@sun-asterisk/sungen 2.6.15 → 2.7.0-beta.1

package/dist/orchestrator/templates/ai-instructions/github-skill-sungen-viewpoint.md

@@ -1,268 +1,97 @@
 ---
 name: sungen-viewpoint
-description: '10 UI patterns x 4 viewpoints — structured checklist for test case generation and review. Auto-loaded by create-test and review commands.'
+description: '17 UI patterns x 4 viewpoints — structured checklist for test case
+  generation and review. Auto-loaded by create-test and review commands.'
 user-invocable: false
 ---
 
-## 4 Viewpoints
-
-| VP | Focus | Keyword |
-|---|---|---|
-| **UI/UX** | Interface states, layout, feedback | VP-UI |
-| **Data & Validate** | Input constraints, data integrity, error messages | VP-VAL |
-| **Logic** | Business rules, interactions, state changes | VP-LOGIC |
-| **Security** | Auth, injection, permissions | VP-SEC |
-
-## Shared Checks (apply across all patterns)
-
-These appear in multiple patterns — test once per screen, not per pattern:
-
-| Check | ER |
-|---|---|
-| **Loading State** | Spinner/skeleton shown, UI interaction locked during fetch |
-| **Empty State** | Clear message when no data, layout intact |
-| **XSS/Injection** | Malicious input sanitized to plain text, never executed |
-| **URL Manipulation** | Invalid URL params fallback to defaults, no server crash |
-
----
-
-## GROUP 1: DATA ENTRY
-
-### 1. Form & Inputs
-
-**UI/UX**
-- Field States: disabled/readonly fields dimmed and locked, no interaction allowed
-- Button States: Submit disabled when form invalid, auto-enabled when valid
-- Keyboard Nav: Tab order correct, Enter submits form
-
-**Data & Validate**
-- Required/Optional: blank required field shows error; optional allows blank
-- Boundaries & Format: min/max length, format (email, number) with error messages
-- Whitespace: auto-trim or reject spaces-only input
-- Error Recovery: error at correct field, disappears immediately when user corrects data
-
-**Logic**
-- Field Dependencies: Field A value determines Field B status/options
-- Double Submit Prevention: button disabled after first click, only 1 request sent
-- Success Flow: redirect / success toast / form reset
-- Failure Flow: server error retains form data + shows system error
-
-**Security**
-- → Shared: XSS/Injection
-
----
-
-## GROUP 2: DATA MANAGEMENT
+## How to use this skill
 
-### 2. Data Table
+This skill is a **router**. The detailed checklists live in 5 group files — load only the ones relevant to the screen under test.
 
-**UI/UX**
-- → Shared: Empty State, Loading State
-- Truncation: long content shows `...` with tooltip on hover, column width stable
-- Sticky Elements: fixed header on vertical scroll, fixed action column on horizontal scroll
+1. Read the **4 Viewpoints** and **Shared Checks** below (always).
+2. Identify which UI patterns the screen contains, resolve any overlap via **Pattern selection** below, then read **only** the matching group file(s) from the routing table.
+3. Generate Tier 1 (`@high`) scenarios first, then Tier 2 (`@normal` + `@low`). Apply each Shared Check **once per screen**, not once per pattern.
 
-**Data & Validate**
-- Record Count: "Total records" on UI matches server data exactly
-- Row Limit: displayed rows never exceed configured page size
-- Cell Integrity: cell data matches database, correct format (date, currency, status label)
-
-**Logic**
-- Sorting: column sort refreshes table with correct order, updates header icon
-- Row Actions: Edit/Delete/View buttons act on correct row ID
-
-**Security**
-- RBAC: hide sensitive columns or privileged action buttons without authority
-- → Shared: XSS/Injection (data from DB displayed safely)
-
----
-
-### 3. Create / Add
-
-**UI/UX**
-- Blank Slate: all fields empty or BA-specified defaults, NO cache from previous operation
-- Required Indicator: required fields marked with visual cue (e.g., red *)
-- Unsaved Changes: navigate away with dirty form → browser/system warning popup
-
-**Data & Validate**
-- → Inherited: all Form & Inputs validation rules apply
-- Unique Constraint: duplicate unique field (e.g., Employee ID) → reject save, inline error
-- Data Dependency: selecting parent field loads correct child options
-
-**Logic**
-- Save & Close: toast notification, redirect to list, new record visible per sort rule
-- Save & Add Another: save to DB, form resets to blank for next entry
-- Double Submit Prevention: → same as Form & Inputs
-- Cancel: form closes, NO garbage record in DB, next open shows blank form
-
-**Security**
-- API Bypass / 403: unauthorized POST → system blocks (403 Forbidden), no record created
-- → Shared: XSS/Injection (persisted safely, not executed on display)
-
----
-
-### 4. Update / Edit
-
-**UI/UX**
-- Pre-fill / Data Binding: all fields display exact current DB data (text, dropdown, radio, date...)
-- Readonly Fields: identity fields (ID, username, employee code) disabled, no interaction
-- Cancel: no data changed in DB; if dirty → unsaved changes warning
-
-**Data & Validate**
-- → Inherited: all Form & Inputs validation rules apply
-- Unique Self: saving without changing unique field → success, no self-duplicate error
-- Unique Conflict: changing unique field to existing value → duplicate error, block save
-- Unchanged Submit: Save disabled until dirty, or success without DB UPDATE
-
-**Logic**
-- Update Success: toast "Updated successfully", new data reflects on UI immediately without reload
-- Concurrent Edit: another user already edited → conflict warning, require reload
-
-**Security**
-- Authorization / 403: access edit without permission → 403 page
-- Not Found / 404: edit deleted object → 404
-
----
+> All checklist items are written in English. Render scenario names, step text, and test IDs in English.
 
-### 5. Delete
+## Routing table
 
-**UI/UX**
-- Confirmation: click Delete → MUST show confirmation dialog, delete button in warning color
-- Cancel: popup closes, record intact on UI and DB, no API called
-- Success Update: toast "Deleted successfully", record disappears immediately without reload
-- Pagination Fallback: delete only record on current page → auto-navigate to previous page
-
-**Data & Validate — Dependencies**
-- Independent: delete succeeds normally
-- Referenced (Restrict): delete parent with children → blocked, clear error "in use at [Module]"
-- Referenced (Cascade): warning first, then deletes parent AND all related children
-- Referenced (Set Null): parent deleted, child reference set to Unassigned/Empty
-
-**Logic — Storage**
-- Soft Delete: record hidden from UI, DB retains with status flag (is_deleted, deleted_at)
-- Hard Delete: record removed from UI AND permanently deleted from DB
-
-**Security**
-- Deleted Access / 404: soft or hard delete → direct URL/API returns 404
-- API Bypass: API delete on restricted object → backend rejects with business error, no 500
-
----
-
-### 6. Search
-
-**UI/UX**
-- → Shared: Empty State ("No results found"), Loading State
-- Clear Action: search box empties, list reloads default data
-
-**Data & Validate**
-- Whitespace: auto-trim, results match cleaned keyword
-- Input Limits: prevent beyond max length or show error
-- Normalization: case-insensitive, handles accented characters correctly
-
-**Logic**
-- Matching: partial/exact match returns correct results, no 500
-- Multi-keyword: results based on AND/OR logic per spec
-- Debounce: ~300ms delay before API call
-
-**Security**
-- → Shared: XSS/Injection
-- Wildcards: `%`, `_`, `*` treated as literal text (escaped), not DB commands
-
----
-
-### 7. Filter
-
-**UI/UX**
-- Feedback: selected filters displayed as tags/badges
-- Persistence: collapse/expand retains selected values
-- Conflicts: conflicting conditions show "No data" message, layout intact
-
-**Data & Validate**
-- Range Validation: start > end or min > max → field error, Apply disabled
-- Dropdown Integrity: options match 100% of actual data, hide unauthorized values
-
-**Logic**
-- AND/OR Logic: results satisfy correct filter logic, total count updated
-- Dependent Filters: selecting Filter A updates Filter B options
-- Reset & Navigation: reset returns original data or preserves state per spec
-
-**Security**
-- → Shared: URL Manipulation
-
----
-
-### 8. Pagination
-
-**UI/UX**
-- Boundary States: Previous/First disabled on page 1, Next/Last disabled on last page
-- Active Page: highlighted, loading effect during page transition
-- Hidden: pagination bar hidden when data fits one page
-
-**Data & Validate**
-- Label Consistency: "Viewing X of Y" matches actual data exactly
-- Zero Records: pagination hidden, empty state displayed
-
-**Logic**
-- Navigation: loads correct dataset for page (page 2, limit 10 = records 11-20)
-- Change Page Size: shows correct quantity, resets to page 1
-- Interaction Resets: new search/filter resets to page 1
-
-**Security**
-- → Shared: URL Manipulation
-
----
-
-## GROUP 3: NAVIGATION & CONTAINERS
-
-### 9. Modal / Dialog
-
-**UI/UX**
-- Overlay: centered modal, backdrop blur, background scroll locked
-- Focus Trapping: Tab key cycles only within modal elements
-- Responsive: modal resizes, action buttons always visible or scrollable
+| UI element on the screen | Pattern | Read file |
+|---|---|---|
+| Plain input form (settings, profile, contact) | 1. Form & Inputs **(base)** | `group-a-data-entry.md` |
+| File picker / drop zone | 2. File Upload | `group-a-data-entry.md` |
+| Bulk import / export | 3. Import / Export | `group-a-data-entry.md` |
+| "Add" / "Create" / "New" | 4. Create / Add | `group-b-data-ops.md` |
+| "Edit" / pencil icon / inline edit | 5. Update / Edit | `group-b-data-ops.md` |
+| "Delete" / trash icon | 6. Delete | `group-b-data-ops.md` |
+| Rows + columns grid | 7. Data Table | `group-c-data-explore.md` |
+| Search box / search bar | 8. Search | `group-c-data-explore.md` |
+| Filter controls (dropdown, date range, checkboxes) | 9. Filter | `group-c-data-explore.md` |
+| Card / list grid, infinite scroll, "Load More" | 10. List / Card View | `group-c-data-explore.md` |
+| Charts / KPI cards / dashboard | 11. Chart / Analytics | `group-d-display.md` |
+| Overlay panel on top of the page | 12. Modal / Dialog | `group-d-display.md` |
+| Side menu / tabs / breadcrumb / top nav | 13. Navigation | `group-d-display.md` |
+| Toast / snackbar / alert / banner | 14. Notification / Toast / Alert | `group-d-display.md` |
+| Login form / logout button | 15. Login / Logout | `group-e-identity.md` |
+| Sign-up form / SSO | 16. Register | `group-e-identity.md` |
+| Forgot / reset / change password | 17. Password Management | `group-e-identity.md` |
+
+## Pattern selection (precedence & inheritance)
+
+A screen often matches several patterns at once — a login screen is *both* a form and an authentication flow. Use these rules so the choice is deterministic and scenarios are never duplicated:
+
+1. **Most specific wins.** Pick the most specialized pattern as the screen's primary section. Auth and CRUD forms route to their specific pattern, NOT to Form & Inputs:
+   - Login/logout → **15**, sign-up → **16**, forgot/reset/change password → **17**
+   - Create form → **4**, edit form → **5**
+2. **Form & Inputs (1) is a BASE pattern, not a sibling.** Generate it as its own section only for a plain form with no more-specific role (settings, profile, contact). When a specialization applies, do NOT also create a separate "Form & Inputs" section.
+3. **Inheritance.** A specialized form pattern (4, 5, 15, 16, 17) **inherits** Form & Inputs field-level validation (required, format, maxlength, whitespace, real-time error clear) and adds its own rules. Apply the inherited checks inside the specialized section — generate each check once, never twice.
+4. **Genuinely parallel pairs** — these cover different concerns; choose per the table:
+
+   | If the screen has… | Decision |
+   |---|---|
+   | A grid of records | Pick **7. Data Table** *or* **10. List/Card** by layout (rows+columns → Table; cards/tiles/infinite-scroll → List/Card) — not both for the same surface |
+   | Both a keyword box and filter controls | Apply **8. Search** *and* **9. Filter** (Search = free-text match; Filter = structured narrowing) + one combined AND-logic scenario |
+   | A form rendered inside an overlay | Apply the form's pattern (1/4/5/15…) for fields/submit **and** **12. Modal/Dialog** for open/close/focus-trap/backdrop |
 
-**Data & Validate**
-- Dismiss Actions: close via X, Cancel, Escape, backdrop click → resets data to default on reopen
+## 4 Viewpoints
 
-**Logic**
-- Submit Success: action button shows loading, modal closes, background data updated
-- Submit Failure: modal stays open, shows error message, retains entered data
-- Stacked Modals: Modal B over A has higher z-index, closing B keeps A intact
+| VP | Focus | Tag |
+|---|---|---|
+| **UI/UX** | Interface state, layout, visual feedback | VP-UI |
+| **Data & Validate** | Input constraints, data integrity, error messages | VP-VAL |
+| **Logic** | Business rules, interactions, state changes | VP-LOGIC |
+| **Security** | Authentication, authorization, injection | VP-SEC |
 
-**Security**
-- DOM Cleanup: remove HTML from DOM on close to protect sensitive data
-- Reload: handles deep linking if present
+**Classification rules:**
+- VP-UI = state that is always true regardless of what the user does (element present, layout, label)
+- VP-VAL = outcome depends on the input *value* (valid / invalid / boundary)
+- VP-LOGIC = outcome depends on the user's *action* (click, submit, navigate)
+- VP-SEC = checks access control and malicious input
 
 ---
 
-## GROUP 4: DISPLAY PATTERNS
-
-### 10. List / Card
-
-**UI/UX**
-- → Shared: Empty State, Loading State
-- Hover Effect: shadow/scale on card hover
-- Content: text truncation without breaking card height, placeholder image on broken image
+## Shared Checks
 
-**Data & Validate**
-- Integrity: data fields (price, status, tag) 100% accurate vs system
-- Total Count: matches actual database count after filtering
+Generate **once per screen**, do not repeat for each pattern.
+Each pattern only points back with "Shared checks applied: [name]".
 
-**Logic**
-- Navigation: clicking card navigates to correct detail page
-- Direct Actions: Like/Add to Cart updates immediately without reloading list
-- Infinite Scroll / Load More: appends records, maintains scroll position
-- Layout Toggle: Grid/List view switch changes UI but preserves data
+| Check | Condition → Expected | VP | Priority |
+|---|---|---|---|
+| **Loading State** | Data fetch in progress → spinner/skeleton shown, user cannot interact | UI | @normal |
+| **Empty State** | Query returns 0 records → clear message shown, layout does not break | UI | @normal |
+| **XSS** | Script tag entered into a field → rendered as literal text, not executed | SEC | @high |
+| **SQL injection** | SQL payload entered into a field → DB unaffected, no data exposed | SEC | @high |
+| **URL Manipulation** | URL params wrong/missing/out-of-range → fallback to default, no 500 crash | SEC | @high |
 
-**Security**
-- RBAC: hide sensitive data or privileged buttons from DOM
-- Network Resilience: error message + "Retry" button on connection loss
+> **SQL injection — 2 layers for search/LIKE fields**: (1) field-level: UI blocks special chars → `@high` automated; (2) API-level: if the field reaches a LIKE query (search, partial-match), send `1 OR 1=1` straight to the API endpoint (bypassing the UI) → verify a parameterized query is used → `@high @manual`. Missing layer 2 = a real attack vector is overlooked even when field validation is correct.
 
 ---
 
 ## Security Tag Rules
 
 For VP-SEC scenarios testing **unauthorized access** (no login, wrong role, direct URL):
-- Use **`@no-auth`** tag — runs without authentication to verify redirect/block.
+- Use the **`@no-auth`** tag — runs without authentication to verify the redirect/block.
 - Do NOT use `@manual` for these — they are automatable.
 
 ```gherkin

package/dist/orchestrator/templates/qa-context.md

@@ -0,0 +1,90 @@
+# Project Context
+
+> Read by the AI before generating test cases for any screen in this project.
+> Fill in what applies — leave sections empty if not relevant.
+> **The more specific you are, the more accurate the generated test cases.**
+
+---
+
+## Project Overview
+
+**Application:**
+<!-- One sentence: what does this app do? -->
+<!-- Example: B2B award nomination platform for enterprise HR teams. -->
+
+**Target users:**
+<!-- Who uses this app and in what context? -->
+<!-- Example: HR managers submit nominations; employees view results. -->
+
+**Domain notes:**
+<!-- Key terminology, conventions, or constraints the AI should know. -->
+<!-- Example: "Nomination = an award record. Once submitted, status cannot revert to Draft." -->
+<!-- Example: "All monetary values are in JPY. No decimal places." -->
+
+---
+
+## Auth Roles
+
+> The AI maps these directly to `@auth:X` tags and generates permission-boundary test scenarios.
+> Leave the table empty (or delete it) if the app has no auth system.
+
+| Role | Can do | Cannot do |
+|------|--------|-----------|
+| | | |
+
+<!--
+Example:
+| Role    | Can do                                      | Cannot do                            |
+|---------|---------------------------------------------|--------------------------------------|
+| admin   | All CRUD, manage users, configure settings  | Nothing blocked                      |
+| manager | Create/edit records, view reports           | Delete records, manage users         |
+| staff   | View and submit own records only            | Edit others' records, view reports   |
+-->
+
+---
+
+## Testing Strategy
+
+**Focus areas** — what to cover thoroughly:
+<!-- List from: functional, security, ui, accessibility, performance -->
+<!-- Example: functional, security -->
+
+**Mandatory coverage:**
+<!-- Rules that override the AI's default tier decisions for every screen. -->
+<!-- Example: "Every screen with admin-only actions MUST have a non-admin blocked-access scenario." -->
+<!-- Example: "All free-text inputs MUST have XSS + SQL injection scenarios regardless of screen risk level." -->
+
+**Deprioritize / skip:**
+<!-- What to move to @low or skip entirely for this project. -->
+<!-- Example: "Skip VP-UI cosmetic checks (label/placeholder presence) — handled separately by design review." -->
+<!-- Example: "Skip accessibility scenarios — separate audit planned." -->
+
+---
+
+## Global Business Rules
+
+> Rules that apply across multiple screens.
+> The AI adds these to the Coverage Map for every screen as `[G]`-tagged Business rules.
+> Screen-specific rules belong in `requirements/spec.md`, not here.
+
+<!-- - Soft-delete only: records are never hard-deleted, only marked inactive -->
+<!-- - All timestamps stored in UTC, displayed in UTC+7 -->
+<!-- - Pagination default: 20 items per page; max 100 -->
+<!-- - File uploads: PNG/JPG/PDF only, max 5 MB -->
+<!-- - After any write operation, the list view must refresh automatically -->
+
+---
+
+## Error Message Patterns
+
+> If your app follows consistent validation error formats, list them here.
+> The AI uses these to fill `test-data.yaml` error keys when `spec.md` doesn't specify exact text.
+> Leave empty to let the AI infer from spec.md.
+
+- Required field: `<!-- "This field is required" -->`
+- Max length: `<!-- "Must be X characters or less" -->`
+- Min length: `<!-- "Must be at least X characters" -->`
+- Invalid format: `<!-- "Invalid format" -->`
+- Unique constraint: `<!-- "Already exists" -->`
+- Not found: `<!-- "Not found" -->`
+- Unauthorized: `<!-- "You do not have permission to perform this action" -->`

package/dist/orchestrator/templates/readme.md

@@ -12,14 +12,16 @@ sungen generate → compiles Gherkin + selectors + data → Playwright .spec.ts
 ## Directory Structure
 
 ```
-├── qa/screens/<name>/
-│   ├── features/         # .feature files (Gherkin)
-│   ├── selectors/        # Element locator YAML mappings
-│   ├── test-data/        # Test data YAML values
-│   └── requirements/     # Screen specs, UI designs, notes
-│       ├── spec.md       # Structured screen specification
-│       ├── ui/           # Screenshots, mockups, design images
-│       └── test-viewpoint.md      # Edge cases, decisions (optional)
+├── qa/
+│   ├── context.md        # Project-wide context: roles, testing strategy, global rules (fill once)
+│   ├── screens/<name>/
+│   │   ├── features/         # .feature files (Gherkin)
+│   │   ├── selectors/        # Element locator YAML mappings
+│   │   ├── test-data/        # Test data YAML values
+│   │   └── requirements/     # Screen specs, UI designs, notes
+│   │       ├── spec.md       # Structured screen specification
+│   │       ├── ui/           # Screenshots, mockups, design images
+│   │       └── test-viewpoint.md      # Edge cases, decisions (optional)
 ├── specs/
 │   └── generated/        # Auto-generated Playwright tests
 ├── .claude/
@@ -66,11 +68,12 @@ Scaffolds `qa/screens/<name>/` with empty feature, selectors, test-data, and req
 | `/sungen:create-test login` | `/sungen-create-test login` |
 
 AI acts as a **Senior QA Engineer**:
-1. Reads `requirements/spec.md` for screen specs (fields, validation, business rules, states)
-2. Optionally explores the live page via Playwright MCP to verify and supplement
-3. Identifies screen sections → asks user which to focus on
-4. Generates **20+ scenarios per viewpoint** (UI/UX, Validation, Logic, Security) for each section
-5. Confirms test plan before generating `.feature` + `test-data.yaml`
+1. Reads `qa/context.md` for project-wide context (roles, testing strategy, global rules)
+2. Reads `requirements/spec.md` for screen specs (fields, validation, business rules, states)
+3. Optionally explores the live page via Playwright MCP to verify and supplement
+4. Identifies screen sections → asks user which to focus on
+5. Generates **20+ scenarios per viewpoint** (UI/UX, Validation, Logic, Security) for each section
+6. Confirms test plan before generating `.feature` + `test-data.yaml`
 
 ### Step 3: Compile & run tests
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sun-asterisk/sungen",
-  "version": "2.6.15",
+  "version": "2.7.0-beta.1",
   "description": "Deterministic E2E Test Compiler - Gherkin + Selectors → Playwright tests",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -65,6 +65,14 @@
   "peerDependencies": {
     "@playwright/test": "^1.57.0"
   },
+  "overrides": {
+    "brace-expansion": "^5.0.6",
+    "uuid": "^11.1.1"
+  },
+  "resolutions": {
+    "brace-expansion": "^5.0.6",
+    "uuid": "^11.1.1"
+  },
   "files": [
     "dist",
     "bin",

package/src/cli/index.ts

@@ -15,13 +15,16 @@ import { registerFigmaCommand } from './commands/figma';
 import { registerAddFlowCommand } from './commands/add-flow';
 import { registerDashboardCommand } from './commands/dashboard';
 
+// Read version from package.json so `--version` never drifts from the released version.
+const { version } = require('../../package.json') as { version: string };
+
 async function main() {
   const program = new Command();
 
   program
     .name('sungen')
     .description('Deterministic E2E Test Compiler — Gherkin + Selectors → Playwright')
-    .version('2.6.15');
+    .version(version);
 
   // Global options
   program

package/src/exporters/feature-parser.ts

@@ -178,13 +178,21 @@ export function mapVpToCategory2(vpId: string | undefined, scenarioName?: string
 }
 
 /**
- * Generate TC ID: keep VP ID exactly as written (e.g. VP-UI-001) when present,
- * or fall back to <SCREEN_UPPER>-<NNN> for scenarios without a VP ID.
+ * Generate TC ID, namespaced by screen/flow so it is globally unique across the
+ * whole project. This matters because the dashboard tracks each test case by its
+ * tcId — without a namespace, `VP-SEC-001` collides across screens (every screen
+ * starts its VP numbering at 001) and one screen's results overwrite another's.
+ *
+ *   - With VP ID:    VP-SEC-001 + screen "login" → "LOGIN-SEC-001" (strip leading "VP-")
+ *   - Without VP ID: "LOGIN-001" via the fallback index
+ *
+ * The scenario title in the .feature still keeps the bare `VP-SEC-001` (human-facing).
  */
 export function generateTcId(screen: string, vpId: string | undefined, fallbackIndex: number): string {
+  const screenUpper = screen.toUpperCase().replace(/[^A-Z0-9]/g, '-');
   if (vpId) {
-    return vpId;
+    const vpCore = vpId.replace(/^VP-/, '');
+    return `${screenUpper}-${vpCore}`;
   }
-  const screenUpper = screen.toUpperCase().replace(/[^A-Z0-9]/g, '-');
   return `${screenUpper}-${String(fallbackIndex).padStart(3, '0')}`;
 }

package/src/orchestrator/ai-rules-updater.ts

@@ -43,6 +43,11 @@ export const AI_RULES_FILE_MAPPING: [string, string][] = [
   ['claude-skill-selector-fix.md', '.claude/skills/sungen-selector-fix/SKILL.md'],
   ['claude-skill-tc-review.md', '.claude/skills/sungen-tc-review/SKILL.md'],
   ['claude-skill-viewpoint.md', '.claude/skills/sungen-viewpoint/SKILL.md'],
+  ['claude-skill-viewpoint-group-a-data-entry.md', '.claude/skills/sungen-viewpoint/group-a-data-entry.md'],
+  ['claude-skill-viewpoint-group-b-data-ops.md', '.claude/skills/sungen-viewpoint/group-b-data-ops.md'],
+  ['claude-skill-viewpoint-group-c-data-explore.md', '.claude/skills/sungen-viewpoint/group-c-data-explore.md'],
+  ['claude-skill-viewpoint-group-d-display.md', '.claude/skills/sungen-viewpoint/group-d-display.md'],
+  ['claude-skill-viewpoint-group-e-identity.md', '.claude/skills/sungen-viewpoint/group-e-identity.md'],
   ['claude-skill-delivery.md', '.claude/skills/sungen-delivery/SKILL.md'],
   ['claude-skill-dashboard.md', '.claude/skills/sungen-dashboard/SKILL.md'],
   ['claude-skill-capture-figma.md', '.claude/skills/sungen-capture-figma/SKILL.md'],
@@ -63,6 +68,11 @@ export const AI_RULES_FILE_MAPPING: [string, string][] = [
   ['github-skill-sungen-selector-fix.md', '.github/skills/sungen-selector-fix/SKILL.md'],
   ['github-skill-sungen-tc-review.md', '.github/skills/sungen-tc-review/SKILL.md'],
   ['github-skill-sungen-viewpoint.md', '.github/skills/sungen-viewpoint/SKILL.md'],
+  ['github-skill-sungen-viewpoint-group-a-data-entry.md', '.github/skills/sungen-viewpoint/group-a-data-entry.md'],
+  ['github-skill-sungen-viewpoint-group-b-data-ops.md', '.github/skills/sungen-viewpoint/group-b-data-ops.md'],
+  ['github-skill-sungen-viewpoint-group-c-data-explore.md', '.github/skills/sungen-viewpoint/group-c-data-explore.md'],
+  ['github-skill-sungen-viewpoint-group-d-display.md', '.github/skills/sungen-viewpoint/group-d-display.md'],
+  ['github-skill-sungen-viewpoint-group-e-identity.md', '.github/skills/sungen-viewpoint/group-e-identity.md'],
   ['github-skill-sungen-delivery.md', '.github/skills/sungen-delivery/SKILL.md'],
   ['github-skill-sungen-dashboard.md', '.github/skills/sungen-dashboard/SKILL.md'],
   ['github-skill-sungen-capture-figma.md', '.github/skills/sungen-capture-figma/SKILL.md'],

package/src/orchestrator/project-initializer.ts

@@ -39,6 +39,9 @@ export class ProjectInitializer {
     // Create directories
     this.createDirectories();
 
+    // Create qa/context.md for QA lead to fill project-wide context
+    this.createContext();
+
     // Ensure package.json and install Playwright
     await this.setupDependencies();
 
@@ -363,6 +366,23 @@ export class ProjectInitializer {
 
   }
 
+  /**
+   * Create qa/context.md for the QA lead to fill project-wide context
+   * (roles, testing strategy, global rules, error patterns).
+   */
+  private createContext(): void {
+    const contextPath = path.join(this.cwd, 'qa', 'context.md');
+
+    if (fs.existsSync(contextPath)) {
+      this.skippedItems.push('qa/context.md');
+      return;
+    }
+
+    const content = this.readTemplate('qa-context.md');
+    fs.writeFileSync(contextPath, content, 'utf-8');
+    this.createdItems.push('qa/context.md');
+  }
+
   /**
    * Create specs/base.ts for shared browser context
    */

package/src/orchestrator/templates/ai-instructions/claude-cmd-create-test.md

@@ -32,7 +32,15 @@ Parse **name** from `$ARGUMENTS`. If missing, ask the user.
    - If no → fresh creation. Use `AskUserQuestion` to ask generation scope:
      - **Tier 1 — Critical & High priority** — ~10-15 scenarios/section covering happy paths, core validation, security basics **(Recommended)**
      - **Full coverage — All tiers at once** — generates Tier 1 + 2 + 3 in one run. Large output (~40-60 scenarios/section), best for experienced users who want complete coverage immediately
-3. **Read requirements & resolve visual source** — check `qa/<screens|flows>/<name>/requirements/`:
+3. **Read project context + screen requirements**
+
+   **Project context** — check `qa/context.md` (project root, not screen-specific):
+   - If exists → read it. Extract: roles, testing strategy directives, global business rules, error patterns.
+   - Summarize what you found in one line (e.g. `"Roles: admin/staff/user | Strategy: focus security, skip VP-UI T1 | 2 global rules"`).
+   - These are carried into the Coverage Map when invoking `sungen-tc-generation`.
+   - If absent → continue without it, no action needed.
+
+   **Screen requirements** — check `qa/<screens|flows>/<name>/requirements/`:
    - If `spec.md` exists → read it as PRIMARY source (sections, fields, validation rules, business rules, states).
    - If `test-viewpoint.md` exists → read it. If it only contains HTML comments (scaffold template), use `AskUserQuestion` to ask:
      - **Fill test-viewpoint.md first** — I'll help you identify edge cases, known issues, and design decisions for this screen before generating tests