xc-brainstorm
Generates diverse solution ideas using parallel agents with different perspectives. Use this whenever the user is exploring solutions for a problem or goal.
What this skill does
# Introduction
## Goal
Generate a high volume of genuinely diverse solution ideas, then organise them into actionable themes.
## Method
Frame the problem as How Might We questions, spawn parallel agents with different diversity primes to generate ideas, then deduplicate and group into strategic themes. Each prime is either context-blind (for divergent thinking) or context-aware (for grounded thinking), decided by the orchestrator based on whether the prime benefits from knowing project reality.
### Success Criteria
- **Volume** — Many ideas per problem area
- **Diversity** — Different approaches, not variations of one
- **Problem-anchored** — Each idea addresses a specific HMW question
- **Actionable** — Concrete enough to evaluate
- **Novelty** — Not just restated existing solutions
## Part 1: Evaluate
- Think about whether this skill actually applies to the current situation. If it doesn't, skip silently and move on.
- If it does, suggest it to the user conversationally. Briefly explain why you think it's relevant. Wait for confirmation before proceeding.
## Part 2: Workflow
### 1. Track progress
- Create a task list so the user can track progress:
- Frame HMW questions and select primes (with context visibility)
- Confirm with user
- Gather context for context-aware primes
- Generate ideas (parallel agents)
- Group ideas into themes
### 2. Frame
- From the user's problem or goal, generate How Might We questions:
- One HMW per problem area (or group related areas)
- Format: "How might we [action] so that [outcome]?"
### 3. Select primes
- Propose 2-4 diversity primes. Genuine diversity comes from different context or lenses:
| Type | Examples |
|------|----------|
| Context-based | No context (naive), full context (strategic) |
| Lens-based | Minimalist, enterprise, developer-focused, end-user-focused |
- For each prime, decide **context visibility**:
- **Context-blind** — primes that derive value from *not knowing* (naive, outsider, cross-domain, minimalist). Ignorance of current reality is the feature.
- **Context-aware** — primes that derive value from *grounding in reality* (developer-focused, pragmatist, strategic, enterprise). Without project context, these primes produce generic ideas indistinguishable from blind ones.
- For each context-aware prime, identify **what context to gather** — relevant files, architecture patterns, existing implementations, constraints, or conventions. Be specific (e.g., "read src/auth/ to understand current auth flow") rather than gathering everything.
### 4. Confirm
- Present HMWs and primes to the user for approval, including context visibility per prime:
- Prime A (context-blind) — why blindness helps this perspective
- Prime B (context-aware: brief description of what context) — why grounding helps this perspective
- Stop and wait for confirmation before proceeding.
### 5. Gather context
- If any primes are context-aware, gather the identified context now — read relevant files, explore relevant parts of the codebase. Use an Explore Agent to do this if necessary.
- Prepare a focused context summary for each context-aware prime. Keep it concise — enough to ground ideation, not so much that it overwhelms the agent's focus.
- Skip this step if all primes are context-blind.
### 6. Generate
- For each prime, spawn an agent (Explore task agent, Haiku). Name each after its prime.
**Context-blind prompt:**
```
You are brainstorming solutions from a {prime} perspective. Do NOT read any files, search any directories, or look for additional context. Work ONLY with what is given below.
HMW QUESTIONS:
{hmw_questions}
Generate 5 solution ideas per HMW question. Be concrete and specific. Think from your assigned perspective — a {prime} thinker would approach this differently from other perspectives.
```
**Context-aware prompt:**
```
You are brainstorming solutions from a {prime} perspective. Do NOT read any files, search any directories, or look for additional context. Work ONLY with what is given below.
PROJECT CONTEXT:
{gathered_context}
HMW QUESTIONS:
{hmw_questions}
Generate 5 solution ideas per HMW question. Be concrete and specific. Think from your assigned perspective — a {prime} thinker would approach this differently from other perspectives. Use the project context to ground your ideas in what actually exists, but don't limit yourself to incremental improvements.
```
- Run all agents in parallel.
### 7. Combine
- Combine all ideas across agents into a single list.
## Final output
- Present the combined idea list to the user.
- Run the **xc-group-ideas** skill to organise the ideas into strategic themes.
## Related skills
- **xc-clarify-framing** — If the problem isn't clear, run xc-clarify-framing first.
- **xc-breakdown-problem** — If the problem is too large, break it down first and brainstorm per sub-part.
- **xc-group-ideas** — Always run after brainstorming to organise ideas into themes.
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.