wize-dev-kit 0.1.5 → 0.2.5

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (39) hide show
  1. package/CHANGELOG.md +130 -1
  2. package/README.md +64 -0
  3. package/package.json +1 -1
  4. package/src/method-skills/1-analysis/wize-document-project/workflow.md +188 -20
  5. package/src/method-skills/1-analysis/wize-prfaq/workflow.md +150 -11
  6. package/src/method-skills/1-analysis/wize-product-brief/workflow.md +90 -19
  7. package/src/method-skills/1-analysis/wize-refresh-knowledge/workflow.md +127 -0
  8. package/src/method-skills/1-analysis/wize-research/workflow.md +101 -9
  9. package/src/method-skills/1-analysis/wize-trigger-map/workflow.md +80 -16
  10. package/src/method-skills/2-plan-workflows/wize-create-prd/workflow.md +132 -23
  11. package/src/method-skills/2-plan-workflows/wize-ux-design/workflow.md +132 -28
  12. package/src/method-skills/2-plan-workflows/wize-ux-scenarios/workflow.md +91 -15
  13. package/src/method-skills/2-plan-workflows/wize-validate-prd/workflow.md +106 -12
  14. package/src/method-skills/3-solutioning/wize-check-implementation-readiness/workflow.md +101 -11
  15. package/src/method-skills/3-solutioning/wize-create-architecture/workflow.md +197 -29
  16. package/src/method-skills/3-solutioning/wize-create-epics-and-stories/workflow.md +127 -12
  17. package/src/method-skills/3-solutioning/wize-design-system/workflow.md +182 -22
  18. package/src/method-skills/3-solutioning/wize-nfr-principles/workflow.md +142 -16
  19. package/src/method-skills/3-solutioning/wize-tech-vision/workflow.md +127 -21
  20. package/src/method-skills/4-implementation/wize-code-review/workflow.md +105 -10
  21. package/src/method-skills/4-implementation/wize-create-story/workflow.md +131 -10
  22. package/src/method-skills/4-implementation/wize-dev-story/workflow.md +140 -17
  23. package/src/method-skills/4-implementation/wize-quick-dev/workflow.md +121 -18
  24. package/src/method-skills/4-implementation/wize-retrospective/workflow.md +112 -10
  25. package/src/method-skills/4-implementation/wize-sprint-planning/workflow.md +85 -10
  26. package/src/method-skills/4-implementation/wize-sprint-status/workflow.md +96 -11
  27. package/src/orchestrator-skills/wize-help/skill.md +25 -1
  28. package/src/tea-skills/wize-tea-design/workflow.md +104 -13
  29. package/src/tea-skills/wize-tea-gate/workflow.md +115 -25
  30. package/src/tea-skills/wize-tea-nfr/workflow.md +104 -14
  31. package/src/tea-skills/wize-tea-review/workflow.md +120 -13
  32. package/src/tea-skills/wize-tea-risk/workflow.md +99 -10
  33. package/src/tea-skills/wize-tea-trace/workflow.md +83 -12
  34. package/tools/installer/baseline.js +128 -0
  35. package/tools/installer/commands/agent.js +197 -0
  36. package/tools/installer/commands/sync.js +45 -0
  37. package/tools/installer/commands/update.js +172 -0
  38. package/tools/installer/version-check.js +117 -0
  39. package/tools/installer/wize-cli.js +98 -11
@@ -3,55 +3,164 @@ code: wize-create-prd
3
3
  name: Create PRD
4
4
  phase: 2-plan
5
5
  owner: wize-agent-pm # Maria Hill
6
- status: stub
6
+ status: ready
7
7
  ---
8
8
 
9
9
  # Create PRD
10
10
 
11
- **Goal.** Turn brief + research + trigger-map into a Product Requirements Document the team can build from.
11
+ **Goal.** Turn brief + research + trigger map into a Product Requirements Document the team can build from. The PRD names *what* and *why* with measurable boundaries. Mantis, Fury, Tony will read it. Shuri ships against the acceptance criteria.
12
+
13
+ Maria Hill drives. Peggy edits prose. Output lands in `.wize/planning/prd.md`.
12
14
 
13
15
  ## Inputs
14
- - `.wize/planning/brief.md`
15
- - `.wize/planning/research.md`
16
- - `.wize/planning/ux/trigger-map.md`
16
+
17
+ - `.wize/planning/brief.md` (vision, audience, success criteria).
18
+ - `.wize/planning/research.md` (when present).
19
+ - `.wize/planning/ux/trigger-map.md` (every PRD goal references rows of this map).
20
+ - `.wize/planning/prfaq.md` (when present — PRD scope mirrors FAQ Q5 "what's in/out").
17
21
 
18
22
  ## Outputs
23
+
19
24
  - `.wize/planning/prd.md`
25
+ - `.wize/solutioning/epics/` — coarse epic outlines Tony refines later.
20
26
 
21
27
  ## Steps
22
- 1. **Goals.** Pull the success criteria from the brief; restate as PRD goals.
23
- 2. **Scope (in / out).** Explicit list of in-scope and out-of-scope items.
24
- 3. **User stories backbone.** "As a … I want … so that …" — coarse, will be sliced by Tony.
25
- 4. **Acceptance criteria per scope item.** Each scope item gets ACs Hawkeye can test.
26
- 5. **Constraints + assumptions.** From brief and Fury (if Fury has run already).
27
- 6. **Open questions.** Owners assigned.
28
- 7. **Hand-off.** Trigger Mantis to start UX scenarios.
29
28
 
30
- ## PRD template
29
+ ### 1. Goals (3–5)
30
+
31
+ Pull the success criteria from the brief; restate as PRD goals. Each goal is:
32
+ - One sentence.
33
+ - Measurable (named metric + target + deadline).
34
+ - Tied to a trigger-map row.
35
+
36
+ Example: *"Reduce signup time from 3.5min to 1min by Q3 (signal: `signup_completed` median; row 1)."*
37
+
38
+ ### 2. Scope — in / out (explicit)
39
+
40
+ | In | Out (for now) |
41
+ |---|---|
42
+ | First-team signup flow | Multi-team admin roles |
43
+ | Self-serve invite | SSO via SAML |
44
+ | English (US) | Other locales |
45
+
46
+ If a stakeholder asked for it and it isn't here, they will ask again at gate review. Put their item in **Out** with a one-line reason, not silence.
47
+
48
+ ### 3. User stories backbone
49
+
50
+ Coarse stories that map to scope items. "As a {role}, I want to {action}, so that {outcome}." Each story will be sliced finer by Tony in `wize-create-epics-and-stories`.
51
+
52
+ Use the trigger-map rows as backbone:
53
+ - Row 1 (Sign up) → "As a team admin, I want to sign up with my work email, so that I can invite my team within 5 minutes."
54
+
55
+ ### 4. Acceptance criteria per scope item
56
+
57
+ For every In-scope item, write 3–7 ACs Hawkeye can test.
58
+
59
+ Format: `Given … When … Then …` or a numbered behavioral list.
60
+
61
+ ACs are **observable**. ✓ "If the user enters an invalid email, the input shows error text within 200ms." ✗ "The form validates emails correctly."
62
+
63
+ Each AC gets an ID: `AC-{epic}-{n}`. Hawkeye references these in `tea-trace.md`.
64
+
65
+ ### 5. Constraints + assumptions
66
+
67
+ Pull constraints from the brief. Add:
68
+ - **Assumptions** that, if wrong, change scope.
69
+ - **Dependencies** on other teams/services with name + deadline.
70
+
71
+ Each assumption is one line + verification plan. *"Assumption: Stripe Connect onboarding average 7 days. Verification: confirm with Stripe by 2026-07-01."*
72
+
73
+ ### 6. NFR pointer
74
+
75
+ Don't redefine NFRs in the PRD. Reference `.wize/planning/nfr-principles.md` (Fury's) once. Note any project-specific tightening.
76
+
77
+ ### 7. Open questions
78
+
79
+ What still needs deciding before solutioning starts. Each with an owner + deadline. Blockers can't carry into Phase 3.
80
+
81
+ ### 8. Hand off
82
+
83
+ - Mark `status: ready-for-validation`.
84
+ - Run `wize-validate-prd` (Maria Hill + Mantis + Fury sign-off).
85
+ - Then Mantis starts `wize-ux-scenarios`.
86
+
87
+ ## Output template
31
88
 
32
89
  ```markdown
90
+ ---
91
+ status: draft | ready-for-validation | validated
92
+ owner: Maria Hill
93
+ created: YYYY-MM-DD
94
+ ---
95
+
33
96
  # PRD — {{project_name}}
34
97
 
35
98
  ## Goals
36
- 1. …
99
+ 1. {{goal}} (metric: …, target: …, deadline: …, trigger-map row: )
100
+ 2. …
37
101
 
38
102
  ## Scope
103
+
39
104
  ### In scope
40
- -
105
+ - {{item}} — {{2–3 lines of detail}}
106
+
41
107
  ### Out of scope
42
- -
108
+ - {{item}} — {{one-line reason: not now / not us / not yet}}
43
109
 
44
- ## Backbone (user stories)
45
- -
110
+ ## Backbone (coarse stories)
111
+ - E01: As a {{role}}, I want to {{action}}, so that {{outcome}}.
112
+ - E02: …
46
113
 
47
114
  ## Acceptance criteria
48
- | Item | ACs |
49
- |---|---|
50
- | … | AC1 …; AC2 … |
51
115
 
52
- ## Constraints / assumptions
116
+ ### E01 Sign-up
117
+ - **AC-01-1:** Given a new visitor on `/signup`, When they submit a valid work email + password, Then an account is created and they land on `/onboarding` within 1.5s.
118
+ - **AC-01-2:** Given an invalid email, When the user blurs the field, Then error text appears within 200ms identifying which rule failed.
119
+ - **AC-01-3:** Given a duplicate email, When the user submits, Then they see a "Sign in instead?" CTA and the request returns HTTP 409.
53
120
  - …
54
121
 
122
+ ## Constraints
123
+ - Deadline: …
124
+ - Budget: …
125
+ - Compliance: GDPR, LGPD, SOC2.
126
+
127
+ ## Assumptions
128
+ - Stripe Connect onboarding ≤ 7 days avg. — verify by …
129
+ - Auth0 free tier sufficient for first 6 months. — verify by …
130
+
131
+ ## Dependencies
132
+ - Design system tokens from Mantis by {{date}}.
133
+ - Database from infra team by {{date}}.
134
+
135
+ ## NFR pointer
136
+ See `.wize/planning/nfr-principles.md`. Project tightening: p95 LCP ≤ 2.0s (vs. global 2.5s) on signup pages.
137
+
55
138
  ## Open questions
56
- - [ ] (owner: …)
139
+ - [ ] (blocker) Pricing tier exposed pre-payment? — *owner: NAME, by: DATE*
140
+ - [ ] (important) Brazil-only beta or global launch? — *owner: NAME, by: DATE*
57
141
  ```
142
+
143
+ ## INVEST checklist (per AC group)
144
+
145
+ Maria Hill validates every story's ACs against INVEST:
146
+
147
+ - **I**ndependent: no implicit dependency on another story being built first.
148
+ - **N**egotiable: details can move; intent can't.
149
+ - **V**aluable: a real outcome to a real user.
150
+ - **E**stimable: Tony can size it.
151
+ - **S**mall: ≤ 1 PR worth (sliced finer in Phase 3 if not).
152
+ - **T**estable: every AC is observable.
153
+
154
+ If any letter fails, fix the story before it leaves Plan.
155
+
156
+ ## Anti-patterns Maria Hill rejects
157
+
158
+ - **PRD as wishlist.** Pages of "the system shall…" with no Out-of-Scope. Force the cut.
159
+ - **ACs as descriptions.** "The form is responsive." → no. *"At 360px, the form fits in the viewport with no horizontal scroll."*
160
+ - **Open questions with no owner / no deadline.** They never get answered.
161
+ - **Constraint hidden in prose.** Pull to its own bullet.
162
+ - **PRD without a version + status.** Reviewers can't tell what they're reviewing.
163
+
164
+ ## Hand-off
165
+
166
+ > PRD draft is at `.wize/planning/prd.md`. Two open blockers; CEO and Sales Lead have until Friday. Mantis — once we're `validated`, you start with the trigger map + PRD. Fury — your call on stack family.
@@ -4,63 +4,167 @@ name: UX Design
4
4
  phase: 2-plan
5
5
  owner: wize-agent-ux-designer # Mantis
6
6
  absorbs: "WDS Freya — Phase 4 (Page Specs)"
7
- status: stub
7
+ status: ready
8
8
  ---
9
9
 
10
10
  # UX Design
11
11
 
12
- **Goal.** Page-by-page specifications. Each screen documents layout, content, interactions, edge/empty/error states.
12
+ **Goal.** Turn scenarios into page-by-page specifications Tony can architect against and Shuri can implement. One spec per screen. Every spec answers: purpose, primary action, layout, content, interactions, states (loading/empty/error/success/disabled), accessibility, and metrics.
13
+
14
+ Mantis drives. Output lands in `.wize/planning/ux/ux-design/{screen-name}.md`.
13
15
 
14
16
  ## Inputs
15
- - `.wize/planning/ux/ux-scenarios.md`
16
- - `.wize/planning/prd.md`
17
+
18
+ - `.wize/planning/ux/ux-scenarios.md` (every screen traces back to ≥ 1 scenario)
19
+ - `.wize/planning/prd.md` (every screen advances at least one AC)
20
+ - `.wize/solutioning/design-system/` (when Mantis already wrote tokens; otherwise this runs in parallel with `wize-design-system`)
21
+ - Overlay playbooks if active:
22
+ - `web-overlay/playbooks/wcag-aa.md`, `responsive-breakpoints.md`, `semantic-html.md`
23
+ - `app-overlay/playbooks/apple-hig.md`, `material-design-3.md`, `touch-targets-and-gestures.md`, `permissions-ux.md`
17
24
 
18
25
  ## Outputs
26
+
19
27
  - `.wize/planning/ux/ux-design/{screen-name}.md` (one per screen)
28
+ - `.wize/planning/ux/ux-design/index.md` (map of screens → scenarios → PRD ACs)
29
+
30
+ ## Steps
31
+
32
+ ### 1. Enumerate the screens
33
+
34
+ From the scenarios, list every screen needed to deliver the moment-of-truth. Name them by role + state: `signup-empty.md`, `signup-error.md`, `team-list-with-members.md`, `team-list-empty.md`. Empty/error/loading states are screens.
35
+
36
+ ### 2. Per screen: fill the spec template
37
+
38
+ For each screen, write the spec below. Stay disciplined; if a section is empty, ask why.
20
39
 
21
- ## Per-screen template
40
+ ### 3. Write the index
41
+
42
+ `index.md` is a single table mapping screen → scenarios touched → PRD ACs advanced. Tony reads this first; Hawkeye references it in `tea-design.md`.
43
+
44
+ ### 4. Hand off
45
+
46
+ Mark `status: ready-for-architecture` on each spec. Notify Wizer; Tony reads next.
47
+
48
+ ## Spec template (one file per screen)
22
49
 
23
50
  ```markdown
24
51
  ---
25
- screen: {{name}}
26
- linked_scenario: ux-scenarios.md#scenario-N
52
+ screen: signup-empty
53
+ status: ready-for-architecture
54
+ owner: Mantis
55
+ linked_scenarios: [S1]
56
+ linked_acs: [AC-01-1, AC-01-2]
27
57
  ---
28
58
 
29
- # {{Screen name}}
59
+ # Sign up (empty state)
30
60
 
31
61
  ## Purpose
32
-
62
+ First contact: a manager wants to create an account. The goal of *this* screen is to collect work email + password with minimum friction, in service of scenario S1 moment-of-truth (3 invites within 5 minutes).
33
63
 
34
64
  ## Primary user action
35
-
65
+ Submit the form (CTA: "Create account").
36
66
 
37
- ## Layout (ASCII wireframe or description)
67
+ ## Layout (ASCII or Mermaid)
68
+
69
+ (web overlay)
38
70
  ```
39
- ┌───────────────────────────────────────┐
40
- Header
41
- ├───────────────────────────────────────┤
42
- Content
43
- └───────────────────────────────────────┘
71
+ ┌─────────────────────────────────────────────────┐
72
+ Wize logo [Sign in →]
73
+ ├─────────────────────────────────────────────────┤
74
+
75
+ │ Create your team's account │
76
+ │ ────────────────────────── │
77
+ │ [ Work email ] │
78
+ │ [ Password (12+) ] │
79
+ │ │
80
+ │ [ Create account ] │
81
+ │ │
82
+ │ Already a member? Sign in │
83
+ │ │
84
+ └─────────────────────────────────────────────────┘
44
85
  ```
45
86
 
46
- ## Content
47
- - Headline: …
48
- - Body:
49
- - CTA: …
87
+ (app overlay note: stacked, top-aligned, system back disabled.)
88
+
89
+ ## Content (copy)
90
+
91
+ - Headline: "Create your team's account"
92
+ - Sub: (none — keep the screen empty for focus)
93
+ - Field 1 label: "Work email"
94
+ - Field 1 placeholder: "name@yourcompany.com"
95
+ - Field 2 label: "Password"
96
+ - Field 2 helper text: "At least 12 characters."
97
+ - CTA: "Create account"
98
+ - Secondary: "Already a member? Sign in" → routes to /signin
50
99
 
51
100
  ## Interactions
52
- - Click {{element}} → {{outcome}}
101
+
102
+ - Click CTA with valid form → submit; show loading state; redirect on success.
103
+ - Click CTA with invalid form → set focus to first invalid field; show error region.
104
+ - Tab order: email → password → CTA → "Sign in" link.
105
+ - Enter on either field submits if both are valid.
53
106
 
54
107
  ## States
55
- - Loading: …
56
- - Empty:
57
- - Error:
58
- - Success:
108
+
109
+ - **Loading:** CTA shows spinner; button is disabled; inputs remain editable.
110
+ - **Empty (this state):** placeholders visible; CTA disabled until both fields non-empty.
111
+ - **Error (inline per field):** error region appears under each field, `role="alert"`, identifies the rule and the fix.
112
+ - **Error (global):** Banner above headline if the back-end fails with a non-field error; provides a "retry" action.
113
+ - **Success:** redirect; no flash. The next screen owns acknowledgement.
114
+ - **Disabled:** CTA opacity 0.4; aria-disabled="true"; tooltip *"Fill both fields to continue"*.
59
115
 
60
116
  ## Accessibility notes
61
- - (web-overlay) WCAG …
62
- - (app-overlay) HIG / Material …
117
+
118
+ (web overlay)
119
+ - Both inputs have visible persistent labels (no placeholder-only).
120
+ - `lang="en"` on `<html>`.
121
+ - Error region: per-field `aria-describedby`, ALL `role="alert"` after first submit only.
122
+ - Contrast pairs all ≥ 4.5:1 in light mode, ≥ 4.5:1 in dark mode.
123
+ - 200% zoom: no horizontal scroll on 360px viewport.
124
+ - Skip link absent (no main nav before).
125
+
126
+ (app overlay)
127
+ - Apple HIG / Material 3 systemic input components.
128
+ - Dynamic Type / font scale: layout reflows at largest accessibility size; CTA pinned to bottom-safe-area.
129
+ - Touch targets ≥ 44pt (iOS) / 48dp (Android).
130
+ - VoiceOver order: headline → email → password → CTA → secondary link.
131
+
132
+ ## Metrics
133
+
134
+ - Event `signup_completed` (Q7 success quote): fires after redirect.
135
+ - Event `signup_error_shown {rule}`: fires on inline error.
136
+ - Event `signup_abandoned`: fires on `beforeunload` if form had focus and CTA never fired.
137
+
138
+ ## Open questions for Tony
139
+
140
+ - Should we use Auth0 hosted UI or our own form? (UX-decision is to keep our own; Tony decides feasibility.)
141
+ - Magic-link as an alternative path? Out of scope per PRD; Mantis recommends putting in *Out*.
63
142
  ```
64
143
 
144
+ ## Index template
145
+
146
+ ```markdown
147
+ # UX Design — index
148
+
149
+ | Screen | Scenarios | PRD ACs |
150
+ |---|---|---|
151
+ | signup-empty | S1 | AC-01-1, AC-01-2 |
152
+ | signup-error | S1 | AC-01-2 |
153
+ | onboarding-step-1 | S1 | AC-02-1 |
154
+ | team-list-empty | S1, S2 | AC-03-1 |
155
+ | team-list-with-members | S1, S2 | AC-03-2, AC-03-3 |
156
+ | invite-modal | S1, S2 | AC-02-2, AC-02-3 |
157
+ ```
158
+
159
+ ## Anti-patterns Mantis rejects
160
+
161
+ - **Specs without states.** A screen with no empty/error spec is half a spec.
162
+ - **Copy as marketing tone.** Use the user's voice. Cut "world-class," "delightful," "seamless."
163
+ - **Mystery icons.** Icons need accessible labels; if you can't name it, draw a word next to it.
164
+ - **Hover-only affordances on touch.** Spec the non-hover equivalent.
165
+ - **Touch targets < platform minimum.** 24×24 CSS px on web (WCAG 2.5.8), 44pt iOS, 48dp Android — non-negotiable.
166
+ - **Screens that don't trace to scenarios + PRD ACs.** If you can't fill the index row, the screen isn't justified.
167
+
65
168
  ## Hand-off
66
- "Tony, screen specs in `.wize/planning/ux/ux-design/`. Architecture time."
169
+
170
+ > UX specs are at `.wize/planning/ux/ux-design/`. Index points screen → scenario → AC. Tony, you can start `wize-create-architecture` now; the moment-of-truth lines in scenarios tell you which interactions are load-bearing. Hawkeye, `tea-design.md` should index by screen to keep test design and UI aligned.
@@ -4,45 +4,121 @@ name: UX Scenarios
4
4
  phase: 2-plan
5
5
  owner: wize-agent-ux-designer # Mantis (absorbs WDS Freya)
6
6
  absorbs: "WDS Freya — Phase 3 (8-question dialog)"
7
- status: stub
7
+ status: ready
8
8
  ---
9
9
 
10
10
  # UX Scenarios
11
11
 
12
- **Goal.** Produce the scenario map that anchors all UX work. Eight focused questions; one answer each.
12
+ **Goal.** Produce a scenario map that anchors all UX work. Eight focused questions; one short answer each. Scenarios are pieces of behavior, not personas — they're how *this* user, in *this* state, tries to accomplish *that* JTBD.
13
+
14
+ Mantis drives. Output lands in `.wize/planning/ux/ux-scenarios.md`. It's the bridge from PM intent (PRD) to designer concreteness (next workflow: `wize-ux-design`).
13
15
 
14
16
  ## Inputs
15
- - `.wize/planning/prd.md`
16
- - `.wize/planning/ux/trigger-map.md`
17
+
18
+ - `.wize/planning/prd.md` (validated)
19
+ - `.wize/planning/ux/trigger-map.md` (Pepper)
17
20
  - `.wize/planning/brief.md`
18
21
 
19
22
  ## Outputs
23
+
20
24
  - `.wize/planning/ux/ux-scenarios.md`
21
25
 
22
- ## The 8 questions (WDS dialog)
26
+ ## Steps
27
+
28
+ ### 1. Identify the scenarios
29
+
30
+ A scenario = one (user, state, JTBD) tuple where the product earns or loses. Aim for **3–8 scenarios** that, taken together, cover all backbone stories in the PRD.
31
+
32
+ Rules:
33
+ - One sentence each at this stage.
34
+ - Verb-led. *"New manager onboards their first team."* Not *"Manager onboarding."*
35
+ - Distinct. If two scenarios share trigger + state, collapse them.
36
+
37
+ ### 2. Run the 8-question dialog per scenario (WDS Freya)
38
+
39
+ For each scenario, answer the eight questions. One paragraph per answer. No filler. Cite trigger-map row when relevant.
23
40
 
24
41
  1. **Who is the user, in one sentence?**
25
- 2. **What state are they in when they arrive?** (emotional, contextual)
26
- 3. **What are they trying to accomplish?** (job-to-be-done)
42
+ Role + context. *"A 38-year-old engineering manager at a 25-person SaaS, primarily on desktop, sometimes phone."*
43
+
44
+ 2. **What state are they in when they arrive?**
45
+ Emotion + situational context. *"It's Monday morning. They just got CTO's request to onboard 3 hires this sprint. They're alt-tabbing between Slack and Linear."*
46
+
47
+ 3. **What are they trying to accomplish?** (JTBD)
48
+ *"Add three teammates and assign each to the right project before the team standup at 10am."* Concrete.
49
+
27
50
  4. **What would they do without our product today?**
51
+ *"Slack screenshots of the project list to each new hire; have them sign up individually; cross-check who landed where."*
52
+
28
53
  5. **What's the moment of truth — when they decide it works?**
54
+ *"The first time they see all three names in the team list with the right project tags, in under 5 minutes."*
55
+
29
56
  6. **What's the failure mode — when do they walk away?**
57
+ *"If they can't tell whether the invite arrived. If the invite email looks like spam. If they have to leave the page to find someone's email."*
58
+
30
59
  7. **What does success look like to them, in their words?**
60
+ *"It just worked. I sent the invites, they signed up, they were on the right project."* (Imagine the future quote.)
61
+
31
62
  8. **What's the next thing we want them to do?**
63
+ *"Open the project where the first teammate landed and verify the access works."*
32
64
 
33
- ## Output structure
65
+ ### 3. Cross-link to the PRD
66
+
67
+ For each scenario, list the **backbone story IDs** + **AC IDs** it touches. Mantis won't write specs for a scenario the PRD doesn't cover (it'd be scope creep); Hill won't sign off on a story the scenarios don't surface (it'd be over-spec).
68
+
69
+ ### 4. Hand off to UX Design
70
+
71
+ Mark `status: ready-for-design`. Wizer pings Mantis to start `wize-ux-design`, where each scenario becomes one or more page specs.
72
+
73
+ ## Output template
34
74
 
35
75
  ```markdown
36
- # UX Scenarios
76
+ ---
77
+ status: ready-for-design
78
+ owner: Mantis
79
+ created: YYYY-MM-DD
80
+ covers_prd_stories: [E01, E02, E04]
81
+ ---
82
+
83
+ # UX Scenarios — {{project_name}}
37
84
 
38
- ## Scenario 1: {{name}}
85
+ ## Scenario 1: New manager onboards their first team
39
86
 
40
- - Q1
41
- - Q2
42
- -
87
+ - **Trigger-map row:** 1 (Sign up), 2 (Invite first teammate)
88
+ - **PRD stories:** E01, E02
89
+ - **AC IDs touched:** AC-01-1, AC-01-2, AC-02-1, AC-02-3
43
90
 
44
- ## Scenario N:
91
+ **Q1 Who:** A 38-year-old engineering manager at a 25-person SaaS, primarily on desktop, sometimes phone.
92
+ **Q2 — State:** It's Monday morning. They just got CTO's request to onboard 3 hires this sprint. They're alt-tabbing between Slack and Linear.
93
+ **Q3 — JTBD:** Add three teammates and assign each to the right project before the team standup at 10am.
94
+ **Q4 — Today:** Slack screenshots of the project list to each new hire; have them sign up individually; cross-check who landed where.
95
+ **Q5 — Moment of truth:** The first time they see all three names in the team list with the right project tags, under 5 minutes.
96
+ **Q6 — Failure mode:** Can't tell whether the invite arrived; the email looks like spam; they have to leave the page to find someone's email.
97
+ **Q7 — Success in their words:** "It just worked. I sent the invites, they signed up, they were on the right project."
98
+ **Q8 — Next thing:** Open the project where the first teammate landed and verify access.
99
+
100
+ ## Scenario 2: Returning admin adds a fourth member months later
101
+
102
+ (…)
103
+
104
+ ## Coverage check
105
+
106
+ | PRD story | Scenarios |
107
+ |---|---|
108
+ | E01 (Sign up) | S1 |
109
+ | E02 (Invite) | S1, S2 |
110
+ | E03 (Switch project) | S2 |
111
+ | E04 (Dashboard) | S1 |
45
112
  ```
46
113
 
114
+ ## Anti-patterns Mantis rejects
115
+
116
+ - **Personas instead of scenarios.** Mantis cares what people *do*, not who they are in the abstract.
117
+ - **Scenarios with no emotion or context.** "User wants to sign up." — that's a backbone story restated. The point is the *state*.
118
+ - **JTBD written as features.** "Wants the dashboard." Wrong layer. Reword to the goal: "Wants to know if the team is healthy at a glance."
119
+ - **Q5 ("moment of truth") that's actually a feature description.** It should be the user's perception, not the UI.
120
+ - **More than 8 scenarios.** Two of them are duplicates. Find which.
121
+
47
122
  ## Hand-off
48
- "Mantis → Mantis": run `wize-ux-design` next.
123
+
124
+ > Scenarios are in `.wize/planning/ux/ux-scenarios.md`. They cover E01–E04. Next: page specs in `.wize/planning/ux/ux-design/` (one per screen). Tony, when you read these, the moment-of-truth lines tell you which interactions are load-bearing.
@@ -2,26 +2,120 @@
2
2
  code: wize-validate-prd
3
3
  name: Validate PRD
4
4
  phase: 2-plan
5
- owner: wize-agent-pm # Maria Hill (with Pepper + Mantis + Fury input)
6
- status: stub
5
+ owner: wize-agent-pm # Maria Hill (with Pepper, Mantis, Fury input)
6
+ status: ready
7
7
  ---
8
8
 
9
9
  # Validate PRD
10
10
 
11
- **Goal.** Make sure the PRD is ready to leave Plan and enter Solutioning. Catch ambiguity before architecture is wasted on it.
11
+ **Goal.** Decide whether the PRD is ready to leave Plan and enter Solutioning. Catch ambiguity before architecture is wasted on it. Cheap step; saves multiples of itself downstream.
12
+
13
+ Maria Hill chairs. Pepper, Mantis, Fury contribute. Output is either `validated: true` written to `prd.md` or a punch list routed back to authors.
14
+
15
+ ## When to run
16
+
17
+ After `wize-create-prd` produces `status: ready-for-validation`. Run once per major PRD change.
12
18
 
13
19
  ## Inputs
20
+
14
21
  - `.wize/planning/prd.md`
22
+ - `.wize/planning/brief.md`
23
+ - `.wize/planning/ux/trigger-map.md`
24
+ - `.wize/planning/research.md` (when present)
25
+ - `.wize/planning/tech-vision.md` (when Fury already wrote one)
15
26
 
16
27
  ## Outputs
17
- - Inline edits + a validation log appended to `prd.md`.
18
28
 
19
- ## Checklist
20
- - [ ] Every scope item has measurable ACs.
21
- - [ ] No "TBD" in goals or constraints.
22
- - [ ] Mantis confirms UX is addressable.
23
- - [ ] Fury approves stack-family direction (or has explicit reason not to yet).
24
- - [ ] No open questions with `blocker` priority remain.
29
+ - In-place edits to `prd.md` (validators add a "Validation log" section).
30
+ - If validated: `prd.md` frontmatter flips to `status: validated`.
31
+ - If not: a punch list, each item routed back to the owning agent.
32
+
33
+ ## Checklist (Maria Hill runs this)
34
+
35
+ ### Completeness
36
+ - [ ] Vision sentence present and matches the brief.
37
+ - [ ] 3–5 goals; each measurable; each tied to a trigger-map row.
38
+ - [ ] Scope `In` and `Out` both populated; `Out` items have reasons.
39
+ - [ ] Backbone stories cover every In-scope item.
40
+ - [ ] Every In-scope item has 3–7 ACs.
41
+ - [ ] Constraints + Assumptions + Dependencies all named.
42
+ - [ ] NFR pointer present.
43
+ - [ ] Open questions: each has an owner + deadline.
44
+
45
+ ### Quality
46
+ - [ ] Every AC is observable (testable by Hawkeye without ambiguity).
47
+ - [ ] No AC contains the word "easy", "intuitive", "responsive" without a numeric criterion.
48
+ - [ ] INVEST: every backbone story passes (independent, negotiable, valuable, estimable, small, testable).
49
+ - [ ] No goal repeats a brief constraint as if it were a goal.
50
+
51
+ ### Cross-checks
52
+ - [ ] **Pepper:** every goal anchors on a row of the trigger map.
53
+ - [ ] **Mantis:** every screen implied by the ACs is addressable in UX (no AC requires a UI the team hasn't agreed exists).
54
+ - [ ] **Fury:** the PRD's NFR pointer doesn't contradict the tech-vision.
55
+ - [ ] **Hawkeye preview:** at least the gate strategy is mentioned (advisory vs enforcing) for visibility.
56
+
57
+ ### Risk
58
+ - [ ] No open question is marked `blocker` AND has a deadline past the PRD validation date.
59
+ - [ ] Any assumption that, if wrong, kills > 30% of the scope has a verification plan.
60
+
61
+ ## Decision
62
+
63
+ After the checklist:
64
+
65
+ - **Validated** → flip frontmatter to `status: validated`. Append a Validation log block to `prd.md` with date + each signatory.
66
+ - **Concerns** → write specific fix-asks per agent. Each fix-ask is concrete (line ref + what to change).
67
+ - **Reject** → rare. Use when the brief itself is wrong; loop back to Pepper.
68
+
69
+ ## Validation log template (appended to `prd.md`)
70
+
71
+ ```markdown
72
+ ## Validation log — YYYY-MM-DD
73
+
74
+ **Status:** validated
75
+
76
+ **Signatories**
77
+ - Maria Hill (PM) — concerns: none
78
+ - Pepper Potts (Analyst) — concerns: trigger-map row 3 needs a stronger signal name, will update.
79
+ - Mantis (UX) — concerns: none, UX work starts next.
80
+ - Fury (Solution Strategy) — concerns: none. NFR pointer confirmed.
81
+
82
+ **Notes**
83
+ - Open question "Brazil-only beta?" was answered by sales lead — added to *Out of scope: global launch* with rationale.
84
+ ```
85
+
86
+ ## Punch-list template (when not validated)
87
+
88
+ ```markdown
89
+ ## Validation punch list — YYYY-MM-DD
90
+
91
+ **Status:** changes required
92
+
93
+ **By Maria Hill — author rewrites:**
94
+ - `AC-02-3`: "loads fast" is not observable. Rewrite with numeric target tied to Fury's NFRs.
95
+ - Backbone story E04 fails INVEST-S (too large). Split into 2 stories.
96
+
97
+ **By Pepper:**
98
+ - Goal 2 is not anchored on a trigger-map row. Add row reference or remove.
99
+
100
+ **By Mantis:**
101
+ - AC-01-4 implies a "preview" screen that isn't in any UX list. Either spec the screen or cut the AC.
102
+
103
+ **By Fury:**
104
+ - NFR pointer cites old version of nfr-principles.md. Update.
105
+ ```
106
+
107
+ ## Anti-patterns
108
+
109
+ - "Looks good to me" with no checklist run. The validation only counts if checked.
110
+ - Validating to keep the schedule, knowing concerns are open. Document the concern.
111
+ - Validating with no Hawkeye preview at all. Even a one-line gate strategy reference matters.
112
+
113
+ ## Hand-off
114
+
115
+ If validated:
116
+
117
+ > PRD validated. Mantis, you're up: `wize-ux-scenarios`. Fury, write or refresh `tech-vision.md` so Tony can read both.
118
+
119
+ If not:
25
120
 
26
- ## Outcome
27
- Either `validated: true` (timestamp + signatories) or list of fix-asks routed back to the right agent.
121
+ > PRD not yet validated. Punch list lives at the bottom of `prd.md`. {{Author}} fixes by {{date}}; we re-run validation.