Interactive exploration of ideas through Socratic Q&A. Produces progressive documents that serve as lightweight pre-PRDs feeding into research.
From despleganpx claudepluginhub desplega-ai/ai-toolbox --plugin desplegaThis skill uses the workspace's default tool permissions.
template.mdSearches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Guides agent creation for Claude Code plugins with file templates, frontmatter specs (name, description, model), triggering examples, system prompts, and best practices.
You are facilitating interactive exploration of ideas through Socratic Q&A. The goal is understanding before implementation — documents grow progressively during the session and end as lightweight pre-PRDs that feed into /research or /create-plan.
These instructions establish a working agreement between you and the user. The key principles are:
AskUserQuestion is your primary communication tool - Whenever you need to ask the user anything, use the AskUserQuestion tool. Don't output questions as plain text - always use the structured tool so the user can respond efficiently.
Establish preferences upfront - Ask about user preferences at the start of the workflow, not at the end when they may want to move on.
Autonomy mode guides interaction level - The user's chosen autonomy level determines how often you check in, but AskUserQuestion remains the mechanism for all questions.
Before starting brainstorming, establish these preferences:
File Review Preference - Check if the file-review plugin is available (look for file-review:file-review in available commands).
If file-review plugin is installed, use AskUserQuestion with:
| Question | Options |
|---|---|
| "Would you like to use file-review for inline feedback on the brainstorm document after synthesis?" | 1. Yes, open file-review when synthesis is ready (Recommended), 2. No, just show me the document |
Store this preference and act on it after synthesis (see "Review Integration" section).
This skill activates when:
/brainstorm command**REQUIRED SUB-SKILL:** Use desplega:brainstormingBrainstorming is inherently interactive, so only two modes are supported:
| Mode | Behavior |
|---|---|
| Verbose (Default) | Full Socratic exploration, ask one question at a time, rich discussion |
| Critical | Fewer questions, focus on the most impactful areas, reach synthesis faster |
Autopilot is not supported — brainstorming requires human input by design. If Autopilot is requested, fall back to Critical with a note explaining why.
The autonomy mode is passed by the invoking command. If not specified, default to Verbose.
Create thoughts/<username|shared>/brainstorms/YYYY-MM-DD-<topic>.md using the template at cc-plugin/base/skills/brainstorming/template.md.
Path selection: Use the user's name (e.g., thoughts/taras/brainstorms/) if known from context. Fall back to thoughts/shared/brainstorms/ when unclear.
Fill in the frontmatter and the Context section with whatever is known: the topic, any context provided, initial thoughts. Write what we know so far.
OPTIONAL SUB-SKILL: If ~/.agentic-learnings.json exists, run /learning recall <current topic> to check for relevant prior learnings before proceeding.
Understand the shape of the exploration. Use AskUserQuestion with:
| Question | Options |
|---|---|
| "What kind of exploration is this?" | 1. Problem to solve, 2. Idea to develop, 3. Comparison to make, 4. Workflow to improve, 5. Other (describe) |
Update the document's exploration_type frontmatter and Context section with the exploration framing.
Socratic Q&A loop. The goal is to systematically uncover requirements, constraints, and insights.
Rules:
## Exploration:
### Q: [Your question]
[User's answer]
**Insights:** [Any observations, implications, or connections you noticed]
Question strategy:
CRITICAL: Resist premature solutions during the Explore phase. The goal is understanding, not implementation. If the user starts solutioning too early:
/create-planWhen exploration is complete (user signals done, or natural saturation), append a ## Synthesis section:
## Synthesis
### Key Decisions
- [Decision 1]
- [Decision 2]
### Open Questions
- [Question that still needs investigation]
### Constraints Identified
- [Constraint 1]
- [Constraint 2]
### Core Requirements
- [Requirement 1 — lightweight PRD-style]
- [Requirement 2]
OPTIONAL SUB-SKILL: If significant insights, patterns, gotchas, or decisions emerged during this workflow, consider using desplega:learning to capture them via /learning capture. Focus on learnings that would help someone else in a future session.
Before handoff, offer to run /review on the brainstorm document to identify unexplored areas.
Then use AskUserQuestion with:
| Question | Options |
|---|---|
| "What's the next step?" | 1. Start research based on this brainstorm (→ /research), 2. Create a plan directly (→ /create-plan), 3. Done for now (park the brainstorm) |
Based on the answer:
/research command with the brainstorm file as input context/create-plan command with the brainstorm file as input contextstatus to parked or complete as appropriateThe brainstorm document is a living artifact during the session. It starts rough and gains structure through the Q&A process. By the end, it should be readable as a standalone context document that someone else could pick up and understand.
If the file-review plugin is available and the user selected "Yes" during User Preferences setup:
/file-review:file-review <path> for inline human commentsfile-review:process-review skill