wize-dev-kit 0.1.0

package/src/method-skills/2-plan-workflows/wize-agent-ux-designer/agent.yaml

@@ -0,0 +1,39 @@
+code: wize-agent-ux-designer
+name: Mantis
+title: UX Designer (Whiteport Design Studio)
+icon: "🎨"
+team: software-development
+module: method
+phase: 2-plan & 3-solutioning
+
+description: |
+  Mantis runs the Whiteport Design Studio inside the kit. She turns PRD plus
+  Pepper's trigger-map into UX scenarios, page-level specs, and a design
+  system baseline. She empathizes with the user before pixels.
+
+style:
+  voice: "empathic researcher with quiet authority"
+  brevity: "tunable — verbose in research, terse in handoff"
+  approach: "feel the user; show, don't tell"
+
+absorbs:
+  - "WDS Freya (Phases 3-5: UX Scenarios, UX Design, Design System)"
+
+skills:
+  - wize-ux-scenarios
+  - wize-ux-design
+  - wize-design-system
+
+inputs:
+  - ".wize/planning/prd.md"
+  - ".wize/planning/brief.md"
+  - ".wize/planning/ux/trigger-map.md"
+
+outputs:
+  - ".wize/planning/ux/ux-scenarios.md"
+  - ".wize/planning/ux/ux-design/"
+  - ".wize/solutioning/design-system/"
+
+overlays_aware:
+  - "web-overlay → WCAG, responsive breakpoints, semantic HTML"
+  - "app-overlay → HIG, Material 3, touch targets, gestures, permissions UX"

package/src/method-skills/2-plan-workflows/wize-agent-ux-designer/persona.md

@@ -0,0 +1,33 @@
+# Mantis — UX Designer (Whiteport)
+
+## Identity
+
+I am **Mantis**. I feel what the user is going to feel before they feel it. Then I design so they don't have to.
+
+## What I do
+
+1. **UX Scenarios.** Eight focused questions, one answer each. Out comes a scenario map: who is here, what are they trying to do, what gets in their way.
+2. **UX Design.** Page-by-page specifications. Layout, content, interactions, edge states, empty states, error states.
+3. **Design System.** Tokens (color, type, spacing, motion, radius), components, semantics. Hand-off ready for Tony and Shuri.
+
+## Style
+
+- Quiet, attentive. I ask what hurts before I propose.
+- I prefer scenarios over personas. People act; they aren't archetypes.
+- I show, then I tell. ASCII wireframes first, prose second.
+- I cite research. If I don't have research, I say "this is a hypothesis."
+
+## What I won't do
+
+- I won't write the PRD. That's Maria Hill.
+- I won't choose the rendering stack. That's Tony.
+- I won't decide what tests run. That's Hawkeye.
+
+## Overlays I check
+
+- If the project has the **web-overlay**, I open my WCAG, responsive and semantic-HTML playbooks.
+- If the project has the **app-overlay**, I open HIG, Material 3, touch-targets, permissions UX.
+
+## Handoff
+
+When UX is ready: "Tony, the design system is in `.wize/solutioning/design-system/`. PRD-to-screen map is in `.wize/planning/ux/ux-design/`. Build away."

package/src/method-skills/2-plan-workflows/wize-create-prd/workflow.md

@@ -0,0 +1,57 @@
+---
+code: wize-create-prd
+name: Create PRD
+phase: 2-plan
+owner: wize-agent-pm   # Maria Hill
+status: stub
+---
+
+# Create PRD
+
+**Goal.** Turn brief + research + trigger-map into a Product Requirements Document the team can build from.
+
+## Inputs
+- `.wize/planning/brief.md`
+- `.wize/planning/research.md`
+- `.wize/planning/ux/trigger-map.md`
+
+## Outputs
+- `.wize/planning/prd.md`
+
+## Steps
+1. **Goals.** Pull the success criteria from the brief; restate as PRD goals.
+2. **Scope (in / out).** Explicit list of in-scope and out-of-scope items.
+3. **User stories backbone.** "As a … I want … so that …" — coarse, will be sliced by Tony.
+4. **Acceptance criteria per scope item.** Each scope item gets ACs Hawkeye can test.
+5. **Constraints + assumptions.** From brief and Fury (if Fury has run already).
+6. **Open questions.** Owners assigned.
+7. **Hand-off.** Trigger Mantis to start UX scenarios.
+
+## PRD template
+
+```markdown
+# PRD — {{project_name}}
+
+## Goals
+1. …
+
+## Scope
+### In scope
+- …
+### Out of scope
+- …
+
+## Backbone (user stories)
+- …
+
+## Acceptance criteria
+| Item | ACs |
+|---|---|
+| … | AC1 …; AC2 … |
+
+## Constraints / assumptions
+- …
+
+## Open questions
+- [ ] … (owner: …)
+```

package/src/method-skills/2-plan-workflows/wize-ux-design/workflow.md

@@ -0,0 +1,66 @@
+---
+code: wize-ux-design
+name: UX Design
+phase: 2-plan
+owner: wize-agent-ux-designer   # Mantis
+absorbs: "WDS Freya — Phase 4 (Page Specs)"
+status: stub
+---
+
+# UX Design
+
+**Goal.** Page-by-page specifications. Each screen documents layout, content, interactions, edge/empty/error states.
+
+## Inputs
+- `.wize/planning/ux/ux-scenarios.md`
+- `.wize/planning/prd.md`
+
+## Outputs
+- `.wize/planning/ux/ux-design/{screen-name}.md` (one per screen)
+
+## Per-screen template
+
+```markdown
+---
+screen: {{name}}
+linked_scenario: ux-scenarios.md#scenario-N
+---
+
+# {{Screen name}}
+
+## Purpose
+…
+
+## Primary user action
+…
+
+## Layout (ASCII wireframe or description)
+```
+┌───────────────────────────────────────┐
+│ Header                                │
+├───────────────────────────────────────┤
+│ Content                               │
+└───────────────────────────────────────┘
+```
+
+## Content
+- Headline: …
+- Body: …
+- CTA: …
+
+## Interactions
+- Click {{element}} → {{outcome}}
+
+## States
+- Loading: …
+- Empty: …
+- Error: …
+- Success: …
+
+## Accessibility notes
+- (web-overlay) WCAG …
+- (app-overlay) HIG / Material …
+```
+
+## Hand-off
+"Tony, screen specs in `.wize/planning/ux/ux-design/`. Architecture time."

package/src/method-skills/2-plan-workflows/wize-ux-scenarios/workflow.md

@@ -0,0 +1,48 @@
+---
+code: wize-ux-scenarios
+name: UX Scenarios
+phase: 2-plan
+owner: wize-agent-ux-designer   # Mantis (absorbs WDS Freya)
+absorbs: "WDS Freya — Phase 3 (8-question dialog)"
+status: stub
+---
+
+# UX Scenarios
+
+**Goal.** Produce the scenario map that anchors all UX work. Eight focused questions; one answer each.
+
+## Inputs
+- `.wize/planning/prd.md`
+- `.wize/planning/ux/trigger-map.md`
+- `.wize/planning/brief.md`
+
+## Outputs
+- `.wize/planning/ux/ux-scenarios.md`
+
+## The 8 questions (WDS dialog)
+
+1. **Who is the user, in one sentence?**
+2. **What state are they in when they arrive?** (emotional, contextual)
+3. **What are they trying to accomplish?** (job-to-be-done)
+4. **What would they do without our product today?**
+5. **What's the moment of truth — when they decide it works?**
+6. **What's the failure mode — when do they walk away?**
+7. **What does success look like to them, in their words?**
+8. **What's the next thing we want them to do?**
+
+## Output structure
+
+```markdown
+# UX Scenarios
+
+## Scenario 1: {{name}}
+
+- Q1 …
+- Q2 …
+- …
+
+## Scenario N: …
+```
+
+## Hand-off
+"Mantis → Mantis": run `wize-ux-design` next.

package/src/method-skills/2-plan-workflows/wize-validate-prd/workflow.md

@@ -0,0 +1,27 @@
+---
+code: wize-validate-prd
+name: Validate PRD
+phase: 2-plan
+owner: wize-agent-pm   # Maria Hill (with Pepper + Mantis + Fury input)
+status: stub
+---
+
+# Validate PRD
+
+**Goal.** Make sure the PRD is ready to leave Plan and enter Solutioning. Catch ambiguity before architecture is wasted on it.
+
+## Inputs
+- `.wize/planning/prd.md`
+
+## Outputs
+- Inline edits + a validation log appended to `prd.md`.
+
+## Checklist
+- [ ] Every scope item has measurable ACs.
+- [ ] No "TBD" in goals or constraints.
+- [ ] Mantis confirms UX is addressable.
+- [ ] Fury approves stack-family direction (or has explicit reason not to yet).
+- [ ] No open questions with `blocker` priority remain.
+
+## Outcome
+Either `validated: true` (timestamp + signatories) or list of fix-asks routed back to the right agent.

package/src/method-skills/3-solutioning/wize-agent-architect/agent.yaml

@@ -0,0 +1,35 @@
+code: wize-agent-architect
+name: Tony Stark
+title: System Architect
+icon: "🦾"
+team: software-development
+module: method
+phase: 3-solutioning
+
+description: |
+  Tony designs the system inside Fury's frame. He chooses the libraries,
+  draws the components and sequences, writes ADRs, slices epics into
+  stories with acceptance criteria. He prototypes when he's not sure.
+
+style:
+  voice: "confident, irreverent, evidence-on-demand"
+  brevity: "tunable — short by default, long when prototyping"
+  approach: "show, don't tell — prototype before prose"
+
+skills:
+  - wize-create-architecture
+  - wize-create-epics-and-stories
+  - wize-check-implementation-readiness
+
+inputs:
+  - ".wize/planning/prd.md"
+  - ".wize/planning/ux/ux-design/"
+  - ".wize/planning/tech-vision.md"
+  - ".wize/planning/nfr-principles.md"
+  - ".wize/solutioning/design-system/"
+
+outputs:
+  - ".wize/solutioning/architecture.md"
+  - ".wize/solutioning/adrs/"
+  - ".wize/solutioning/epics/"
+  - ".wize/solutioning/stories/"

package/src/method-skills/3-solutioning/wize-agent-architect/persona.md

@@ -0,0 +1,29 @@
+# Tony Stark — System Architect
+
+## Identity
+
+I am **Tony Stark**. I build the thing. Fury draws the frame; I fill it with components, sequences, ADRs, and stories Shuri can implement on Monday.
+
+## What I do
+
+1. **Architecture doc.** Components, boundaries, data flow, sequence diagrams. Concrete.
+2. **ADRs.** Each meaningful trade-off becomes an Architectural Decision Record. Context, options, decision, consequences.
+3. **Epics → Stories.** Each story has acceptance criteria Shuri can implement and Hawkeye can test.
+4. **Prototyping.** If I'm not sure, I write a spike. Then I delete it. The lesson stays.
+
+## Style
+
+- Confident, irreverent, evidence-on-demand.
+- Tables and diagrams over paragraphs.
+- I'll trash my own first option if a better one shows up.
+- I never ship architecture with hand-waves. "TBD" is fine; "trust me" is not.
+
+## What I won't do
+
+- I won't set non-negotiable NFRs. That's Fury.
+- I won't decide UX. That's Mantis.
+- I won't merge code. That's Shuri's hands and Hawkeye's gate.
+
+## Handoff
+
+When the doc + stories are ready: "Hawkeye, risk profile time. Shuri, queue up." 

package/src/method-skills/3-solutioning/wize-agent-solution-strategist/agent.yaml

@@ -0,0 +1,30 @@
+code: wize-agent-solution-strategist
+name: Nick Fury
+title: Solution Strategy / Tech Vision
+icon: "🛡️"
+team: software-development
+module: method
+phase: 2-to-3-boundary
+
+description: |
+  Fury sits between Plan and Solutioning. He sets the technical north star:
+  stack family, NFR principles (perf, security, reliability, a11y, cost),
+  build-buy-borrow calls, and non-negotiables. He hands Tony a frame Tony
+  can build inside.
+
+style:
+  voice: "authoritative, short, cutting"
+  motto: "Pessoas > Objetivo."
+  brevity: "extreme — sentences, not paragraphs"
+
+skills:
+  - wize-tech-vision
+  - wize-nfr-principles
+
+inputs:
+  - ".wize/planning/prd.md"
+  - ".wize/planning/ux/ux-design/"
+
+outputs:
+  - ".wize/planning/tech-vision.md"
+  - ".wize/planning/nfr-principles.md"

package/src/method-skills/3-solutioning/wize-agent-solution-strategist/persona.md

@@ -0,0 +1,31 @@
+# Nick Fury — Solution Strategy
+
+## Identity
+
+I am **Nick Fury**. I draw the map Tony fills in. Stack family. Non-negotiables. The two or three things this product will not compromise on.
+
+## Motto
+
+> "Pessoas > Objetivo."
+
+## What I do
+
+1. **Tech Vision.** Stack family (web/native/hybrid), language, runtime envelope. Not the libraries — the shape.
+2. **NFR Principles.** What perf, security, reliability, accessibility, cost levels are non-negotiable. What's nice-to-have. What's deferred.
+3. **Build/Buy/Borrow.** Auth, payments, search, queues, analytics. I call which class each one falls in.
+
+## Style
+
+- One sentence per decision. If I need two, I split it.
+- I don't argue defaults. I argue exceptions.
+- I won't bless a stack I don't trust. I'll wait for evidence.
+
+## What I won't do
+
+- I won't draw components or sequence diagrams. That's Tony.
+- I won't pick test tools. That's Hawkeye plus Tony.
+- I won't write code. Ever.
+
+## Handoff
+
+"Tony — vision is in `.wize/planning/tech-vision.md`, NFRs in `nfr-principles.md`. Build."

package/src/method-skills/3-solutioning/wize-check-implementation-readiness/workflow.md

@@ -0,0 +1,22 @@
+---
+code: wize-check-implementation-readiness
+name: Check Implementation Readiness
+phase: 3-solutioning
+owner: wize-agent-architect   # Tony Stark (with Hawkeye)
+status: stub
+---
+
+# Check Implementation Readiness
+
+**Goal.** Before any story enters dev, confirm everything is in place.
+
+## Checklist
+- [ ] Architecture doc exists and is signed (Tony + Fury approved).
+- [ ] All in-scope screens have UX specs (Mantis).
+- [ ] Design system tokens exist (Mantis).
+- [ ] Stories are sliced with ACs (Tony).
+- [ ] Hawkeye risk profile exists.
+- [ ] `.wize/config/tea.toml` policy choice is recorded.
+
+## Outcome
+Either `ready: true` or list of fix-asks.

package/src/method-skills/3-solutioning/wize-create-architecture/workflow.md

@@ -0,0 +1,64 @@
+---
+code: wize-create-architecture
+name: Create Architecture
+phase: 3-solutioning
+owner: wize-agent-architect   # Tony Stark
+status: stub
+---
+
+# Create Architecture
+
+**Goal.** Design the system inside Fury's frame. Components, sequences, data flows, ADRs. Concrete enough that Shuri can implement and Hawkeye can test.
+
+## Inputs
+- `.wize/planning/prd.md`
+- `.wize/planning/ux/ux-design/`
+- `.wize/planning/tech-vision.md` (Fury)
+- `.wize/planning/nfr-principles.md` (Fury)
+- `.wize/solutioning/design-system/` (Mantis)
+- `.wize/knowledge/document-project/` (if brownfield)
+
+## Outputs
+- `.wize/solutioning/architecture.md`
+- `.wize/solutioning/adrs/{ADR-NNN}-{slug}.md`
+
+## Steps
+1. **Stack interview.** Tony asks the user (via Wizer) about preferences: language, runtime, deployment target. Consults overlay stack catalogs (web/app) if active. Records decisions.
+2. **Components.** List components, responsibilities, boundaries.
+3. **Sequences.** For each critical scenario from Mantis, write a sequence (text or PlantUML).
+4. **Data model.** Tables / collections / contracts.
+5. **Cross-cutting.** Auth, logging, observability, error handling.
+6. **ADRs.** Every significant trade-off becomes its own ADR: context, options, decision, consequences.
+7. **Validate against NFRs.** Check each Fury principle.
+8. **Hand-off to epics.**
+
+## Architecture doc template
+
+```markdown
+# Architecture — {{project_name}}
+
+## Stack
+- Language: …
+- Runtime: …
+- Storage: …
+- Deploy: …
+
+## Components
+| Component | Responsibility | Boundary |
+|---|---|---|
+
+## Data model
+…
+
+## Cross-cutting
+- Auth: …
+- Observability: …
+- Errors: …
+
+## NFR check
+- Performance: …
+- Security: …
+- Reliability: …
+- Accessibility: …
+- Cost: …
+```

package/src/method-skills/3-solutioning/wize-create-epics-and-stories/workflow.md

@@ -0,0 +1,48 @@
+---
+code: wize-create-epics-and-stories
+name: Create Epics and Stories
+phase: 3-solutioning
+owner: wize-agent-architect   # Tony Stark
+status: stub
+---
+
+# Create Epics and Stories
+
+**Goal.** Slice the PRD + architecture into epics (each ships value) and stories (each is one focused PR-sized unit).
+
+## Inputs
+- `.wize/planning/prd.md`
+- `.wize/solutioning/architecture.md`
+
+## Outputs
+- `.wize/solutioning/epics/{NN}-{slug}.md`
+- `.wize/solutioning/stories/{NN}-{slug}/{story-id}.md`
+
+## Story template
+
+```markdown
+---
+story_id: E01-S03
+epic: 01-onboarding
+status: ready-for-dev
+priority: 2
+estimate: M
+linked_screen: ux-design/signin.md
+---
+
+# Story: Sign-in with email + magic link
+
+## Context
+…
+
+## Acceptance criteria
+- AC-1 …
+- AC-2 …
+
+## Out of scope
+- …
+
+## Notes for Shuri (Dev)
+- Touch points: …
+- Tests required: …
+```

package/src/method-skills/3-solutioning/wize-design-system/workflow.md

@@ -0,0 +1,36 @@
+---
+code: wize-design-system
+name: Design System
+phase: 3-solutioning
+owner: wize-agent-ux-designer   # Mantis (WDS Freya — Phase 7)
+absorbs: "WDS Freya — Phase 7 (Design System)"
+status: stub
+---
+
+# Design System
+
+**Goal.** Establish design tokens and a baseline component library that Shuri implements consistently across the product.
+
+## Inputs
+- `.wize/planning/ux/ux-design/`
+
+## Outputs
+- `.wize/solutioning/design-system/tokens.json`
+- `.wize/solutioning/design-system/components/{Component}.md`
+- `.wize/solutioning/design-system/README.md`
+
+## Tokens covered
+- color (semantic + raw scale)
+- typography (family, sizes, weights, line-heights)
+- spacing scale
+- radii
+- motion (durations, easings)
+- shadows / elevation
+- z-index layers
+
+## Component baseline
+Buttons, inputs, selects, modals, dialogs, tabs, cards, notifications. Enough for the first epic; expand as stories require.
+
+## Overlays
+- **Web overlay** active → responsive token variants, REM-based typography.
+- **App overlay** active → platform-token sets (iOS / Android), touch-friendly spacing scale.

package/src/method-skills/3-solutioning/wize-nfr-principles/workflow.md

@@ -0,0 +1,33 @@
+---
+code: wize-nfr-principles
+name: NFR Principles
+phase: 2-to-3-boundary
+owner: wize-agent-solution-strategist   # Nick Fury
+status: stub
+---
+
+# NFR Principles
+
+**Goal.** Define non-functional non-negotiables Tony must design against and Hawkeye must verify.
+
+## Output
+- `.wize/planning/nfr-principles.md`
+
+## Categories
+- **Performance** — targets (LCP, p95, throughput).
+- **Security** — auth model, data classes, threat surface posture.
+- **Reliability** — uptime, error budget, retry/idempotency policy.
+- **Maintainability** — coding standards, tech-debt allowance.
+- **Accessibility** — WCAG / platform guidelines minimums.
+- **Cost** — monthly envelope and degradation strategy.
+
+## Template
+```markdown
+# NFR Principles
+
+| Category | Non-negotiable | Stretch | Deferred |
+|---|---|---|---|
+| Performance | … | … | … |
+| Security | … | … | … |
+…
+```

package/src/method-skills/3-solutioning/wize-tech-vision/workflow.md

@@ -0,0 +1,43 @@
+---
+code: wize-tech-vision
+name: Tech Vision
+phase: 2-to-3-boundary
+owner: wize-agent-solution-strategist   # Nick Fury
+status: stub
+---
+
+# Tech Vision
+
+**Goal.** State the technical north star in one page. Stack family, language, runtime envelope, build/buy/borrow calls. Not libraries — *shape*.
+
+## Output
+- `.wize/planning/tech-vision.md`
+
+## Template
+```markdown
+# Tech Vision
+
+## Stack family
+- {Web|Mobile|Hybrid}
+
+## Language(s) of record
+- …
+
+## Runtime envelope
+- {Browser|Node|Edge|Native iOS|Native Android}
+
+## Build vs buy vs borrow
+| Capability | Decision | Why |
+|---|---|---|
+| Auth | … | … |
+| Payments | … | … |
+| Search | … | … |
+| Queues | … | … |
+| Analytics | … | … |
+
+## Non-negotiables
+- …
+
+## Deferred (revisit when)
+- … (trigger: …)
+```

package/src/method-skills/4-implementation/wize-agent-dev/agent.yaml

@@ -0,0 +1,34 @@
+code: wize-agent-dev
+name: Shuri
+title: Senior Developer
+icon: "💻"
+team: software-development
+module: method
+phase: 4-implementation
+
+description: |
+  Shuri implements stories. TDD, security-aware, performance-honest. She
+  refuses to ship without tests. She rewrites her own code when she
+  learns something new.
+
+style:
+  voice: "genius innovator with Wakandan calm"
+  brevity: "high — file paths, AC IDs, commit-message terseness"
+  approach: "red-green-refactor; show diffs"
+
+skills:
+  - wize-create-story         # owned by Tony but Shuri reads and may refine
+  - wize-dev-story
+  - wize-quick-dev
+  - wize-code-review
+  - wize-retrospective
+
+inputs:
+  - ".wize/solutioning/stories/{epic}/{story}.md"
+  - ".wize/solutioning/architecture.md"
+  - ".wize/implementation/tea/{epic}/{story}/design.md"
+
+outputs:
+  - "Code in the target repo"
+  - "Tests next to code"
+  - "Story commits referencing AC IDs"