Skill

plan-task

Generates the next self-contained task file from a plan, with context, scope, acceptance criteria, and constraints. Tracks progress for sequential decomposition.

developer-tools

automation

npx claudepluginhub haowjy/orchestrate --plugin orchestrate

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Create the next implementable task from a plan.

SKILL.md

Similar Skills

implement-plan

Parses plan Markdown files from context/plans/ into Claude Code tasks: implementation steps with files and verification tasks with dependencies. Invoke via /implement-plan [filename].

arete

task-decomposition

Decomposes contextualized plans into atomic, independently executable tasks with embedded context, CLEAR ordering, CoVe checks, and dependency graphs for parallel execution.

task-breakdown

Breaks down implementation plans into detailed task lists with agent contexts, acceptance criteria, dependencies, priorities, complexity levels, and status tracking.

claudio

Stats

Stars16

Forks4

Last CommitMar 1, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Plan Task

Create the next implementable task from a plan.

When Invoked

Step 1: Read Inputs

Use these prompt variables:

{{PLAN_FILE}} — source plan to read

Resolve output directory:

Always use a path next to the plan: <dir-of-PLAN_FILE>/tasks.

Create the output directory if it does not exist.

Step 2: Read Progress

Gather context on what is already completed:

Read {{PLAN_FILE}} and inspect status/phase tracking sections.

If <resolved-tasks-dir>/progress.md exists, read it for prior completed tasks.

If <resolved-tasks-dir>/task.md exists, use it as context for continuity.

Step 3: Determine Completion

If all phases/steps in the plan are complete:

Write only the text ALL_DONE to <resolved-tasks-dir>/task.md.

Stop here.

Step 4: Create Task File

Determine the next logical task from the plan.

Write <resolved-tasks-dir>/task.md. Include whatever structure makes sense, but the task file should give an implementing agent everything it needs:

Context: why this task is next

Scope: what to implement — files, functions, integration points

Acceptance criteria: how to verify it's done

Constraints: architectural limits, gotchas

A good task is self-contained: the codebase must be in a working state when done. Size is secondary — focus on logical completeness, not line count.

Plan Task

Create the next implementable task from a plan.

When Invoked

Step 1: Read Inputs

Use these prompt variables:

{{PLAN_FILE}} — source plan to read

Resolve output directory:

Always use a path next to the plan: <dir-of-PLAN_FILE>/tasks.
Create the output directory if it does not exist.

Step 2: Read Progress

Gather context on what is already completed:

Read {{PLAN_FILE}} and inspect status/phase tracking sections.
If <resolved-tasks-dir>/progress.md exists, read it for prior completed tasks.
If <resolved-tasks-dir>/task.md exists, use it as context for continuity.

Step 3: Determine Completion

If all phases/steps in the plan are complete:

Write only the text ALL_DONE to <resolved-tasks-dir>/task.md.
Stop here.

Step 4: Create Task File

Determine the next logical task from the plan.

Write <resolved-tasks-dir>/task.md. Include whatever structure makes sense, but the task file should give an implementing agent everything it needs:

Context: why this task is next
Scope: what to implement — files, functions, integration points
Acceptance criteria: how to verify it's done
Constraints: architectural limits, gotchas

A good task is self-contained: the codebase must be in a working state when done. Size is secondary — focus on logical completeness, not line count.