From space-agents
Engages in interactive idea exploration via multi-round conversations: asks questions, shares opinions, suggests background agents for research/architecture/risks, generates specs.
How this skill is triggered — by the user, by Claude, or both
Slash command
/space-agents:exploration-brainstormThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
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.
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.
TaskOutput block: falseSpawn with run_in_background: true, continue conversation immediately:
space-agents:brainstorm-research - Explore codebase for patterns/constraintsspace-agents:brainstorm-architecture - Propose approaches with trade-offsspace-agents:brainstorm-risk - Identify risks and estimate effortAlways use AskUserQuestion for every question in exploration. Prefer multiple choice when you can anticipate likely answers. Use open-ended only when the answer could be anything.
When exploration reaches clarity, transition to spec creation:
exploration-write-spec skill using the Skill tool
Skill tool with skill: "exploration-write-spec"
exploration/ideas/YYYY-MM-DD-<topic>/spec.md/plan when ready to plan implementationNote: Do NOT create exploration.md directly. The write-spec skill produces a structured spec.md that feeds cleanly into /plan.
npx claudepluginhub thebrownproject/space-agents --plugin space-agentsCreates, edits, and verifies skills using a test-driven development approach with pressure scenarios and subagents.