brainstorming
Collaborative design exploration for new features and architecture decisions. Triggers: 'brainstorm', 'ideate', 'explore options', or /ideate. Presents 2-3 approaches with trade-offs, documents chosen approach. Do NOT use for implementation planning or code review. Requires no existing design document — use /plan if one exists.
What this skill does
# Brainstorming Skill
## Overview
Collaborative design exploration for new features, architecture decisions, and complex problem-solving.
## Triggers
Activate this skill when:
- User says "let's brainstorm", "let's ideate", or "let's explore"
- User runs `/exarchos:ideate` command
- User wants to discuss design options before implementation
- A problem has multiple valid solutions needing evaluation
For a complete worked example, see `references/worked-example.md`.
## Four-Phase Process
### Phase 0: Constraint anchoring (first turn, before Phase 1)
**Goal:** Surface the architectural invariants relevant to the proposal *before* the clarifying questions, so the design is anchored to load-bearing constraints from the first turn.
Load the **core** invariants catalog at `.exarchos/invariants.md` (entries marked `cost-of-load: always-load`) and surface a **Constraints** section naming the relevant invariants — e.g. a CLI / agent-first surface proposal anchors on `INV-5a` (input ergonomics) and `INV-5c` (Aspire verbs). The full selection rules — `always-load` baseline vs `reference-only` on-demand vs `archivable` not-surfaced, the proposal-shape → anchor-invariant table, the emit format, and the `invariants.devCatalog` gating — are the **single shared source of truth** for the design-time Constraints step used by `/ideate`, `/refactor`, and `/debug`. See `@skills/brainstorming/references/constraint-anchoring.md`.
Emit the **Constraints** section (per that reference) *before* Phase 1 so the clarifying questions can probe the proposal against the load-bearing invariants instead of re-discovering them mid-design.
### Phase 1: Understanding
**Goal:** Deeply understand the problem before proposing solutions.
**Rules:**
- Ask ONE question at a time
- Wait for response before asking next question
- Focus on: goals, constraints, existing patterns, user preferences
- Maximum 5 questions before moving to exploration
**Question Types:**
1. "What problem are we solving?" (core need)
2. "What constraints exist?" (time, tech, compatibility)
3. "What patterns already exist in the codebase?" (consistency)
4. "Who/what will consume this?" (users, APIs, other systems)
5. "What does success look like?" (acceptance criteria)
### Phase 2: Exploration
**Goal:** Present 2-3 distinct approaches with trade-offs.
Use the approach format from `references/design-template.md`. Present genuinely different approaches with honest trade-offs. Recommend one option with rationale.
### Phase 3: Design Presentation
**Goal:** Document the chosen approach in detail with numbered requirements.
Document the chosen approach using the structure in `references/design-template.md`. Sections of 200-300 words max. Use diagrams for complex flows.
**Requirements format (MANDATORY):**
- Use numbered requirement identifiers: `DR-1`, `DR-2`, ..., `DR-N`
- Each requirement MUST have an `**Acceptance criteria:**` block with concrete, testable criteria
- At least one requirement MUST address error handling, failure modes, or edge cases
- These DR-N identifiers are provenance anchors — implementation plans trace tasks to them
**Save Location:** `docs/designs/YYYY-MM-DD-<feature>.md`
## Iteration Limits
**Design iterations: max 3.** If Phase 2 (Exploration) cycles through 3 rounds of presenting approaches without the user converging on a choice, pause and summarize the trade-offs for the user to make a final decision.
The user can override: `/exarchos:ideate --max-iterations 5`
## Anti-Patterns
| Don't | Do Instead |
|-------|------------|
| Jump to solution immediately | Ask clarifying questions first |
| Present only one option | Always show 2-3 alternatives |
| Hide drawbacks of preferred option | Be transparent about trade-offs |
| Write walls of text | Use 200-300 word sections max |
| Ignore existing patterns | Reference codebase conventions |
| Skip documentation | Save design to docs/designs/ |
## State Management
This skill manages workflow state for context persistence.
### On Start (before Phase 1)
Initialize workflow state using `mcp__plugin_exarchos_exarchos__exarchos_workflow` with `action: "init"`, `workflowType: "feature"`, and the featureId.
This creates a state file tracked by the MCP server.
### On Design Save (after Phase 3)
```
action: "update", featureId: "<id>", updates: { "artifacts": { "design": "<path>" } }, phase: "plan"
```
### Phase Transitions and Guards
This skill is the entry point for the **feature workflow** (`workflowType: "feature"`). The full lifecycle is:
```
ideate → plan → plan-review → delegate ⇄ review → synthesize → completed
```
For the full transition table, consult `@skills/workflow-state/references/phase-transitions.md`.
### Schema Discovery
Use `exarchos_workflow({ action: "describe", actions: ["update", "init"] })` for
parameter schemas and `exarchos_workflow({ action: "describe", playbook: "feature" })`
for phase transitions, guards, and playbook guidance.
## Completion Verification
Run the ideation artifact verification:
```typescript
mcp__plugin_exarchos_exarchos__exarchos_orchestrate({
action: "check_design_completeness",
featureId: "<featureId>",
designPath: "docs/designs/YYYY-MM-DD-<feature>.md"
})
```
**On `passed: true`:** All completion criteria met — proceed to gate check.
**On `passed: false`:** Missing artifacts — review output and complete before continuing. If the check is advisory (`advisory: true`), emit a warning but do not block auto-chain.
## Adversarial Gate Check (ideate → plan)
After artifact verification passes, run the design completeness gate check. This is the D1 (spec fidelity) lightweight adversarial check at the ideate → plan boundary.
```typescript
mcp__plugin_exarchos_exarchos__exarchos_orchestrate({
action: "check_design_completeness",
featureId: "<id>",
designPath: "<path>"
})
```
The handler returns a structured result: `{ passed, advisory, findings[], checkCount, passCount, failCount }`.
- **`passed=true`:** Design complete — all requirements have acceptance criteria and error coverage.
- **`passed=false, advisory=true`:** Findings detected. These are advisory — they do NOT block the auto-chain to `/exarchos:plan`. Present `result.data.findings` to the user alongside the transition message.
Gate events (`gate.executed`) are emitted automatically by the handler — no manual event emission is needed.
## Transition
After brainstorming completes, **auto-continue to planning** (no user confirmation):
### Pre-Chain Validation (MANDATORY)
Before invoking `/exarchos:plan`:
1. Verify `artifacts.design` exists in workflow state
2. Verify the design file exists on disk: `test -f "$DESIGN_PATH"`
3. Run `mcp__plugin_exarchos_exarchos__exarchos_orchestrate({ action: "check_design_completeness", featureId: "<id>", designPath: "<path>" })` (advisory — record findings but don't block)
4. If steps 1 or 2 fail: "Design artifact not found, cannot auto-chain to /exarchos:plan"
### Chain Steps
1. Update state: `action: "update", featureId: "<id>", updates: { "artifacts": { "design": "<path>" } }, phase: "plan"`
2. If `result.data.passed === false` and `result.data.advisory === true`: Output `result.data.findings` summary, then: "Advisory findings noted. Auto-continuing to implementation planning..."
If `result.data.passed === true`: Output: "Design complete. Auto-continuing to implementation planning..."
3. Invoke immediately:
```typescript
Skill({ skill: "exarchos:plan", args: "<design-path>" })
```
This is NOT a human checkpoint. The human checkpoint occurs at plan-review (plan approval) and synthesize (merge confirmation).
**Workflow continues:** `/exarchos:ideate` -> `/exarchos:plan` -> plan-review -> [HUMAN CHECKPOINT] -> `/exarchos:delegate` -> `/exarchos:review` -> `/exarchos:synthesize` -> [HUMAN CHECKPOINT]
## Exarchos Integration
When Exarchos MCP tools are available:
1. **At workflow start:** Auto-emitted by `exarchos_workflow` `action: "init"` — do NOTRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.