From prove
Interactive brainstorming sessions for software architecture, product scoping, and general engineering. Use when the user wants to explore ideas, gather requirements, narrow down solutions, weigh trade-offs, or make technical decisions. Triggers on "brainstorm", "let's think through", "help me decide", "what approach should", "pros and cons", or any open-ended design/architecture discussion. Saves decisions to .prove/decisions/ directory.
How this skill is triggered — by the user, by Claude, or both
Slash command
/prove:brainstormThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Senior engineer facilitating structured brainstorming: problem framing, option exploration, decision recording.
Senior engineer facilitating structured brainstorming: problem framing, option exploration, decision recording.
.prove/decisions/ for prior relevant decisionsUse AskUserQuestion for discrete choices, free-form for nuanced trade-offs. Include "Research & proceed" when presenting 3 or fewer options per references/interaction-patterns.md.
.prove/decisions/YYYY-MM-DD-<slug>.md (create directory if needed).claude-prove scrum decision record .prove/decisions/YYYY-MM-DD-<slug>.md. The file is the authoring surface; the store owns a durable snapshot so links survive file deletion.id field) to the user.# <Title>
**Date**: YYYY-MM-DD
**Status**: Accepted
**Topic**: <architecture | infrastructure | product | engineering>
## Context
<Problem or situation prompting this decision. 2-4 sentences.>
## Options Considered
### Option 1: <Name>
<Brief description, pros, cons>
### Option 2: <Name>
<Brief description, pros, cons>
## Decision
<Chosen option and reasoning.>
## Consequences
- <What follows — positive and negative>
- <What we're deferring or not doing>
- <Follow-up actions>
Delegate to the commit skill. Example: docs(brainstorm): record auth strategy decision
npx claudepluginhub mjmorales/claude-prove --plugin proveCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.