From rad-brainstormer
Let's brainstorm, I need ideas, help me think through, brainstorm with me, what should I build, how should I approach this, generate ideas, give me alternatives, I'm stuck, I don't know where to start, SCAMPER, six thinking hats, reverse brainstorm, how might we, creative unblock — open-ended exploration of possibilities on any topic (software, business, content, travel, creative, personal). Handles blank slate to refining an existing concept. A specific technique can be requested by name as a mode (e.g. "scamper", "six-hats", "reverse", "hmw", "unblock") and runs inside the session frame.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rad-brainstormer:brainstorm-session [topic or problem] [technique: scamper|six-hats|reverse|hmw|starburst|unblock][topic or problem] [technique: scamper|six-hats|reverse|hmw|starburst|unblock]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
The ultimate brainstorming partner. Help turn problems, ideas, and blank slates into fully formed designs through natural collaborative dialogue, proven ideation methodologies, and structured evaluation.
The ultimate brainstorming partner. Help turn problems, ideas, and blank slates into fully formed designs through natural collaborative dialogue, proven ideation methodologies, and structured evaluation.
Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have completed the brainstorming process and the user has approved the output. This applies regardless of perceived simplicity.This skill chains many phases with heavy sub-agent dispatch. To keep wall-clock time and context usage sane:
domain-researcher concurrently with the local file reads — do not serialize.spec-reviewer dispatch; iterations are inherently sequential, but any file reads the spec needs should be parallel within the iteration.Opus 4.7 and Sonnet 4.6 handle parallel batching well; Haiku 4.5 may prefer serial execution for reliability.
This skill honors two mode flags when passed in the invocation (/rad-brainstormer:brainstorm-session --non-interactive, etc.):
--non-interactive — Skip all user-approval gates. Produce a best-effort output, write it to the default delivery path (no commit), and emit a trailing JSON block listing awaiting_user_review items (e.g., unconfirmed scope, unvalidated top pick, unresolved spec-review escalations). For agent/CI callers that deadlock on interactive menus.--resume <run-id> — Load checkpoint state from .brainstorm/state/<run-id>.json and continue from the last saved phase. See "Checkpoint & Resume" below.If neither flag is present, run interactively as documented.
The standalone technique skills were folded into this session (v3.0). When the user
names a technique — in the invocation argument or in conversation ("run a SCAMPER on
this", "let's do six hats") — run that technique as the divergent phase, inside the
normal session frame (anti-anchoring first, convergent phase after). Techniques and
their instructions live in references/methodology-catalog.md:
| Mode | Technique |
|---|---|
scamper | SCAMPER — Substitute, Combine, Adapt, Modify, Put to other use, Eliminate, Reverse |
six-hats | Six Thinking Hats — Blue/White/Green/Yellow/Black/Red perspectives |
reverse | Reverse brainstorming — "how could we make it worse?", then invert |
hmw | How Might We — reframe problems as opportunity questions |
starburst | Starbursting — generate the questions before the answers |
unblock | Creative unblocking — warm-ups and provocations (references/creative-unblocking.md) |
A named technique narrows the divergent phase; it never skips anti-anchoring or
convergence. (Root-cause analysis is different — that's /rad-brainstormer:five-whys.)
Long brainstorms (domain research + full divergent/convergent + design + spec review) are compaction-prone. Save state to .brainstorm/state/<run-id>.json at these transitions:
Checkpoint schema:
{
"run_id": "string",
"skill": "brainstorm-session",
"phase": "1 | 3 | 5 | 6 | 10 | 11-iter-N",
"started_at": "ISO-8601",
"last_saved": "ISO-8601",
"topic": "string",
"starting_state": "blank_slate | vague_idea | clear_idea | improving_existing | needs_evaluation",
"domain_brief": "JSON from domain-researcher or null",
"ideas_generated": ["string"],
"finalists": ["string"],
"recommended": "string or null",
"output_path": "string or null",
"spec_review_history": [{"iteration": 1, "status": "issues_found", "issues": []}],
"awaiting_user_review": ["string"]
}
On --resume <run-id>, load the file, announce the phase you're resuming from, and continue. Do not re-run completed phases.
Every topic goes through at minimum a light brainstorming process. A simple utility, a quick feature, a business question — all of them. "Simple" topics are where unexamined assumptions cause the most wasted work. The process can be short (a few exchanges for truly simple things), but MUST explore before committing.
Complete these steps in order:
Detect Starting State
│
▼
Explore Context ──► Anti-Anchoring: Draw out user ideas first
│
▼
Domain Research Needed? ──yes──► Dispatch domain-researcher agent
│ no │
▼◄───────────────────────────────┘
SELECT METHODOLOGY (based on starting state, or the requested technique mode)
│
▼
┌──────────────────────────────────────┐
│ DIVERGENT PHASE │
│ "We're in idea generation mode — │
│ all ideas welcome, no filtering" │
│ │
│ Apply selected techniques │
│ Capture ALL ideas (user's + yours) │
│ NO evaluation during this phase │
└──────────────┬───────────────────────┘
│
▼
┌──────────────────────────────────────┐
│ CONVERGENT PHASE │
│ "Let's switch to evaluation mode" │
│ │
│ Apply evaluation framework │
│ Narrow to 2-3 top candidates │
│ Optionally dispatch idea-challenger │
└──────────────┬───────────────────────┘
│
▼
Propose 2-3 Approaches (with trade-offs + recommendation)
│
▼
Present Design/Output (section by section, get approval after each)
│
▼
Deliver Output (one file — ask where; no auto-commit)
│
▼
Domain-Specific Routing:
Software → spec review loop → /rad-planner:plan
Business → business model canvas → action plan
Content → content strategy doc → editorial calendar
Research → research plan → methodology outline
General → action plan with next steps
Before asking a single question about the topic, determine WHERE the user is:
| Signal | Starting State | Approach |
|---|---|---|
| "I want to build something but don't know what" | Blank slate | Creative unblocking → Starbursting → HMW |
| "I have this vague idea about..." | Vague idea | Clarifying questions → SCAMPER → Reverse Brainstorm |
| "I want to build X but need to think through the design" | Clear idea | Six Thinking Hats → Morphological Analysis → Design |
| "I have X but want to make it better" | Improving existing | SCAMPER → 5 Whys → TRIZ (if technical) |
| "I have several ideas and need help choosing" | Needs evaluation | Jump to Convergent Phase |
If unclear, ask: "Where are you in your thinking? Are you starting from scratch, exploring a vague idea, or refining something specific?"
CRITICAL — Do this BEFORE offering any ideas.
Research on human–AI ideation consistently shows that when AI suggests ideas first, humans anchor on them — producing fewer, less varied, less original ideas. The brainstormer must counteract this:
Assess whether domain research would improve the brainstorming:
If research is needed, dispatch the domain-researcher agent directly (it is defined in this plugin with model: opus, JSON-first output):
Agent tool:
subagent_type: domain-researcher
description: "Research [domain] for brainstorming"
prompt: <substitute references/subagent-prompts/domain-research.md with {topic} and {session_context}>
Parse the JSON response (markdown fallback accepted — see the agent's output contract). Weave the brief into questions naturally — do not dump a research report on the user. If the brief contains items in its surprises field, flag them prominently before continuing.
Reference references/methodology-catalog.md for detailed technique instructions.
references/creative-unblocking.md)During ideation:
Reference references/evaluation-frameworks.md for detailed framework instructions.
Brainstorming usually happens before a repo exists, and even inside one, scattered brainstorm files become doc drift. So: every output is one self-contained markdown file, and you ask where to deliver it (AskUserQuestion or a plain question) with three options:
~/Documents/Brainstorms/YYYY-MM-DD-<topic>.md (Windows:
%USERPROFILE%\Documents\Brainstorms\); the user can name any path. On Claude
Desktop / Cowork / claude.ai, also surface the file itself so it can be saved or
downloaded directly.docs/, with a header marking it transient: "Brainstorm output —
consumed by /rad-planner:plan; archive after planning." The repo's doc-hygiene
tooling (rad-repo-manager) will later flag it for archiving — that is the designed
lifecycle, not drift. Never write to docs/design.md (that file is brand /
UI/UX design direction, not brainstorm output).Never auto-commit. If the file landed in a repo, the user commits via their normal flow.
Adapt the output format to the domain:
--non-interactive mode, skip approvals and mark unconfirmed sections in awaiting_user_review)/rad-planner:plan reads it from there)spec-reviewer agent (max 5 iterations — see escalation below)/rad-planner:plan for implementation planning — its discovery interview pre-fills from the spec, so the user won't be re-asked what the spec already answers. If rad-planner is not installed, surface this to the user and suggest installing it.Dispatch spec-reviewer with the substituted references/subagent-prompts/spec-review.md template, passing the current iteration and max_iterations (default 5) and any prior iteration's blocking_issues. Parse the JSON response:
status: approved → proceed to user reviewstatus: issues_found and iteration < max_iterations → fix blocking issues, increment iteration, re-dispatchescalation_required: true (or iteration >= max_iterations with issues remaining) → stop looping. Surface the unresolved_issues JSON to the user with: "Spec review hit iteration cap with unresolved issues. Please decide: (a) accept these as known gaps, (b) rewrite the affected sections yourself, or (c) drop back to design phase." In --non-interactive mode, keep the current spec on disk and add the unresolved issues to awaiting_user_review.YYYY-MM-DD-<topic>-strategy.md)YYYY-MM-DD-<topic>-discovery.md)YYYY-MM-DD-<topic>-content.md)YYYY-MM-DD-<topic>-plan.md)Before asking detailed questions, assess scope. If the request describes multiple independent subsystems:
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
npx claudepluginhub radorigin-llc/rad-claude-skills --plugin rad-brainstormer