aj-geddes/bmad-brainstorm
bmad-planning-orchestrator/skills/bmad-brainstorm/SKILL.md
Facilitates structured ideation sessions using proven brainstorming techniques (SCAMPER, SWOT, 5 Whys, Mind Mapping, Six Thinking Hats, Reverse Brainstorming, Starbursting, Brainwriting). Produces a brainstorming-report.md of organized ideas and actionable insights. Operates in three intents: Create (new session), Update (add techniques or deepen coverage), Validate (confirm insights align with project goals). Use when the user says: "brainstorm", "ideate", "generate ideas", "explore options", "SCAMPER", "SWOT analysis", "mind map", "Six Thinking Hats", "5 Whys", "creative session", "what if we", "let's explore", "think through possibilities", "find alternatives", or "problem-solve". This skill PLANS only — it never writes application code or runs tests.
$ install --global
skillsauthnpx skillsauth add aj-geddes/claude-code-bmad-skills bmad-brainstormInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 20, 2026, 4:06 AM25.1s4 files scanned
SKILL.md
- name:
- bmad-brainstorm
- description:
- |
- and actionable insights. Operates in three intents:
- Create (new session), Update
- Use when the user says:
- brainstorm", "ideate", "generate ideas", "explore options",
- allowed-tools:
- Read, Write, Edit, Bash, Glob, Grep, WebSearch, WebFetch, TodoWrite
BMAD Brainstorm
Structured ideation harness for the BMAD planning lifecycle. Produces a
brainstorming-report.md of organized ideas and insights ready to feed downstream
planning skills (product-brief, PRD, architecture).
Three Intents
Ask the user which intent applies — or infer from context:
| Intent | When to use | |--------|-------------| | Create | New brainstorming session on a topic or problem | | Update | Add techniques, deepen coverage, or incorporate new constraints | | Validate | Confirm generated insights align with project goals or decision-log |
Technique Menu
| Technique | Best For | Approx Time | |-----------|----------|-------------| | 5 Whys | Root cause analysis | 10-15 min | | SCAMPER | Feature ideation & creative variations | 20-30 min | | Mind Mapping | Idea organization & hierarchy | 15-20 min | | Reverse Brainstorming | Risk and failure-mode identification | 15-20 min | | Six Thinking Hats | Multi-perspective evaluation | 30-45 min | | Starbursting | Question exploration (Who/What/When/Where/Why/How) | 20-30 min | | SWOT Analysis | Strategic positioning | 30-45 min | | Brainwriting | Silent parallel idea generation | 15-20 min |
Technique Selection Guide
- Exploring a problem? → 5 Whys, then Starbursting
- Generating features or solutions? → SCAMPER, Mind Mapping
- Assessing risk or failure modes? → Reverse Brainstorming, Six Thinking Hats (Black Hat)
- Strategic planning or positioning? → SWOT, Six Thinking Hats (full cycle)
- Need parallel idea volume? → Brainwriting
Session Workflow
Use TodoWrite to track each step.
- Gather context — Ask: topic/problem, relevant constraints, which BMAD track is active
- Read project context — Load
bmad-output/project-context.mdandbmad-output/decision-log.mdif present - Select techniques — Choose 2-4 complementary techniques; confirm with user
- Execute sessions — Apply each technique systematically (diverge first, do not filter)
- Organize ideas — Categorize all generated ideas; label Impact (H/M/L) and Feasibility (H/M/L)
- Extract insights — Identify top 3-5 actionable insights across all techniques
- Identify risks — Capture risks surfaced during ideation
- Produce report — Fill
templates/brainstorm-session.template.md; save to output folder - Update decision-log — Record key decisions or directions confirmed during the session
- Recommend next steps — Which BMAD skill to engage next
Script Utilities
Generate SCAMPER prompts for a specific topic:
bash "${CLAUDE_PLUGIN_ROOT}/skills/bmad-brainstorm/scripts/scamper-prompts.sh" "your topic"
Generate a SWOT analysis scaffold:
bash "${CLAUDE_PLUGIN_ROOT}/skills/bmad-brainstorm/scripts/swot-template.sh" "your subject" > bmad-output/swot-draft.md
Output Artifacts
All artifacts go under the user-configured output folder (default bmad-output/).
| File | Description |
|------|-------------|
| bmad-output/brainstorming-report.md | Primary output — organized ideas + insights |
| bmad-output/decision-log.md | Append key decisions made during session |
| bmad-output/swot-draft.md | Optional SWOT scaffold (from script) |
Use templates/brainstorm-session.template.md for the report structure.
Subagent Strategy
For sessions covering multiple techniques in parallel, fan out one agent per technique.
Pattern: Fan-Out Ideation
Agents: 2-6 parallel (one per selected technique)
| Agent | Task | Output |
|-------|------|--------|
| Agent 1 | Apply SCAMPER to generate feature variations | bmad-output/brainstorm-scamper.md |
| Agent 2 | Build Mind Map to organize ideas hierarchically | bmad-output/brainstorm-mindmap.md |
| Agent 3 | Reverse Brainstorming — identify failure modes | bmad-output/brainstorm-risks.md |
| Agent 4 | Six Thinking Hats — multi-perspective analysis | bmad-output/brainstorm-hats.md |
| Agent 5 | Starbursting — Who/What/When/Where/Why/How | bmad-output/brainstorm-questions.md |
| Agent 6 | SWOT Analysis — strategic positioning | bmad-output/brainstorm-swot.md |
Coordination:
- Write brainstorming objective to
bmad-output/brainstorm-objective.md - Select 2-6 techniques; launch one agent per technique with context path
- Each agent generates 10-20 ideas/insights using its assigned technique
- Main context synthesizes all outputs into
bmad-output/brainstorming-report.md - Extract top 3-5 actionable insights; append decisions to
bmad-output/decision-log.md
Example subagent prompt:
Task: Apply SCAMPER technique
Context: Read bmad-output/brainstorm-objective.md for topic and constraints
Output: Write 15-20 creative variations to bmad-output/brainstorm-scamper.md
Apply each SCAMPER letter systematically. Generate 2-4 ideas per letter.
For each idea: one-sentence description, potential value, innovation level
(incremental / breakthrough). Conclude with your top 3 most promising ideas.
Do not implement anything — ideation output only.
BMAD Fidelity Notes
- This skill feeds Phase 1 (Analysis) and Phase 2 (Planning). Insights flow into the product-brief and PRD skills.
- Insights that become commitments must be logged in
bmad-output/decision-log.md. - This skill does not produce stories. It produces raw insight material that upstream skills (product-manager, system-architect) refine into epics and stories.
- Scale-adaptive tracks apply: Quick Flow sessions may use 1-2 techniques; Enterprise sessions should apply 4-6 for comprehensive coverage.
Guiding Principles
- Diverge before converging — generate volume first; filter later
- Structured over freeform — every technique has a defined process; follow it
- Document everything — capture all ideas; even "bad" ones can spark breakthroughs
- Quantify insights — numbers make insights actionable (market size, feature counts)
- Cross-pollinate — consider how other industries or domains solve the same problem
- No implementation — this skill plans; it never writes code or runs tests
Part of the BMAD Planning & Orchestrator plugin — a Claude Code harness for the BMAD Method by the BMAD Code Organization (https://github.com/bmad-code-org/BMAD-METHOD). Implements the spirit of
bmad-brainstorming. All methodology credit belongs to the BMAD Code Organization.
Related Skills
aj-geddes/bmad-ux
testing
VerifiedTrustedCommunity
Solutioning-phase UX planning skill (optional; activate when the project has a UI). Produces TWO planning documents: DESIGN.md (the visual system — design tokens, color palette, typography, spacing, component specs, WCAG 2.1 AA contract) and EXPERIENCE.md (user journeys, flow diagrams, screen states, error/empty/loading handling). Use when the user says "design the UX", "create UX planning docs", "define the design system", "map the user flows", "UX for this feature", "wireframe the flows", "what are the user journeys", "accessibility design", "WCAG compliance", "design tokens", "responsive design plan", "mobile-first design", or "create DESIGN.md / EXPERIENCE.md". Runs after architecture is drafted and before stories are created. Supports Create / Update / Validate intents.
451SKILL.mdUpdated Jun 20, 2026
aj-geddes/bmad-tech-spec
testing
VerifiedTrustedCommunity
Quick Flow lightweight technical specification for small-scope work (1-15 stories). Replaces the full PRD + architecture pair when scope is small and requirements are clear. Produces bmad-output/tech-spec.md as the single planning artifact before story creation. Use when the user says: "write a tech spec", "create a technical specification", "I need a tech spec for this feature", "quick spec", "small project spec", "we don't need a full PRD", "just a tech spec", "spec out this change", "document this feature". QUICK FLOW TRACK ONLY (1-15 stories). If scope grows beyond ~15 stories or involves multiple teams / external integrations at scale, stop and redirect to bmad-prd + bmad-architecture instead — those skills are built for that complexity. Supports three intents: Create (new spec), Update (revise an existing tech-spec.md), Validate (review a draft for completeness against BMAD criteria).
451SKILL.mdUpdated Jun 20, 2026
aj-geddes/bmad-sprint-planning
tools
VerifiedTrustedCommunity
Orchestration handoff bridge: emits and maintains sprint-status.yaml as the project's sequencing system-of-record. Orders stories by epic then dependency, assigns parallel-set (wave) membership, and drives the status lifecycle (backlog → ready-for-dev → in-progress → review → done) as a view — never as a metric. Use when the user says "sequence the stories", "build the sprint status", "plan the waves", "create sprint-status.yaml", "assign parallel sets", "order stories by dependency", "what can run in parallel", "set up story sequencing", "initialize sprint tracking", "ready the backlog", or "prepare for dev handoff". Also triggers on "sprint planning" when the project already has epics defined. SCOPE: SEQUENCING AND ORCHESTRATION ONLY. No velocity, no burndown, no committed points, no coverage metrics. Capacity is expressed as wave width (concurrent story count), not points. The final artifact is a ready-for-dev handoff manifest; implementation is delegated to external dev tools.
451SKILL.mdUpdated Jun 20, 2026
aj-geddes/bmad-spec
development
VerifiedTrustedCommunity
Distills ANY messy input — brain dump, transcript, long PRD, stakeholder notes, feature request, voice memo — into a tight five-field SPEC.md kernel that any downstream planning skill can consume. The five fields are: Problem, Capabilities, Constraints, Non-Goals, Success Metrics. Use when the user says "create a spec", "write a spec for", "distill this into a spec", "I have a brain dump", "turn this into something structured", "clean up these notes", "make a SPEC from", "I want to define the problem", "help me scope this", "summarize what we're building", "I have a PRD but need a kernel", "what are we actually solving?", or drops raw text/transcript and asks for structure. Also use when starting any new initiative and a clean shared definition is missing.
451SKILL.mdUpdated Jun 20, 2026