analyze-task

Analyze Task

Use this skill before coding for non-trivial repository work:

• new features
• cross-layer changes
• architecture or model changes
• complex bugs
• tasks that likely need multiple commits / reviews / loops

Do not use it for tiny local edits that can be implemented and verified immediately.

Purpose

Produce a short Analysis Brief that makes the task discussable and executable.

This skill is for:

• clarifying the goal
• defining non-goals
• identifying what must be decided before coding
• deciding whether a subagent is justified
• preparing the task for a scope-alignment discussion
• setting up the handoff to write-task-todo only after alignment

This skill is not for writing code and not for writing docs/todolist.md.

Core rules

1. Prioritize structure before UI

   • think about canonical docs/contracts, data model, types, interfaces, repo/service/runtime boundaries before UI details

2. Prefer explicit boundaries

   • say what is in scope and what is not
   • surface ambiguity instead of silently choosing

3. Use subagents selectively

   • default is local analysis
   • use an xhigh explorer subagent only when the task is cross-layer, ambiguous, high-risk, or likely to benefit from an independent architectural read
   • if you use a subagent, give it a narrow question; do not outsource the entire solution

4. Do not create a canonical doc yet unless the concept is already clearly stable and long-lived

   • early definitions belong in analysis/todo first

5. Every analysis should end with an alignment state:

   • ready for alignment discussion
   • ready for write-task-todo after confirmation
   • or blocked on a single clarification

Required output

Produce a brief with these sections:

## Analysis Brief

### Goal

### Product Boundary

### Scope

### Non-goals

### Canonical-Doc Impact

### Data / Type / Interface First

### Layer Impact

### Risks / Ambiguities

### Need Subagent?

### Test Strategy

### Alignment Questions

### Ready for Todo?