From skill-issue
Clarifies under-defined problems, resolves ambiguous outcomes, and compares options before committing to a plan. Use when the problem, outcome, or direction is unclear.
How this skill is triggered — by the user, by Claude, or both
Slash command
/skill-issue:brainstormingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Clarify what should be built before planning begins. Resolve ambiguity in the problem, the intended outcome, or the approach. Land on a clear direction that planning can execute against.
Clarify what should be built before planning begins. Resolve ambiguity in the problem, the intended outcome, or the approach. Land on a clear direction that planning can execute against.
These categories should be covered during the interview step. Not every category applies to every brainstorm — mark N/A when not relevant.
Brainstorm documents are written to docs/brainstorms/ with date-prefixed filenames:
docs/brainstorms/YYYY-MM-DD-<descriptive-name>.md
---
title: <brainstorm title>
date: YYYY-MM-DD
status: exploring | decided
---
# <Brainstorm Title>
## Problem Statement
What problem is being solved and why it matters.
## User Intent
Who needs this and what outcome they expect.
## Success Criteria
How to know the solution is working.
## Constraints
Known limits that shape the direction.
## Options Explored
Viable directions considered. What each offers and its key tradeoff.
### Option A: <name>
<description and tradeoff>
### Option B: <name>
<description and tradeoff>
### Selected: <option>
<why this direction>
## Architecture Sketch
Rough sketch of boundaries and data flow for the selected direction. Use Mermaid fenced code blocks.
```mermaid
graph LR
A[Service] --> B[Service]
Decisions made during exploration with rationale.
Unresolved questions that planning or implementation must answer.
What happens next — typically planning.
## Constraints On This Skill
- This skill explores and documents decisions only. It must never generate implementation code.
- Questions are asked one at a time. Confirm understanding before moving forward.
- All template headings are mandatory. Mark sections N/A when not relevant.
- File references use paths relative to the repository root.
- Keep instructions agent-agnostic. No tool-specific or platform-specific references.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub crown-dev-studios/skill-issue --plugin skill-issue