REVIEW", "👀" → REVIEW
    • Contains "PAUSED", "⏸️" → PAUSED
    • Otherwise → PLANNED
  • Priority: Look in the lines following the header for **Priority**: P0-P3. Default to P2 if not found.

Step 3: Check for Active Work

Look for IN PROGRESS tasks first — these should be finished before starting new work.

Also check git status:

git status --short

If uncommitted changes exist, mention: "You have uncommitted changes — consider committing or running /master-plan:save first."

Step 4: Sort and Filter

Default sort order (what to START next):

  1. PLANNED first, then REVIEW, IN PROGRESS, PAUSED, DONE last
  2. Within same status: P0 → P1 → P2 → P3

If $ARGUMENTS contains a filter (bugs, progress, planned, review, active), apply it before sorting.

Exclude DONE tasks unless $ARGUMENTS contains all.

Step 5: Present Interactive Selection

Use AskUserQuestion to let user pick from the top tasks:

AskUserQuestion({
  questions: [{
    question: "Which task would you like to work on?",
    header: "Task",
    multiSelect: false,
    options: [
      // Top 4 tasks, formatted as:
      { label: "TASK-XXX: Title here", description: "P0 · IN PROGRESS" },
      { label: "BUG-YYY: Another task", description: "P1 · PLANNED" },
      // ...
    ]
  }]
})

Option formatting:

  • Label: {ID}: {title (max 40 chars)}
  • Description: {priority} · {status}

If there are IN PROGRESS tasks, always show them first with a note: "You have N task(s) in progress."

Step 6: Show Task Details

When user selects a task, show the full section from MASTER_PLAN.md:

  • ID, title, status, priority
  • Description (everything between this ### header and the next ### or ##)

Step 7: Offer Actions

After showing task details, ask:

AskUserQuestion({
  questions: [{
    question: "What would you like to do?",
    header: "Action",
    multiSelect: false,
    options: [
      { label: "Start working on this", description: "Update status to IN PROGRESS" },
      { label: "Pick a different task", description: "Go back to task list" },
      { label: "Just show context", description: "No status change" }
    ]
  }]
})

If "Start working on this" is selected:

  1. Update the task's status to IN PROGRESS in MASTER_PLAN.md (all locations — see update rules below)
  2. Confirm: "Started TASK-XXX. Ready to begin implementation."

MASTER_PLAN.md Update Rules

Tasks may appear in multiple locations. When updating status, check ALL of:

  1. Summary/Roadmap table — Update the status column
  2. Detailed ### section header — Update (STATUS) in parentheses
  3. Subtask bullet points — Add strikethrough + ✅ if marking DONE

Always verify with a grep after updating.

Rules

  1. Finish before starting — Always highlight IN PROGRESS tasks first
  2. P0 trumps all — Critical issues come first regardless of status
  3. Interactive selection — Always use AskUserQuestion, never just print a list
  4. Context on selection — Always show full task details when picked
  5. Action oriented — Offer to start work immediately

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.