@sun-asterisk/sungen 2.5.2 → 2.6.1

package/src/orchestrator/templates/ai-instructions/claude-cmd-add-flow.md

@@ -0,0 +1,88 @@
+---
+name: add-flow
+description: 'Add a new Sungen flow — scaffolds directories for E2E cross-screen testing, helps fill spec.md, and can capture visuals via the capture skills'
+argument-hint: [flow-name] [--path <start-url>]
+allowed-tools: Read, Grep, Bash, Glob, Edit, Write, AskUserQuestion, mcp__playwright__browser_navigate, mcp__playwright__browser_take_screenshot, mcp__playwright__browser_snapshot, mcp__figma__get_design_context, mcp__figma__get_variable_defs, mcp__figma__get_screenshot
+---
+
+You are adding a new Sungen flow for E2E cross-screen test generation.
+
+## Parameters
+
+Parse from `$ARGUMENTS`:
+- **flow** — flow name (e.g., `award-submission`, `user-onboarding`)
+- **--path \<url\>** — starting page URL path (default: `/login`)
+- **--description \<text\>** — flow description (optional)
+
+If **flow** is missing, ask: "What is the flow name? (e.g., `award-submission`, `user-onboarding`)"
+If **path** is missing, ask: "What is the starting URL path? (e.g., `/login`)"
+
+## Steps
+
+### 1. Scaffold the flow
+
+```bash
+sungen add-flow --flow <name> --path <path>
+```
+
+This creates:
+```
+qa/flows/<name>/
+├── features/<name>.feature        # Gherkin with @flow tag, Background, sample scenarios
+├── selectors/<name>.yaml          # Namespaced keys: "login:submit", "awards:submit"
+├── test-data/<name>.yaml          # Namespaced data: login.email, submission.nominee
+└── requirements/
+    ├── spec.md                    # Flow specification
+    └── ui/                        # Screenshots, mockups
+```
+
+### 1a. Identify the screens in the flow
+
+Ask the user: "Which screens does this flow visit, in order? (e.g., login → dashboard → award-form → confirmation)"
+
+Record the screen list — you will need it for:
+- Filling `spec.md` (Step 3)
+- Suggesting `[Screen:Element]` namespace prefixes
+- Capturing visuals per screen (Step 2)
+
+### 2. Capture visual source
+
+Use `AskUserQuestion`: *"Pick a visual source for this flow's screens:"*
+- **Figma designs** (Recommended for pre-launch) — invoke `sungen-capture-figma` skill for each screen
+- **Live page scan** (dev/staging is up) — invoke `sungen-capture-live` skill for each screen URL
+- **Local images** — invoke `sungen-capture-local` skill to load from `requirements/ui/`
+- **Skip** — user will drop images manually into `requirements/ui/` later
+
+Each capture skill writes outputs into `qa/flows/<name>/requirements/ui/` and reports back a summary. Do not inline capture logic here — always delegate to the skill so behavior stays consistent with `/sungen:create-test`.
+
+### 3. Fill spec.md
+
+Use `AskUserQuestion`: *"Fill `spec.md` now? (You can reference the captured visuals)"* — offer **Yes, fill now (Recommended)** / **Skip, fill later**.
+
+If yes → open `qa/flows/<name>/requirements/spec.md` and help the user fill:
+- **Screens list** — ordered list of screens with URL paths
+- **Flow steps** — what the user does at each screen
+- **Transitions** — what triggers navigation between screens
+- **Business rules** — cross-screen validation, state that persists
+- **Test data** — what data is entered at each screen
+
+Reference the captured visuals from Step 2 to suggest field names, form elements, and UI states.
+
+### 4. Next steps
+
+Tell the user what was created, then use `AskUserQuestion` to offer next steps:
+
+- **`/sungen:create-test <name>`** — Create test scenarios for the flow (Recommended)
+- **Done for now** — I'll come back later
+
+If user picks `/sungen:create-test`, **you MUST use the Skill tool** to invoke it. Do NOT generate test cases yourself — the skill auto-loads `sungen-gherkin-syntax` and `sungen-tc-generation`.
+
+## Key Rules
+
+- Flows are **independent** from screens — own selectors, own test-data
+- Selectors use `[Screen:Element]` namespace format with colon
+- YAML keys must be **quoted** due to colon: `"login:submit":`
+- Test data namespaced by phase: `login.email`, `submission.nominee`
+- `@flow` tag required at feature level
+- `Background:` should only contain the starting page navigation
+- Each scenario = one phase of the journey

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

@@ -19,13 +19,16 @@ You are a **Senior QA Engineer** specialized in test case design. You structure
 
 ## Parameters
 
-Parse **screen** from `$ARGUMENTS`. If missing, ask the user.
+Parse **name** from `$ARGUMENTS`. If missing, ask the user.
+
+**Auto-detect context**: check if `qa/flows/<name>/` exists → flow mode. Else check `qa/screens/<name>/` → screen mode. This determines paths, generation strategy, and CLI commands.
 
 ## Steps
 
-1. Verify `qa/screens/<screen>/` exists. If not → `/sungen:add-screen` first.
+1. **Flow**: Verify `qa/flows/<name>/` exists. If not → `/sungen:add-flow` first.
+   **Screen**: Verify `qa/screens/<name>/` exists. If not → `/sungen:add-screen` first.
 2. Check if `.feature` file already has scenarios. If yes → use `AskUserQuestion` to ask the update mode (see `sungen-tc-generation` skill for details). If no → fresh creation.
-3. **Read requirements & resolve visual source** — check `qa/screens/<screen>/requirements/`:
+3. **Read requirements & resolve visual source** — 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
@@ -44,13 +47,13 @@ Parse **screen** from `$ARGUMENTS`. If missing, ask the user.
 
    Summarize what you found in requirements and present to the user.
 
-4. Follow the `sungen-tc-generation` skill for section identification, viewpoint generation, and output format. When requirements exist, use the "Requirements-Driven Generation" strategy.
-5. Generate or update `.feature` + `test-data.yaml` following `sungen-gherkin-syntax` and `sungen-tc-generation` skills.
+4. Follow the `sungen-tc-generation` skill for section identification, viewpoint generation, and output format. **For flows**, use the "Flow Test Generation" section in the skill. When requirements exist, use the "Requirements-Driven Generation" strategy.
+5. Generate or update `.feature` + `test-data.yaml` following `sungen-gherkin-syntax` and `sungen-tc-generation` skills. **For flows**: use `[Screen:Element]` namespace format, namespace test-data by phase, add `@flow` tag.
 6. Show summary, then use `AskUserQuestion` to offer next steps:
 
-- **`/sungen:review <screen>`** — Review syntax, coverage, viewpoint quality (Recommended)
-- **`/sungen:run-test <screen>`** — Skip review, generate selectors and run tests now
-- **`/sungen:create-test <screen>`** — Expand coverage: add @normal + @low scenarios
+- **`/sungen:review <name>`** — Review syntax, coverage, viewpoint quality (Recommended)
+- **`/sungen:run-test <name>`** — Skip review, generate selectors and run tests now
+- **`/sungen:create-test <name>`** — Expand coverage: add @normal + @low scenarios
 - **Done for now** — I'll come back later
 
 **No selectors.yaml** — selectors are generated during `/sungen:run-test`.

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

@@ -11,17 +11,19 @@ You are a **Senior QA Reviewer**. You evaluate Gherkin test cases using the `sun
 
 ## Parameters
 
-Parse **screen** from `$ARGUMENTS`. If missing, ask the user.
+Parse **name** from `$ARGUMENTS`. If missing, ask the user.
+
+**Auto-detect context**: check if `qa/flows/<name>/` exists → flow mode (base path: `qa/flows/<name>/`). Else check `qa/screens/<name>/` → screen mode (base path: `qa/screens/<name>/`).
 
 ## Steps
 
-1. Read `qa/screens/<screen>/features/<screen>.feature` and `qa/screens/<screen>/test-data/<screen>.yaml`. If missing → `/sungen:create-test` first.
-2. Follow the `sungen-tc-review` skill — score 3 dimensions: Syntax (30pts), Coverage (40pts), Viewpoint (30pts). Use `sungen-viewpoint` for pattern checklists.
-3. **Unverified Selectors check** — if `qa/screens/<screen>/selectors/<screen>.yaml` exists, count lines matching `@needs-live-verify`. Include in the review report as a non-scoring metric (see `sungen-tc-review` skill for report format). Does NOT affect the 60% threshold.
+1. Read `<base>/<name>/features/<name>.feature` and `<base>/<name>/test-data/<name>.yaml`. If missing → `/sungen:create-test` first.
+2. Follow the `sungen-tc-review` skill — score 3 dimensions: Syntax (30pts), Coverage (40pts), Viewpoint (30pts). **For flows**, also apply the "Flow Review Additions" section. Use `sungen-viewpoint` for pattern checklists.
+3. **Unverified Selectors check** — if `<base>/<name>/selectors/<name>.yaml` exists, count lines matching `@needs-live-verify`. Include in the review report as a non-scoring metric. Does NOT affect the 60% threshold.
 4. Output review report per `sungen-tc-review` format. **>= 60%**: PASS. **< 60%**: FAIL with recommendations.
 5. If FAIL and user confirms → update test cases following `sungen-gherkin-syntax` and `sungen-tc-generation` skills, then re-review.
 6. After PASS (or user decides to proceed), use `AskUserQuestion` to offer next steps:
 
-- **`/sungen:run-test <screen>`** — Generate selectors, compile, and run tests (Recommended)
-- **`/sungen:create-test <screen>`** — Add more test cases before running
+- **`/sungen:run-test <name>`** — Generate selectors, compile, and run tests (Recommended)
+- **`/sungen:create-test <name>`** — Add more test cases before running
 - **Done for now** — I'll come back later

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

@@ -11,11 +11,13 @@ You are a **Senior Developer**. Use `sungen-selector-fix`, `sungen-selector-keys
 
 ## Parameters
 
-Parse **screen** from `$ARGUMENTS`. If missing, ask the user.
+Parse **name** from `$ARGUMENTS`. If missing, ask the user.
+
+**Auto-detect context**: check if `qa/flows/<name>/` exists → flow mode (base path: `qa/flows/<name>/`). Else check `qa/screens/<name>/` → screen mode (base path: `qa/screens/<name>/`).
 
 ## Pre-run (phased — per `sungen-selector-fix` skill)
 
-1. Verify `qa/screens/<screen>/` has `.feature` + `test-data.yaml`.
+1. Verify `<base>/<name>/` has `.feature` + `test-data.yaml`.
 2. **Phase 0 — Selector Pre-gen**: if `selectors.yaml` is missing/empty or doesn't cover the feature file's `[Reference]`s, apply the following decision tree before running Phase 0 from `sungen-selector-fix`:
 
    ```
@@ -29,14 +31,14 @@ Parse **screen** from `$ARGUMENTS`. If missing, ask the user.
                    2. Apply selector heuristics from sungen-figma-source skill (testid > role+name > placeholder > label > locator > text)
                    3. Write selectors.yaml — every provisional entry gets this comment on the line above:
                           # @needs-live-verify source=figma node_id=<id>
-                   4. Compile: sungen generate --screen <screen> — must succeed
+                   4. Compile: Screen: sungen generate --screen <name>. Flow: sungen generate --flow <name> — must succeed
                    5. Phase 1 smoke check runs; tests using unverified selectors may fail
                       → auto-fix triggers on next run-test invocation when a live page is available
              NO  → hard stop: print the following message and stop:
                    "Cannot generate selectors: no live page URL and no spec_figma.md found.
                     Options:
                     • Provide the live URL so Playwright MCP can snapshot the page, OR
-                    • Run: sungen add --screen <screen> --figma <figma-url>  to generate spec_figma.md first"
+                    • Run: sungen add --screen <name> --figma <figma-url>  to generate spec_figma.md first"
    ```
 
    **Auto-fix on subsequent runs**: when `run-test` is invoked again with a reachable live page, Phase 0 compares the DOM snapshot against existing `selectors.yaml` entries. Entries tagged `# @needs-live-verify` are treated as candidates — if the actual selector differs, the entry is replaced and the comment removed (entry becomes verified). Entries that already match are also promoted to verified (comment removed).
@@ -50,7 +52,7 @@ Parse **screen** from `$ARGUMENTS`. If missing, ask the user.
      name: "Submit"
    ```
 3. **Phase 0.5 — Auth Persistence**: if the feature has `@auth:<role>` tags and `specs/.auth/<role>.json` is missing/expired, run Phase 0.5 from `sungen-selector-fix` — user logs in manually in MCP browser → `browser_storage_state` → `specs/.auth/<role>.json`. Offer `sungen makeauth <role>` as CLI fallback only if `browser_storage_state` isn't available in this MCP version.
-4. Compile: `sungen generate --screen <screen>` (default: runtime data loading from YAML). Use `--inline-data` only if user requests compile-time hardcoded values.
+4. Compile: **Screen**: `sungen generate --screen <name>`. **Flow**: `sungen generate --flow <name>`. Default: runtime data loading from YAML. Use `--inline-data` only if user requests compile-time hardcoded values.
 
 ## Run & Fix (phased — per `sungen-selector-fix` skill)
 
@@ -61,15 +63,17 @@ Parse **screen** from `$ARGUMENTS`. If missing, ask the user.
 
 ## Playwright command guidelines
 
-**Per-screen JSON results** — each run must write its JSON report to a dedicated path co-located with the `.spec.ts`, so `sungen delivery` can read the correct results per screen:
+**Per-screen/flow JSON results** — each run must write its JSON report to a dedicated path co-located with the `.spec.ts`, so `sungen delivery` can read the correct results:
 
 ```bash
-# ✅ Correct — per-screen output file via env var
-PLAYWRIGHT_JSON_OUTPUT_NAME=specs/generated/<screen>/<screen>-test-result.json \
-  npx playwright test specs/generated/<screen>/<screen>.spec.ts
-```
+# ✅ Screen
+PLAYWRIGHT_JSON_OUTPUT_NAME=specs/generated/<name>/<name>-test-result.json \
+  npx playwright test specs/generated/<name>/<name>.spec.ts
 
-Output: `specs/generated/<screen>/<screen>-test-result.json`
+# ✅ Flow
+PLAYWRIGHT_JSON_OUTPUT_NAME=specs/generated/flows/<name>/<name>-test-result.json \
+  npx playwright test specs/generated/flows/<name>/<name>.spec.ts
+```
 
 **DO NOT** pass `--reporter=...` flag — it overrides the reporters from `playwright.config.ts` and disables the JSON reporter that `sungen delivery` depends on.
 

package/src/orchestrator/templates/ai-instructions/claude-config.md

@@ -21,22 +21,28 @@ You generate 3 files for sungen — a Gherkin compiler that produces Playwright
 | `sungen-capture-live` | Capture a live running page via Playwright MCP (snapshot + screenshot) |
 | `sungen-figma-source` | Figma URL → spec_figma.md + ui/*.png + provisional selectors |
 
-## Workflow (5 AI commands)
+## Workflow (6 AI commands)
 
 | Command | What it does |
 |---|---|
 | `/sungen:add-screen <name> <path>` | Scaffold `qa/screens/<name>/` directories |
-| `/sungen:create-test <name>` | Generate `.feature` + `test-data.yaml` (no selectors) |
-| `/sungen:review <name>` | Score syntax, coverage, viewpoint quality (60% threshold) |
-| `/sungen:run-test <name>` | Generate `selectors.yaml` from live page, compile, run, auto-fix |
+| `/sungen:add-flow <name> [--path <url>]` | Scaffold `qa/flows/<name>/` directories for E2E cross-screen testing |
+| `/sungen:create-test <name>` | Generate `.feature` + `test-data.yaml` (auto-detects screen or flow) |
+| `/sungen:review <name>` | Score syntax, coverage, viewpoint quality (auto-detects screen or flow) |
+| `/sungen:run-test <name>` | Generate `selectors.yaml`, compile, run, auto-fix (auto-detects screen or flow) |
 | `/sungen:delivery [name...]` | Export test cases → CSV for QA delivery (all screens if no arg) |
 
-**Order:** add-screen → create-test → review → run-test → delivery.
+**Screen path:** add-screen → create-test → review → run-test → delivery.
+**Flow path:** add-flow → create-test → review → run-test → delivery.
+
+`create-test`, `review`, and `run-test` auto-detect context: if `qa/flows/<name>/` exists → flow mode, else `qa/screens/<name>/` → screen mode.
 
 After each command completes, use `AskUserQuestion` to present the next actions as selectable options. Never just print text — always give clickable choices so the user can continue the workflow seamlessly.
 
 ## File Structure
 
+### Screen (single-screen testing)
+
 ```
 qa/screens/<screen-name>/
 ├── features/<screen>.feature      # Gherkin scenarios
@@ -47,9 +53,27 @@ qa/screens/<screen-name>/
 └── requirements/
     ├── spec.md                    # Screen specification (primary source)
     └── ui/                        # Screenshots, mockups
+```
+
+### Flow (E2E cross-screen testing)
 
-qa/deliverables/<screen>-testcases.csv  # Exported test cases (from /sungen:delivery)
-qa/deliverables/<screen>-testcases.xlsx # Styled workbook for client hand-off
+```
+qa/flows/<flow-name>/
+├── features/<flow>.feature        # Gherkin with @flow tag, [Screen:Element] refs
+├── selectors/<flow>.yaml          # Namespaced keys: "login:submit", "awards:title"
+├── test-data/<flow>.yaml          # Namespaced data: login.email, submission.nominee
+├── test-data/<flow>.staging.yaml      # Environment override (optional)
+├── test-data/<flow>.production.yaml   # Environment override (optional)
+└── requirements/
+    ├── spec.md                    # Flow specification (screens, steps, transitions)
+    └── ui/                        # Screenshots, mockups
+```
+
+Flows are **independent** from screens — own selectors, own test-data. Selectors use colon-namespaced keys (`"login:submit":`) to avoid duplicate element names across screens.
+
+```
+qa/deliverables/<name>-testcases.csv   # Exported test cases (from /sungen:delivery)
+qa/deliverables/<name>-testcases.xlsx  # Styled workbook for client hand-off
 ```
 
 ## Test Data
@@ -61,11 +85,18 @@ qa/deliverables/<screen>-testcases.xlsx # Styled workbook for client hand-off
 ## CLI Commands
 
 ```bash
+# Screen
 sungen add --screen <name> --path <url-path>               # Scaffold screen directories
 sungen add --screen <name> --path <path> --feature <name>   # Scaffold with sub-feature
 sungen generate --screen <name>                              # Compile .feature → .spec.ts (runtime data)
 sungen generate --screen <name> --inline-data                # Compile with hardcoded data (legacy)
-sungen generate --all                                        # Compile all screens
-sungen delivery                                              # Export all screens → CSV + XLSX
-sungen delivery <screen>                                     # Export a single screen
+
+# Flow
+sungen add-flow --flow <name> --path <start-url>            # Scaffold flow directories
+sungen generate --flow <name>                                # Compile flow .feature → .spec.ts
+
+# All
+sungen generate --all                                        # Compile all screens and flows
+sungen delivery                                              # Export all → CSV + XLSX
+sungen delivery <name>                                       # Export a single screen or flow
 ```

package/src/orchestrator/templates/ai-instructions/claude-skill-capture-live.md

@@ -61,6 +61,18 @@ Where `<timestamp>` is `YYYYMMDD-HHMM` in local time (e.g. `live-20260421-1430.p
 
 This gives users a visual record they can reference later without re-scanning.
 
+### 6a. Verify unauthenticated redirect target (flow capture only)
+
+When capturing for a **flow** that includes security scenarios (e.g., "unauthenticated user cannot access X"):
+
+1. Open a **fresh incognito/unauthenticated** browser context (no storage state).
+2. `browser_navigate` to the protected route (e.g., `/dashboard`).
+3. Record the **actual redirect URL** — do NOT assume it goes to `/login`. The app may redirect to `/register`, `/`, or any other route.
+4. Report the redirect target to the caller: *"Unauthenticated access to `/dashboard` redirects to `/register`"*.
+5. The caller must use the **actual redirect URL** in Gherkin assertions (e.g., `Then User is on [Register] page`), never an assumed one.
+
+Skip this step if the flow has no security scenarios or the user explicitly says to skip.
+
 ### 6. Detect discrepancies vs spec
 
 If `spec.md` exists, briefly cross-check the snapshot against spec sections:

package/src/orchestrator/templates/ai-instructions/claude-skill-delivery.md

@@ -6,7 +6,7 @@ user-invocable: false
 
 ## Purpose
 
-Export test cases from Sungen screens to a standardized CSV file (format BM-2-901-13) for QA delivery.
+Export test cases from Sungen screens and flows to a standardized CSV file (format BM-2-901-13) for QA delivery.
 
 **This skill delegates all heavy work to the `sungen delivery` CLI.** The CLI is the single source of truth for parsing logic — do NOT re-parse files in AI. Your role is only to:
 
@@ -19,18 +19,19 @@ Export test cases from Sungen screens to a standardized CSV file (format BM-2-90
 ## Architecture
 
 ```
-User → /sungen:delivery [screen...]
+User → /sungen:delivery [name...]
        │
        ▼
   sungen delivery CLI  (deterministic — no AI tokens)
-  ├─ Scope detection (no-arg = all screens)
-  ├─ Pre-flight source checks per screen
+  ├─ Scope detection (no-arg = all screens + flows)
+  ├─ Auto-detect: qa/flows/<name>/ → flow, qa/screens/<name>/ → screen
+  ├─ Pre-flight source checks per target
   ├─ Parse .feature (metadata)
   ├─ Parse .spec.ts (resolved Playwright code — source of truth)
   ├─ Parse test-data.yaml (resolve {{vars}})
   ├─ Parse test-results/results.json (match test titles)
   ├─ Merge sources + generate CSV rows
-  └─ Write qa/deliverables/<screen>-testcases.csv
+  └─ Write qa/deliverables/<name>-testcases.csv
 ```
 
 Source modules: `src/exporters/*.ts`
@@ -39,18 +40,18 @@ Source modules: `src/exporters/*.ts`
 
 ## Required sources (CLI pre-flight checks these)
 
-| # | Source | Path | Created by |
-|---|--------|------|------------|
-| 1 | Feature file | `qa/screens/<screen>/features/<screen>.feature` | `/sungen:add-screen` + `/sungen:create-test` |
-| 2 | Test data | `qa/screens/<screen>/test-data/<screen>.yaml` | `/sungen:create-test` |
-| 3 | Selectors | `qa/screens/<screen>/selectors/<screen>.yaml` | `/sungen:run-test` |
-| 4 | Compiled spec | `specs/generated/<screen>/<screen>.spec.ts` | `sungen generate` (during `/sungen:run-test`) |
-| 5 | Test results | `specs/generated/<screen>/<screen>-test-result.json` (per-screen) or `test-results/results.json` (global fallback) | `/sungen:run-test` |
+| # | Source | Screen path | Flow path | Created by |
+|---|--------|-------------|-----------|------------|
+| 1 | Feature file | `qa/screens/<name>/features/<name>.feature` | `qa/flows/<name>/features/<name>.feature` | `add-screen`/`add-flow` + `create-test` |
+| 2 | Test data | `qa/screens/<name>/test-data/<name>.yaml` | `qa/flows/<name>/test-data/<name>.yaml` | `create-test` |
+| 3 | Selectors | `qa/screens/<name>/selectors/<name>.yaml` | `qa/flows/<name>/selectors/<name>.yaml` | `run-test` |
+| 4 | Compiled spec | `specs/generated/<name>/<name>.spec.ts` | `specs/generated/flows/<name>/<name>.spec.ts` | `sungen generate` |
+| 5 | Test results | `specs/generated/<name>/<name>-test-result.json` or `test-results/results.json` | `specs/generated/flows/<name>/<name>-test-result.json` or global fallback | `run-test` |
 
 **Sources 1-4 are blocking** — CLI aborts if any is missing.
 **Source 5 is optional** — CSV is still generated but Test Result/Date/Executor/Env columns are empty (all tests show as Pending).
 
-The CLI reads the **per-screen result file first** (co-located with `.spec.ts`), then falls back to the global `test-results/results.json`. Per-screen is preferred because the global file gets OVERWRITTEN each time Playwright runs, losing results from earlier screens.
+The CLI reads the **per-target result file first** (co-located with `.spec.ts`), then falls back to the global `test-results/results.json`. Per-target is preferred because the global file gets OVERWRITTEN each time Playwright runs, losing results from earlier targets.
 
 ---
 
@@ -87,17 +88,17 @@ The CLI reads the **per-screen result file first** (co-located with `.spec.ts`),
 ## CLI command reference
 
 ```bash
-# Export all screens
+# Export all screens and flows
 sungen delivery
 
-# Export specific screens
-sungen delivery kudos awards
+# Export specific targets (auto-detects screen vs flow)
+sungen delivery kudos awards nomination-flow
 
 # Skip pre-flight (CI only)
 sungen delivery --skip-preflight
 
-# Skip screens with blocking misses
+# Skip targets with blocking misses
 sungen delivery --continue-on-missing
 ```
 
-Output: `qa/deliverables/<screen>-testcases.csv` (UTF-8 with BOM)
+Output: `qa/deliverables/<name>-testcases.csv` (UTF-8 with BOM)

package/src/orchestrator/templates/ai-instructions/claude-skill-error-mapping.md

@@ -101,6 +101,18 @@ If `toHaveText` fails on an input → the Gherkin step has wrong target type. Fi
 
 ---
 
+## Flow-Specific Errors
+
+| Error | Diagnosis | Fix |
+|---|---|---|
+| Navigation timeout between screens | Cross-screen transition takes too long or URL mismatch | Add explicit `wait for page` step between screen transitions in `.feature`. Verify target URL path |
+| Selector `"screen:element"` not found | Namespace key missing or wrong format | Ensure colon-namespaced key in `selectors.yaml` is **quoted**: `"login:submit":`. Check screen prefix matches `[Screen:Element]` ref in Gherkin |
+| Test data `screen.key` undefined | Phase namespace mismatch | Verify `test-data.yaml` uses dot-namespaced keys: `login.email`, `submission.nominee`. Keys must match `{{screen.key}}` refs in `.feature` |
+| State lost between screens | Auth/session expired during multi-screen flow | Ensure all screens in the flow share the same `@auth:role` tag. Check if the app invalidates sessions on navigation |
+| Duplicate selector key across screens | Two screens use same element name without namespace | Always use `[Screen:Element]` format in flow `.feature`. Selectors must use `"screen:element":` quoted keys |
+
+---
+
 ## Performance & Infrastructure Errors → Fix in `specs/base.ts`
 
 All generated `.spec.ts` import from `specs/base.ts` — shared context caching, navigation, overlay cleanup. AI **can and should** tune `base.ts` to match the project.

package/src/orchestrator/templates/ai-instructions/claude-skill-gherkin-syntax.md

@@ -120,6 +120,32 @@ Most elements auto-infer from `[Label] type` → `getByRole(type, { name: 'Label
 - Same label, nth occurrence → add `--N` suffix
 - Target Name > 30 chars → shorten to 1–3 meaningful words
 
+## Dynamic Variables (test-data YAML)
+
+Use `{{$var}}` in test-data YAML for values that must be unique per test run. Resolved at **runtime** by `TestDataLoader` — the compiler passes them through unchanged.
+
+| Variable | Example | Output |
+|---|---|---|
+| `{{$timestamp}}` | `"User-{{$timestamp}}"` | `"User-1714000000"` |
+| `{{$uuid}}` | `"{{$uuid}}"` | `"a1b2c3d4-..."` |
+| `{{$random:min:max}}` | `"{{$random:1:100}}"` | `"42"` |
+| `{{$date}}` | `"{{$date}}"` | `"2026-04-24"` |
+| `{{$datetime}}` | `"{{$datetime}}"` | `"2026-04-24T10:30:00.000Z"` |
+
+**Rules:**
+- `$timestamp` and `$uuid` → same value across all keys in one `load()` call (stable within a test file)
+- `$random` → unique per occurrence (each key gets a different random)
+- Resolved once at load time → every `get()` returns the same resolved value
+- Use for CRUD flows to avoid data collision between parallel runs
+
+```yaml
+# test-data/crud-award.yaml
+award:
+  name: "Award-{{$timestamp}}"
+  email: "test+{{$uuid}}@example.com"
+  score: "{{$random:1:100}}"
+```
+
 ## Selectors (priority order)
 
 | type | value | name | use |
@@ -138,27 +164,112 @@ Options: `nth` `exact` `scope` `match` `variant` `frame` `contenteditable` `colu
 
 ## Tags
 
+### Functional tags (affect code generation)
+
 | Tag | Effect |
 |---|---|
-| `@auto` | Standard scenario, ready for automation |
 | `@manual` | Skip in generation |
-| `@smoke` / `@regression` | Test suite grouping |
-| `@critical` | Priority: system unusable if fails (login, auth, core CRUD) |
-| `@high` | Priority: major feature broken (required validation, key business rules) |
-| `@normal` | Priority: degraded experience (UI layout, secondary flows) |
-| `@low` | Priority: minor/cosmetic (tooltips, hover states, empty states) |
 | `@auth:role` | Use auth storage state for role |
 | `@no-auth` | Disable inherited auth |
 | `@steps:name` | Define reusable step block (base scenario) |
 | `@extend:name` | Prepend Given→When from @steps block (skip Then) |
-| `@cleanup:overlay` | Auto-cleanup: dismiss dialogs/overlays after each test (base.ts fixture) |
-| `@cleanup:forms` | Auto-cleanup: clear form fields after each test (base.ts fixture) |
-| `@cleanup:scroll` | Auto-cleanup: scroll to top after each test (base.ts fixture) |
-| `@cleanup:storage` | Auto-cleanup: clear sessionStorage after each test (base.ts fixture) |
+| `@cleanup:overlay` | Auto-cleanup: dismiss dialogs/overlays after each test (cleanupPage) |
+| `@cleanup:forms` | Auto-cleanup: clear form fields after each test (cleanupPage) |
+| `@cleanup:scroll` | Auto-cleanup: scroll to top after each test (cleanupPage) |
+| `@cleanup:storage` | Auto-cleanup: clear sessionStorage after each test (cleanupPage) |
 | `@screenshot:on-failure` | Auto-capture screenshot when test fails (base.ts fixture) |
+| `@parallel` | Opt-out: fresh page per test instead of serial default (for independent scenarios) |
 | `@beforeAll` | Hook: runs once before all tests → `test.beforeAll()` |
 | `@afterEach` | Hook: runs after each test → `test.afterEach()` (custom cleanup) |
 | `@afterAll` | Hook: runs once after all tests → `test.afterAll()` |
+| `@flow` | Mark feature as E2E flow (cross-screen testing) |
+
+### Pass-through tags (filter at runtime via Playwright --grep)
+
+Any tag not listed above passes through to Playwright `{ tag: [...] }`. Feature-level tags inherit to all scenarios.
+
+| Tag | Purpose |
+|---|---|
+| `@smoke` | Quick sanity check — run after every deploy |
+| `@regression` | Full test suite — run nightly or before release |
+| `@critical` | Priority: system unusable if fails (login, auth, core CRUD) |
+| `@high` | Priority: major feature broken (required validation, key business rules) |
+| `@normal` | Priority: degraded experience (UI layout, secondary flows) |
+| `@low` | Priority: minor/cosmetic (tooltips, hover states, empty states) |
+| `@auto` | Standard scenario, ready for automation |
+| Any custom | e.g., `@sprint-42`, `@team-payment` — any tag works |
+
+**Run filtered:**
+```bash
+npx playwright test --grep "@smoke"          # only smoke tests
+npx playwright test --grep "@critical"       # only critical priority
+npx playwright test --grep "@smoke|@critical" # smoke OR critical
+```
+
+### Serial vs Parallel (test execution mode)
+
+**Default: serial** — `test.describe.serial()` with shared page. Background runs once in `beforeAll`. Fail → skip remaining.
+
+**`@parallel` opt-out** — `test.describe()` with fresh page per test. Background runs as `beforeEach`. Use when scenarios are truly independent (validation rules, permission tests).
+
+| Mode | Generated | Page | Background | On fail |
+|---|---|---|---|---|
+| Serial (default) | `test.describe.serial()` | Shared | `beforeAll` (1 goto) | Skip remaining |
+| `@parallel` | `test.describe()` | Fresh per test | `beforeEach` (N goto) | Continue |
+
+**`@parallel` is required** when a feature has multiple auth groups (e.g., `@auth:user` + `@no-auth` scenarios). Serial mode uses one shared browser context and cannot mix auth roles. The compiler will error if `@parallel` is missing in this case.
+
+### `@flow` tag (E2E cross-screen testing)
+
+`@flow` marks a feature as a **flow** — an E2E journey spanning multiple screens. Flows live in `qa/flows/<name>/` with their own selectors, test-data, and requirements.
+
+**Key differences from screen tests:**
+
+| Aspect | Screen (`qa/screens/`) | Flow (`qa/flows/`) |
+|---|---|---|
+| Scope | Single page | Multiple pages |
+| Selectors | `[Element]` → own YAML | `[Screen:Element]` → own YAML (namespaced) |
+| Test data | `{{variable}}` | `{{phase.variable}}` (namespaced by phase) |
+| Tag | `@auto` / `@smoke` etc. | `@flow` (required at feature level) |
+| Multi-domain | N/A | Absolute URL in selector `path:` skips baseURL |
+
+**Selector namespace format:** `[Screen:Element]` where colon separates screen prefix from element name. The YAML key is `"screen:element"` (quoted, lowercase).
+
+```gherkin
+# Feature file
+When User fill [Login:Email] field with {{login.email}}
+And User click [Login:Submit] button
+Then User see [Dashboard] page
+When User click [Dashboard:Awards] link
+```
+
+```yaml
+# selectors.yaml — keys are namespaced, quoted due to colon
+"login:email":
+  type: 'testid'
+  value: 'email-input'
+
+"login:submit":
+  type: 'role'
+  value: 'button'
+  name: 'Login'
+
+dashboard:
+  type: 'page'
+  value: '/dashboard'
+
+"dashboard:awards":
+  type: 'role'
+  value: 'link'
+  name: 'Awards'
+```
+
+**Flow structure:**
+- `Background:` — set starting page only (e.g., `Given User is on [Login] page`)
+- Each `Scenario:` — one phase/step of the flow (login, navigate, submit, etc.)
+- Page navigation between scenarios uses `[Screen] page` references
+
+**CLI:** `sungen add-flow --flow <name>`, `sungen generate --flow <name>`, `sungen generate --all` (includes flows)
 
 ### @extend behavior
 
@@ -185,6 +296,7 @@ Options: `nth` `exact` `scope` `match` `variant` `frame` `contenteditable` `colu
 | Missing target type | `fill [email] with {{v}}` | `fill [email] field with {{v}}` |
 | Background with scope | `Background: ... And User is on [X] dialog` | Use `@steps` + `@extend` for scope-dependent flows |
 | `is on` after When | `When ... And User is on [X] dialog` | `And User see [X] dialog` or separate Given |
+| Literal URL navigate | `User navigate to "/dashboard"` | `User is on [Dashboard] page` (add page selector in `selectors.yaml`) |
 
 ## Background vs @steps/@extend