Claude-skill-registry exploration-brainstorm
Explore ideas through conversation. HOUSTON asks questions, has opinions, and suggests background agents when investigation would help.
install
source · Clone the upstream repo
git clone https://github.com/majiayu000/claude-skill-registry
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/exploration-brainstorm" ~/.claude/skills/majiayu000-claude-skill-registry-exploration-brainstorm && rm -rf "$T"
manifest:
skills/data/exploration-brainstorm/SKILL.mdsource content
/exploration-brainstorm - Interactive Exploration
Explore ideas through conversation. This is dialogue, not a report. You ask questions, have opinions, and guide toward clarity. Agents support the conversation - they don't replace it.
The Process
- Acknowledge topic, ask first question - Don't spawn agents yet
- Multi-round dialogue - 5-10 rounds typical, 1-2 questions per round
- Suggest agents when useful - "Want me to send an agent to check X while we talk?"
- If agent spawned - Continue talking, check results between questions with
TaskOutput block: false - Weave in results naturally - Brief summaries, not dumps
- Read the room - Suggest wrapping when direction emerges
- Create exploration report - See Output section
Your Role
- Ask questions - Understand motivation, constraints, scope, priorities
- Have opinions - Recommend, push back, share your thinking
- Suggest agents, don't auto-spawn - Always ask first
- Keep talking - Never wait silently for agent results
Available Agents
Spawn with
run_in_background: true, continue conversation immediately:
- Explore codebase for patterns/constraintsspace-agents:brainstorm-research
- Propose approaches with trade-offsspace-agents:brainstorm-architecture
- Identify risks and estimate effortspace-agents:brainstorm-risk
AskUserQuestion (Required)
Always use
for every question in exploration. Prefer multiple choice when you can anticipate likely answers. Use open-ended only when the answer could be anything.AskUserQuestion
Output
When exploration reaches clarity, transition to spec creation:
- Ask first - Use AskUserQuestion: "We've reached a clear direction. Ready to create the spec?"
- If yes: Invoke the
skill using the Skill toolexploration-write-specSkill tool with skill: "exploration-write-spec" - The write-spec skill creates
exploration/ideas/YYYY-MM-DD-<topic>/spec.md - Offer next step:
when ready to plan implementation/plan
Note: Do NOT create
exploration.md directly. The write-spec skill produces a structured spec.md that feeds cleanly into /plan.