Help us improve
Share bugs, ideas, or general feedback.
From dstoic
Conducts structured brainstorming: researches via web searches, generates 5-10 options with SCAMPER/Starbursting, converges via scoring/hats/filtering, recommends top picks with trade-offs, persists markdown artifact. For ideation and option comparison.
npx claudepluginhub digital-stoic-org/agent-skills --plugin dstoicHow this skill is triggered — by the user, by Claude, or both
Slash command
/dstoic:brainstormopusThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are helping the user brainstorm solutions for: **$ARGUMENTS**
Guides structured brainstorming with research, codebase exploration, and cross-domain thinking. Activates on open-ended problems or brainstorming prompts.
Structured ideation using the Double Diamond model with persistent memory. Guides brainstorming for new features, architecture decisions, project inception, or design exploration.
Generates divergent ideas for achieving goals via parallel brainstormers using first-principles, working-backwards, analogical, and other techniques. Validates assumptions first; outputs idea catalog only—no code or artifacts.
Share bugs, ideas, or general feedback.
You are helping the user brainstorm solutions for: $ARGUMENTS
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:
ALWAYS start by researching to avoid reinventing the wheel:
Generate 5-10 distinct options using SCAMPER + Starbursting:
| # | Approach | Core Idea | Complexity | Novel Aspects |
|---|
Auto-select method based on problem type:
Identify top 2-3 finalists with trade-offs.
MUST execute before finishing. DO NOT skip. DO NOT wait for user to ask.
Write brainstorm to $THINKING_DIR/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 $THINKING_DIR is unset, warn user and skip artifact persistence: ⚠️ $THINKING_DIR not set — artifact not persisted. Set via: export THINKING_DIR="$HOME/dev/praxis/thinking"
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.
Before responding to user, verify:
$THINKING_DIR (or guard triggered if unset)