brainstorm
Facilitate AI-assisted brainstorming sessions for requirements discovery. Uses divergent-convergent thinking patterns to generate ideas, then filters and refines them. Supports multiple brainstorming techniques.
What this skill does
# Brainstorm Command
Facilitate AI-assisted brainstorming sessions for discovering new requirements and ideas.
## Interactive Session Setup
Use AskUserQuestion to configure the brainstorming session:
```yaml
# Question 1: Brainstorming Technique (MCP: divergent thinking methodologies)
question: "What brainstorming technique should we use?"
header: "Technique"
options:
- label: "Freeform (Recommended)"
description: "Classic brainstorm - quantity over quality, build on ideas"
- label: "Reverse Brainstorming"
description: "Think about how to CAUSE the problem, then flip"
- label: "SCAMPER"
description: "Substitute, Combine, Adapt, Modify, Eliminate, Reverse"
- label: "Six Thinking Hats"
description: "Parallel thinking from six perspectives"
# Question 2: Session Scope (MCP: CLI best practices - MVP vs Full)
question: "How comprehensive should the session be?"
header: "Scope"
options:
- label: "Quick Ideation (Recommended)"
description: "1 round, 20-30 ideas, top 5 candidates (~15 min)"
- label: "Standard Session"
description: "2 rounds, 40-50 ideas, grouped themes (~30 min)"
- label: "Deep Exploration"
description: "3+ rounds, all techniques, full refinement (~60 min)"
```
Use these responses to tailor technique selection and session depth.
## Usage
```bash
/requirements-elicitation:brainstorm
/requirements-elicitation:brainstorm --domain "mobile-app"
/requirements-elicitation:brainstorm --domain "checkout" --technique reverse
/requirements-elicitation:brainstorm --domain "onboarding" --technique sixhats --rounds 3
```
## Arguments
| Argument | Required | Description |
|----------|----------|-------------|
| --domain | No | Domain to brainstorm for (default: current/most recent) |
| --technique | No | Brainstorming technique: `freeform`, `reverse`, `starbursting`, `scamper`, `sixhats` (default: `freeform`) |
| --rounds | No | Number of brainstorming rounds (default: 2) |
## Brainstorming Techniques
### Freeform (Default)
Classic brainstorming - generate as many ideas as possible without judgment.
```yaml
freeform:
phase_1_diverge:
goal: "Generate maximum ideas"
rules:
- "No criticism or evaluation"
- "Quantity over quality"
- "Build on others' ideas"
- "Wild ideas welcome"
prompts:
- "What features could help users achieve [goal]?"
- "What would make this 10x better?"
- "What would competitors wish they had?"
- "What would users love but not expect?"
phase_2_converge:
goal: "Filter and group ideas"
actions:
- "Remove duplicates"
- "Group related ideas"
- "Identify themes"
- "Flag most promising"
```
### Reverse Brainstorming
Generate ideas by thinking about how to cause the problem.
```yaml
reverse:
phase_1_reverse:
question: "How could we make [problem] WORSE?"
examples:
- "How could we make checkout MORE confusing?"
- "How could we make search MORE frustrating?"
- "How could we make onboarding SLOWER?"
phase_2_flip:
action: "Reverse each idea to find solutions"
example:
problem: "Make checkout take longer"
flipped: "Add one-click checkout option"
phase_3_refine:
action: "Evaluate flipped ideas as requirements"
```
### Starbursting
Generate questions rather than answers to explore the problem space.
```yaml
starbursting:
question_categories:
who:
- "Who will use this?"
- "Who is affected by this?"
- "Who needs to approve this?"
what:
- "What problem does this solve?"
- "What features are needed?"
- "What could go wrong?"
when:
- "When will users need this?"
- "When should this be available?"
- "When would this fail?"
where:
- "Where will this be used?"
- "Where does this fit in the journey?"
- "Where are the integration points?"
why:
- "Why do users need this?"
- "Why would they choose this?"
- "Why might they resist this?"
how:
- "How will users interact with this?"
- "How will we know it's working?"
- "How will we support this?"
```
### SCAMPER
Systematic creativity technique using seven prompts.
```yaml
scamper:
substitute:
prompt: "What can be substituted?"
examples:
- "Replace password with biometrics"
- "Substitute manual entry with auto-fill"
combine:
prompt: "What can be combined?"
examples:
- "Combine login and preferences setup"
- "Merge checkout and account creation"
adapt:
prompt: "What can be adapted from elsewhere?"
examples:
- "Adapt Netflix's recommendation engine"
- "Adapt Uber's real-time tracking"
modify:
prompt: "What can be modified/magnified/minimized?"
examples:
- "Magnify the confirmation feedback"
- "Minimize the number of form fields"
put_to_other_uses:
prompt: "What else could this be used for?"
examples:
- "Use search for navigation"
- "Use purchase history for recommendations"
eliminate:
prompt: "What can be eliminated?"
examples:
- "Eliminate mandatory registration"
- "Remove unnecessary confirmation steps"
reverse_rearrange:
prompt: "What can be reversed or rearranged?"
examples:
- "Rearrange checkout to show total first"
- "Reverse the sign-up flow"
```
### Six Thinking Hats
Parallel thinking from six perspectives.
```yaml
six_hats:
white_hat:
focus: "Facts and Information"
questions:
- "What data do we have?"
- "What information is missing?"
- "What do we know for certain?"
red_hat:
focus: "Emotions and Intuition"
questions:
- "How do users feel about this?"
- "What's your gut reaction?"
- "What frustrations exist?"
black_hat:
focus: "Critical Judgment"
questions:
- "What could go wrong?"
- "What are the risks?"
- "Why might this fail?"
yellow_hat:
focus: "Optimistic Value"
questions:
- "What are the benefits?"
- "What's the best outcome?"
- "Why will this succeed?"
green_hat:
focus: "Creative Ideas"
questions:
- "What new ideas emerge?"
- "What alternatives exist?"
- "What innovations are possible?"
blue_hat:
focus: "Process and Summary"
questions:
- "What's our conclusion?"
- "What should we do next?"
- "What have we learned?"
```
## Workflow
### Step 1: Setup
```yaml
setup:
1. Load existing requirements from .requirements/{domain}/synthesis/
2. Identify the domain focus area
3. Select brainstorming technique
4. Prepare technique-specific prompts
```
### Step 2: Divergent Phase
```yaml
divergent:
goal: "Generate maximum ideas without judgment"
approach:
- Apply selected technique prompts
- Generate ideas in rapid succession
- Build on and combine ideas
- Capture all ideas without filtering
output: "Raw idea list (30-50+ ideas typical)"
```
### Step 3: Convergent Phase
```yaml
convergent:
goal: "Filter, group, and prioritize ideas"
steps:
1. Remove duplicates and near-duplicates
2. Group related ideas into themes
3. Evaluate feasibility (quick assessment)
4. Rate value/impact potential
5. Select top ideas for refinement
```
### Step 4: Refinement Phase
```yaml
refinement:
goal: "Transform top ideas into requirement candidates"
for_each_selected_idea:
- Expand into requirement statement
- Identify stakeholders affected
- Note dependencies and constraints
- Flag for validation with stakeholders
```
### Step 5: Output Generation
```yaml
output:
brainstorm_session:
domain: "{domain}"
technique: "{technique}"
date: "{ISO-8601}"
rounds: 2
raw_ideas:
total: 47
by_theme:
- theme: "Speed/Performance"
ideas: ["...", "..."]
- theme: "Personalization"
ideas: ["...", "..."]
filtered_ideas:Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.