How do I install the Brainstorm skill?

Run npx skillmds@latest add digital-stoic-org/brainstorm in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Brainstorm safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Brainstorm?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Brainstorm free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Brainstorm?

digital-stoic-org (@digital-stoic-org) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Brainstorm by digital-stoic-org — Agent Skill

Name: Brainstorm
Rating: 4.2 (5 reviews)
Author: digital-stoic-org

Brainstorm

Divergent-convergent brainstorming with research, ideation, and trade-off analysis. Use when exploring options, generating ideas, comparing approaches. Triggers include "brainstorm", "explore options", "ideate", "compare approaches".

File contents

Brainstorming Protocol

You are helping the user brainstorm solutions for: $ARGUMENTS

⚠️ AskUserQuestion Guard

CRITICAL: After EVERY AskUserQuestion call, check if answers are empty/blank. Known Claude Code bug: outside Plan Mode, AskUserQuestion silently returns empty answers without showing UI.

If answers are empty: DO NOT proceed with assumptions. Instead:

Output: "⚠️ Questions didn't display (known Claude Code bug outside Plan Mode)."
Present the options as a numbered text list and ask user to reply with their choice number.
WAIT for user reply before continuing.

Phase 1: Research First 🔍

ALWAYS start by researching to avoid reinventing the wheel:

Generate 2-3 focused web searches (existing solutions, best practices, real-world examples)
Synthesize findings into key insights
Note what already exists vs. what's missing

Phase 2: Divergent Thinking 💡

Generate 5-10 distinct options using SCAMPER + Starbursting:

#	Approach	Core Idea	Complexity	Novel Aspects

Phase 3: Convergent Thinking 🎯

Auto-select method based on problem type:

Technical/architectural: Weighted Scoring
Product/feature: Six Thinking Hats
Tooling/workflow: Constraint-Based filtering

Identify top 2-3 finalists with trade-offs.

Phase 4: Recommendation ✅

Recommend best option with reasoning
Flag assumptions to validate
Auto-detect boulder vs. pebble → suggest OpenSpec or direct implementation

Phase 5: Persist Thinking Artifact ⚠️ MANDATORY

MUST execute before finishing. DO NOT skip. DO NOT wait for user to ask.

Write brainstorm to $PRAXIS_DIR/thinking/brainstorms/{project}/{date}-{slug}-llm.md.

{project} = current project folder name (e.g., agent-skills, gtd-pcm). {slug} = lowercase hyphenated from brainstorm topic. Create directory if missing.

Collision handling: If filename exists, append sequence: {date}-{slug}-2-llm.md, {date}-{slug}-3-llm.md. First write gets clean name.

Guard: If $PRAXIS_DIR is unset, warn user and skip artifact persistence: ⚠️ $PRAXIS_DIR not set — artifact not persisted. Set via: export PRAXIS_DIR="$HOME/dev/praxis"

Content: problem/topic + research findings + options generated (SCAMPER) + convergence analysis + recommendation + assumptions to validate.

See reference.md for SCAMPER details, Starbursting dimensions, and convergence frameworks.

✅ Completion Checklist

Before responding to user, verify:

Artifact written to $PRAXIS_DIR/thinking (or guard triggered if unset)

---name: brainstormdescription: Divergent-convergent brainstorming with research, ideation, and trade-off analysis. Use when exploring options, generating ideas, comparing approaches. Triggers include "brainstorm", "explore options", "ideate", "compare approaches".---# Brainstorming ProtocolYou are helping the user brainstorm solutions for: **$ARGUMENTS**## ⚠️ AskUserQuestion Guard**CRITICAL**: After EVERY `AskUserQuestion` call, check if answers are empty/blank. Known Claude Code bug: outside Plan Mode, AskUserQuestion silently returns empty answers without showing UI.**If answers are empty**: DO NOT proceed with assumptions. Instead:1. Output: "⚠️ Questions didn't display (known Claude Code bug outside Plan Mode)."2. Present the options as a **numbered text list** and ask user to reply with their choice number.3. WAIT for user reply before continuing.## Phase 1: Research First 🔍**ALWAYS start by researching** to avoid reinventing the wheel:1. Generate 2-3 focused web searches (existing solutions, best practices, real-world examples)2. Synthesize findings into key insights3. Note what already exists vs. what's missing## Phase 2: Divergent Thinking 💡Generate **5-10 distinct options** using SCAMPER + Starbursting:| # | Approach | Core Idea | Complexity | Novel Aspects ||---|----------|-----------|------------|---------------|## Phase 3: Convergent Thinking 🎯**Auto-select method** based on problem type:- **Technical/architectural**: Weighted Scoring- **Product/feature**: Six Thinking Hats- **Tooling/workflow**: Constraint-Based filteringIdentify top 2-3 finalists with trade-offs.## Phase 4: Recommendation ✅1. Recommend best option with reasoning2. Flag assumptions to validate3. Auto-detect boulder vs. pebble → suggest OpenSpec or direct implementation## Phase 5: Persist Thinking Artifact ⚠️ MANDATORY**MUST execute before finishing. DO NOT skip. DO NOT wait for user to ask.**Write brainstorm to `$PRAXIS_DIR/thinking/brainstorms/{project}/{date}-{slug}-llm.md`.`{project}` = current project folder name (e.g., `agent-skills`, `gtd-pcm`). `{slug}` = lowercase hyphenated from brainstorm topic. Create directory if missing.**Collision handling**: If filename exists, append sequence: `{date}-{slug}-2-llm.md`, `{date}-{slug}-3-llm.md`. First write gets clean name.**Guard**: If `$PRAXIS_DIR` is unset, warn user and skip artifact persistence: `⚠️ $PRAXIS_DIR not set — artifact not persisted. Set via: export PRAXIS_DIR="$HOME/dev/praxis"`Content: problem/topic + research findings + options generated (SCAMPER) + convergence analysis + recommendation + assumptions to validate.See `reference.md` for SCAMPER details, Starbursting dimensions, and convergence frameworks.## ✅ Completion ChecklistBefore responding to user, verify:- [ ] Artifact written to `$PRAXIS_DIR/thinking` (or guard triggered if unset)

Frequently asked questions