@relipa/ai-flow-kit 0.1.3 → 0.1.4-beta.0

package/custom/templates/shared/gate-workflow.md

@@ -18,6 +18,8 @@ Read `.aiflow/context/current.json` → check the `taskType` field:
 | `testing` | **[TESTER] 4-Gate Testing Workflow** (below) |
 | `execute` | **[EXECUTE] Executing Flow** (below) |
 | `feature`, `bug-fix`, `refactor`, `investigation`, `documentation` | **[DEV] 5-Gate Development Workflow** (below) |
+| `create-spec` | **[BA] 4-Gate Spec Creation Workflow** (below) |
+| `create-testcase` | **[QA] 4-Gate TestCase Creation Workflow** (below) |
 
 If `taskType` is missing or unrecognized, default to the DEV workflow and ask ONE clarifying question.
 
@@ -40,14 +42,20 @@ AI actively reads ticket + source code to understand the requirement:
    - Requirements summary, source code analysis
    - Proposed solution and approach
    - Impact analysis, effort estimate, testing plan
-6. Display "GATE 1: Requirement doc ready" → wait for **APPROVED**
+6. **INVOKE** `gate-review` skill (generate mode) — write `.aiflow/review/gate-1-[ticket-id].md`
+7. Display gate pause message from `gate-review` skill — wait for **APPROVED**
+
+**When APPROVED received:**
+→ **INVOKE** `gate-review` skill (verify mode) — run `ak review check --gate 1 --ticket [ticket-id]`
+→ If passed: run `ak gate 1 approved --ticket [ticket-id]` → proceed to Gate 2
+→ If blocked: follow gate-review skill response protocol
 
 > **Tip:** If auto-start doesn't trigger, the developer can start this gate by typing: **"start"**, **"Gate 1"** or **"Analyze ticket"**.
 
 DO NOT just check format — **understand the content and propose solutions**.
 
 > **Telemetry:** Run `ak gate 1 start --ticket [ticket-id]` when starting this gate (auto-start or when developer types "start"/"Gate 1"). Run as-is — do NOT append shell redirects like `2>$null` or `>/dev/null`.
-> Run `ak gate 1 approved --ticket [ticket-id]` immediately when APPROVED is received. Run as-is — do NOT append shell redirects.
+> Run `ak gate 1 approved --ticket [ticket-id]` after gate-review verify passes (see When APPROVED received block above). Run as-is — do NOT append shell redirects.
 
 ---
 
@@ -57,11 +65,16 @@ DO NOT just check format — **understand the content and propose solutions**.
 
 - Create a detailed TDD implementation plan based on the approved requirement.
 - Output `plan/[ticket-id]/plan.md` with the detailed TDD implementation plan.
-- Display: "GATE 2 PAUSED: type APPROVED to start coding".
-- CODE WILL NOT BE GENERATED until "APPROVED" is received.
+- **INVOKE** `gate-review` skill (generate mode) — write `.aiflow/review/gate-2-[ticket-id].md`
+- Display gate pause message from `gate-review` skill — CODE WILL NOT BE GENERATED until all items checked and APPROVED received.
+
+**When APPROVED received:**
+→ **INVOKE** `gate-review` skill (verify mode) — run `ak review check --gate 2 --ticket [ticket-id]`
+→ If passed: run `ak gate 2 approved --ticket [ticket-id]` → proceed to Gate 3
+→ If blocked: follow gate-review skill response protocol
 
 > **Telemetry:** Run `ak gate 2 start --ticket [ticket-id]` when starting this gate. Run as-is — do NOT append shell redirects.
-> Run `ak gate 2 approved --ticket [ticket-id]` immediately when APPROVED is received. Run as-is — do NOT append shell redirects.
+> Run `ak gate 2 approved --ticket [ticket-id]` after gate-review verify passes (see When APPROVED received block above). Run as-is — do NOT append shell redirects.
 
 ---
 
@@ -88,12 +101,21 @@ Mandatory order:
 3. Tick `custom/rules/review-checklist.md`
 4. Create `plan/[ticket-id]/summary.md`
 
-Then: "GATE 4 PAUSED: type APPROVED or BUG: [description]"
-- Coding bug -> fix -> repeat Gate 4.
-- Requirement bug -> return to Gate 1.
+Then:
+- **INVOKE** `gate-review` skill (generate mode) — write `.aiflow/review/gate-4-[ticket-id].md`
+- Display gate pause message from `gate-review` skill. Also accepts `BUG: [description]` (bypasses review check — goes directly to fix cycle).
+
+**When APPROVED received:**
+→ **INVOKE** `gate-review` skill (verify mode) — run `ak review check --gate 4 --ticket [ticket-id]`
+→ If passed: run `ak gate 4 approved --ticket [ticket-id]` → proceed to Gate 5
+→ If blocked: follow gate-review skill response protocol
+
+**When BUG: [description] received (no review check needed):**
+- Coding bug → fix → repeat Gate 4 (re-generate review file)
+- Requirement bug → return to Gate 1
 
 > **Telemetry:** Run `ak gate 4 start --ticket [ticket-id]` when starting this gate. Run as-is — do NOT append shell redirects.
-> Run `ak gate 4 approved --ticket [ticket-id]` immediately when APPROVED is received. Run as-is — do NOT append shell redirects.
+> Run `ak gate 4 approved --ticket [ticket-id]` after gate-review verify passes (see When APPROVED received block above). Run as-is — do NOT append shell redirects.
 
 ---
 
@@ -122,18 +144,24 @@ Guide on creating a Pull Request with the ticket link.
 3. Analyze scope, functional flows, non-functional requirements, risks
 4. Ask clarifying questions — **ONE at a time**, wait for reply
 5. Write `test-plan/test-analysis.md`
-6. Display gate pause — wait for **APPROVED**
+6. **INVOKE** `gate-review` skill (generate mode) — write `.aiflow/review/gate-1-[ticket-id].md`
+7. Display gate pause message from `gate-review` skill — wait for **APPROVED**
 
 > **Tip:** TESTER can trigger with: **"start"**, **"Gate 1"** or **"Analyze ticket"**.
 
 ```
 ⏸️ GATE 1: TEST ANALYSIS READY
-→ Review: test-plan/test-analysis.md
+→ Review: [test-plan/test-analysis.md](test-plan/test-analysis.md)
 → Type APPROVED to proceed to Gate 2
 ```
 
+**When APPROVED received:**
+→ **INVOKE** `gate-review` skill (verify mode) — `ak review check --gate 1 --ticket [ticket-id]`
+→ If passed: `ak gate 1 approved --ticket [ticket-id]` → Gate 2
+→ If blocked: follow gate-review skill response protocol
+
 > **Telemetry:** Run `ak gate 1 start --ticket [ticket-id]` when starting this gate. Run as-is — do NOT append shell redirects.
-> Run `ak gate 1 approved --ticket [ticket-id]` immediately when APPROVED is received. Run as-is — do NOT append shell redirects.
+> Run `ak gate 1 approved --ticket [ticket-id]` after gate-review verify passes (see When APPROVED received block above). Run as-is — do NOT append shell redirects.
 
 ---
 
@@ -152,12 +180,19 @@ Only runs after Gate 1 APPROVED.
 - If TESTER declared `PR: <url>` → **INVOKE** `pr-impact-analysis` skill (Dev Artifacts Check) first
 - Generate test scenarios/checklist TABLE covering: Happy Path, Negative, Validation, Boundary, Edge Cases, State Transitions, Role-based, Accessibility, Compatibility, Data Integrity, Integration, Exploratory
 - Save `test-plan/checklist.md`
+- **INVOKE** `gate-review` skill (generate mode) — write `.aiflow/review/gate-2a-[ticket-id].md`
+- Display gate pause message from `gate-review` skill — wait for **APPROVED**
 
 ```
 ⏸️ GATE 2a: SCENARIOS READY
 → Type APPROVED to generate test cases
 ```
 
+**When APPROVED received:**
+→ **INVOKE** `gate-review` skill (verify mode) — `ak review check --gate 2a --ticket [ticket-id]`
+→ If passed: `ak gate 2a approved --ticket [ticket-id]` → Phase 2b
+→ If blocked: follow gate-review skill response protocol
+
 #### Phase 2b — Generate Test Cases
 
 **INVOKE:** `generate-testcase` skill (Phase 2b)
@@ -166,24 +201,38 @@ Only runs after Gate 1 APPROVED.
 - TC_ID format: `TC_[Module]_[NNN]` (e.g. `TC_Login_001`)
 - Expected result ONLY from ticket/spec — never from PR/dev description
 - Save `test-plan/test-cases/`
+- **INVOKE** `gate-review` skill (generate mode) — write `.aiflow/review/gate-2b-[ticket-id].md`
+- Display gate pause message from `gate-review` skill — wait for **APPROVED**
 
 ```
 ⏸️ GATE 2b: TEST CASES READY
 → Type APPROVED to proceed to review
 ```
 
+**When APPROVED received:**
+→ **INVOKE** `gate-review` skill (verify mode) — `ak review check --gate 2b --ticket [ticket-id]`
+→ If passed: `ak gate 2b approved --ticket [ticket-id]` → Phase 2c
+→ If blocked: follow gate-review skill response protocol
+
 #### Phase 2c — Review & Optimize
 
 **INVOKE:** `generate-testcase` skill (Phase 2c)
 
 - Self-review: check duplicates, problematic TCs (vague steps, unmeasurable expected result), missing TCs, coverage gaps, accessibility/compatibility coverage
 - Output `test-plan/review-report.md` with action items
+- **INVOKE** `gate-review` skill (generate mode) — write `.aiflow/review/gate-2c-[ticket-id].md`
+- Display gate pause message from `gate-review` skill — wait for **APPROVED**
 
 ```
 ⏸️ GATE 2c: REVIEW COMPLETE
 → Type APPROVED to finalize and generate scripts
 ```
 
+**When APPROVED received:**
+→ **INVOKE** `gate-review` skill (verify mode) — `ak review check --gate 2c --ticket [ticket-id]`
+→ If passed: `ak gate 2c approved --ticket [ticket-id]` → Phase 2d
+→ If blocked: follow gate-review skill response protocol
+
 #### Phase 2d — Coverage Check & Playwright Scripts
 
 **INVOKE:** `coverage-check` skill
@@ -192,6 +241,8 @@ Only runs after Gate 1 APPROVED.
 - Generate coverage matrix (requirement → TC IDs)
 - Export final test case set to `test-plan/test-cases/final-testcases.md`
 - **INVOKE** `automation-testing` skill → generate Playwright scripts to `test-plan/test-scripts/`
+- **INVOKE** `gate-review` skill (generate mode) — write `.aiflow/review/gate-2d-[ticket-id].md`
+- Display gate pause message from `gate-review` skill — wait for **APPROVED**
 
 ```
 ⏸️ GATE 2: TEST PLAN READY
@@ -201,7 +252,12 @@ Scripts: [N] Playwright specs generated
 → Type APPROVED to proceed to Gate 3 (execution)
 ```
 
-> **Telemetry:** Run `ak gate 2 approved --ticket [ticket-id]` immediately when final APPROVED received. Run as-is — do NOT append shell redirects.
+**When APPROVED received:**
+→ **INVOKE** `gate-review` skill (verify mode) — `ak review check --gate 2d --ticket [ticket-id]`
+→ If passed: `ak gate 2 approved --ticket [ticket-id]` → Gate 3
+→ If blocked: follow gate-review skill response protocol
+
+> **Telemetry:** Run `ak gate 2 approved --ticket [ticket-id]` after gate-review verify passes (see When APPROVED received block above). Run as-is — do NOT append shell redirects.
 
 ---
 
@@ -236,6 +292,9 @@ BASE_URL=<url> npx playwright test --headed
 - Update evidence (create `run-N/` subfolder — never delete prior evidence)
 - Update bug status (RESOLVED / Still OPEN)
 
+**INVOKE** `gate-review` skill (generate mode) — write `.aiflow/review/gate-3-[ticket-id].md` — summarize execution results + bug list
+Display gate pause message from `gate-review` skill — wait for **APPROVED**
+
 ```
 ⏸️ GATE 3: EXECUTION COMPLETE
 Passed: [N] | Failed: [N] | Blocked: [N]
@@ -245,6 +304,11 @@ Bugs: [N Critical] [N High] [N Medium] [N Low]
 → Type PR: [url] to declare new dev PRs
 ```
 
+**When APPROVED received:**
+→ **INVOKE** `gate-review` skill (verify mode) — `ak review check --gate 3 --ticket [ticket-id]`
+→ If passed: `ak gate 3 approved --ticket [ticket-id]` → Gate 4
+→ If blocked: follow gate-review skill response protocol
+
 > **Telemetry:** Run `ak gate 3 start --ticket [ticket-id]` when starting this gate. Run as-is — do NOT append shell redirects.
 
 ---
@@ -261,6 +325,9 @@ Only runs after Gate 3 APPROVED.
 4. Determine Go / No-Go: 0 unresolved Critical = Go
 5. Write `test-plan/test-report.md`
 
+- **INVOKE** `gate-review` skill (generate mode) — write `.aiflow/review/gate-4-[ticket-id].md` — summarize test report + go/no-go decision
+- Display gate pause message from `gate-review` skill. Also accepts `NO-GO: [reason]` (bypasses review check).
+
 ```
 ⏸️ GATE 4: TEST REPORT READY
 Decision: [GO / NO-GO]
@@ -270,8 +337,15 @@ Coverage: [N]% acceptance criteria
 → Type NO-GO: [reason] to reject release
 ```
 
+**When APPROVED received:**
+→ **INVOKE** `gate-review` skill (verify mode) — `ak review check --gate 4 --ticket [ticket-id]`
+→ If passed: `ak gate 4 approved --ticket [ticket-id]` → sign off complete
+→ If blocked: follow gate-review skill response protocol
+
+**When NO-GO: [reason] received (no review check needed):** reject release per reason.
+
 > **Telemetry:** Run `ak gate 4 start --ticket [ticket-id]` when starting this gate. Run as-is — do NOT append shell redirects.
-> Run `ak gate 4 approved --ticket [ticket-id]` immediately when APPROVED received. Run as-is — do NOT append shell redirects.
+> Run `ak gate 4 approved --ticket [ticket-id]` after gate-review verify passes (see When APPROVED received block above). Run as-is — do NOT append shell redirects.
 
 ---
 
@@ -297,15 +371,23 @@ Pre-flight checks (stop and report if any fail):
 
 Then display work plan:
 
+- **INVOKE** `gate-review` skill (generate mode) — write `.aiflow/review/gate-1-[ticket-id].md`
+- Display gate pause message from `gate-review` skill — wait for **APPROVED**
+
 ```
 ⏸️ GATE 1: EXECUTE FLOW READY
-TC file: [path]
+TC file: [path](path)
 Repo: [repo]
 Screen: [ScreenID] — [Screen Name]
 BASE_URL: [url]
 → Type APPROVED to sync scripts (Gate 2)
 ```
 
+**When APPROVED received:**
+→ **INVOKE** `gate-review` skill (verify mode) — `ak review check --gate 1 --ticket [ticket-id]`
+→ If passed: `ak gate 1 approved --ticket [ticket-id]` → Gate 2
+→ If blocked: follow gate-review skill response protocol
+
 > **Telemetry:** Run `ak gate 1 start --ticket [ticket-id]` when starting. Run `ak gate 1 approved --ticket [ticket-id]` when APPROVED.
 
 ---
@@ -324,12 +406,20 @@ Hash-based TC↔script sync — for each TC in the file:
 
 Output: `ak-test/{repo}/scripts/{screenId}/{ScreenID}.spec.ts` (1 file per screen, all TCs inside)
 
+- **INVOKE** `gate-review` skill (generate mode) — write `.aiflow/review/gate-2-[ticket-id].md`
+- Display gate pause message from `gate-review` skill — wait for **APPROVED**
+
 ```
 ⏸️ GATE 2: SCRIPT SYNC COMPLETE
 ✅ New: [N] | 🔄 Updated: [N] | ⏭️ Skipped: [N] | ⚠️ Manual: [N]
 → Type APPROVED to execute (Gate 3)
 ```
 
+**When APPROVED received:**
+→ **INVOKE** `gate-review` skill (verify mode) — `ak review check --gate 2 --ticket [ticket-id]`
+→ If passed: `ak gate 2 approved --ticket [ticket-id]` → Gate 3
+→ If blocked: follow gate-review skill response protocol
+
 ---
 
 ### GATE 3 — Execute & Evidence
@@ -359,6 +449,9 @@ BASE_URL=<url> npx playwright test scripts/{screenId}/{ScreenID}.spec.ts
 - Create new `run-{N}/` — never delete prior runs
 - Update R1/R2 columns
 
+**INVOKE** `gate-review` skill (generate mode) — write `.aiflow/review/gate-3-[ticket-id].md`
+Display gate pause message from `gate-review` skill — wait for **APPROVED**
+
 ```
 ⏸️ GATE 3: EXECUTION COMPLETE
 Run: run-{N} | Passed: [N] | Failed: [N] | Untest: [N] | Pending: [N]
@@ -367,6 +460,11 @@ Run: run-{N} | Passed: [N] | Failed: [N] | Untest: [N] | Pending: [N]
 → Type PR: [url] to declare a dev fix PR
 ```
 
+**When APPROVED received:**
+→ **INVOKE** `gate-review` skill (verify mode) — `ak review check --gate 3 --ticket [ticket-id]`
+→ If passed: `ak gate 3 approved --ticket [ticket-id]` → Gate 4
+→ If blocked: follow gate-review skill response protocol
+
 > **Telemetry:** Run `ak gate 3 start --ticket [ticket-id]` when starting. Run as-is — do NOT append shell redirects.
 
 ---
@@ -384,12 +482,20 @@ Only runs after Gate 3 APPROVED.
 
 Wait for reply before moving to next bug.
 
+- **INVOKE** `gate-review` skill (generate mode) — write `.aiflow/review/gate-4-[ticket-id].md`
+- Display gate pause message from `gate-review` skill — wait for **APPROVED**
+
 ```
 ⏸️ GATE 4: REPORT READY
 Decision: [GO / NO-GO]
 Bugs logged: [N] | Skipped: [N]
-→ Review: ak-test/{repo}/results/{screenId}/run-{N}/testreport.md
+→ Review: [ak-test/{repo}/results/{screenId}/run-{N}/testreport.md](ak-test/{repo}/results/{screenId}/run-{N}/testreport.md)
 → Type APPROVED to sign off
 ```
 
+**When APPROVED received:**
+→ **INVOKE** `gate-review` skill (verify mode) — `ak review check --gate 4 --ticket [ticket-id]`
+→ If passed: `ak gate 4 approved --ticket [ticket-id]` → sign off complete
+→ If blocked: follow gate-review skill response protocol
+
 > **Telemetry:** Run `ak gate 4 start --ticket [ticket-id]` when starting. Run `ak gate 4 approved --ticket [ticket-id]` when APPROVED.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@relipa/ai-flow-kit",
-  "version": "0.1.3",
+  "version": "0.1.4-beta.0",
   "description": "All-in-one AI Flow Kit for team development with Claude AI - skills, templates, and MCP adapters",
   "author": "Example Team",
   "publishConfig": {
@@ -65,4 +65,4 @@
       "<rootDir>/tests/**/*.test.js"
     ]
   }
-}
+}

package/scripts/create-score-excel.js

@@ -164,16 +164,25 @@ function buildRow(email, u) {
   const ticketsStr      = ticketsCompleted.length ? ticketsCompleted.join(', ') : '';
 
   // Notes
+  const onlyExploreCmds = [...rawCmds].every(c => EXPLORE_CMDS.has(c));
   let notes = '';
-  if (score === 0) notes = 'Không có event nào trong tuần';
-  else if (score === 1) notes = 'Chỉ có lệnh khám phá cơ bản (init/update/version/help)';
+  if (score === 0) notes = 'Không có hoạt động';
+  else if (score === 1) notes = 'Chỉ dùng lệnh khám phá';
   else if (score === 2) {
-    if (ticketsStarted.length > 0) notes = `Có gate.start nhưng chưa gate4.approved, ${activeDays} ngày active`;
-    else notes = `${displayCmds.slice(0, 3).join('/')}, ${activeDays} ngày active, chưa dùng gate workflow`;
+    if (ticketsStarted.length > 0)
+      notes = `${ticketsStarted.length} ticket(s) trong tuần; Có gate.start nhưng chưa hoàn thành ticket`;
+    else if (onlyExploreCmds)
+      notes = 'Chỉ dùng lệnh khám phá';
   }
-  else if (score === 3) notes = `Gate workflow bắt đầu, ${ticketsStarted.length} ticket(s), chưa hoàn thành`;
-  else if (score === 4) notes = `${ticketsCompleted.length} ticket hoàn thành (gate4+)`;
-  else if (score === 5) notes = `Gate 3-5 approved, ${ticketsCompleted.length} tickets hoàn thành`;
+  else if (score === 3)
+    notes = `${ticketsStarted.length} ticket(s) trong tuần; Có gate.start nhưng chưa hoàn thành ticket`;
+  else if (score === 4) {
+    notes = `Gate 3-5 approved; ${ticketsCompleted.length} ticket(s) hoàn thành`;
+    if (ticketsStarted.length > ticketsCompleted.length)
+      notes += `; ${ticketsStarted.length} ticket(s) trong tuần`;
+  }
+  else if (score === 5)
+    notes = `Gate 3-5 approved; ${ticketsCompleted.length} ticket(s) hoàn thành; ${ticketsStarted.length} ticket(s) trong tuần`;
 
   return {
     email,
@@ -315,6 +324,7 @@ const CANONICAL_USERS = [
 const LOG_EMAIL_ALIAS = {
   'tructh@relipasoft.com':   'tructth@relipasoft.com',
   'duongnt1@relipasoft.com': 'duongnt@relipasoft.com',
+  'anhtt2@relipasoft.com':   'anhtt@relipasoft.com',
 };
 
 const EMPTY_USER = (email) => ({

package/scripts/init.js

@@ -285,6 +285,37 @@ async function verifySuperpowersSkills(versionDir) {
     }
 }
 
+/**
+ * Install Claude Code custom commands from shared workflow templates.
+ * Creates .claude/commands/<name>.md for each shared workflow template.
+ * Users can invoke these with /<name> in Claude Code.
+ */
+async function setupClaudeCommands(projectDir) {
+    const commandsDir = path.join(projectDir, '.claude', 'commands');
+    await fs.ensureDir(commandsDir);
+
+    const commands = [
+        {
+            src: path.join(PKG_DIR, 'custom', 'templates', 'shared', 'create-spec-workflow.md'),
+            dest: 'create-spec.md',
+            description: 'BA 4-Gate Spec Creation Workflow — converts raw requirements (Jira/Backlog/file) into complete UC Spec documents following the UCflow process: Gate 1 (analysis & Q&A), Gate 2 (Q&A loop until all Confirmed), Gate 3 (HTML/CSS prototype design), Gate 4 (full UC Spec). Reads BA sub-skills from .claude/skills/ba-skills/.',
+        },
+        {
+            src: path.join(PKG_DIR, 'custom', 'templates', 'shared', 'create-testcase-workflow.md'),
+            dest: 'create-testcase.md',
+            description: 'QA 4-Gate TestCase Creation Workflow — converts raw requirements (SRS/Backlog/Jira/Spec file) into a complete, execution-ready Test Case set following the QA Workflow standard: Gate 1 (requirement & risk analysis), Gate 2 (scenario building), Gate 3 (detailed test case design), Gate 4 (review & optimization). Reads QA sub-skills from .claude/skills/test-skills/.',
+        },
+    ];
+
+    for (const cmd of commands) {
+        if (!(await fs.pathExists(cmd.src))) continue;
+        const body = await fs.readFile(cmd.src, 'utf-8');
+        const content = `---\ndescription: ${cmd.description}\n---\n\n${body}`;
+        await fs.writeFile(path.join(commandsDir, cmd.dest), content);
+        console.log(chalk.green(`✓ Installed /${path.basename(cmd.dest, '.md')} command → .claude/commands/${cmd.dest}`));
+    }
+}
+
 
 async function generateSkillRegistry(projectDir) {
     const skillsDir = path.join(projectDir, '.claude', 'skills');
@@ -332,10 +363,24 @@ async function setupFramework(projectDir, framework, multi = false, selectedTool
     const frameworkContent = await fs.readFile(frameworkTemplatePath, 'utf-8');
     const workflowFile = resolveWorkflowFile(framework);
     const workflowPath = path.join(PKG_DIR, 'custom', 'templates', 'shared', workflowFile);
-    const workflowContent = (await fs.pathExists(workflowPath))
+    const gateWorkflowContent = (await fs.pathExists(workflowPath))
         ? await fs.readFile(workflowPath, 'utf-8')
         : '';
 
+    // Load BA spec creation workflow (appended to all instruction files)
+    const createSpecPath = path.join(PKG_DIR, 'custom', 'templates', 'shared', 'create-spec-workflow.md');
+    const createSpecContent = (await fs.pathExists(createSpecPath))
+        ? await fs.readFile(createSpecPath, 'utf-8')
+        : '';
+
+    // Load QA testcase creation workflow (appended to all instruction files)
+    const createTestcasePath = path.join(PKG_DIR, 'custom', 'templates', 'shared', 'create-testcase-workflow.md');
+    const createTestcaseContent = (await fs.pathExists(createTestcasePath))
+        ? await fs.readFile(createTestcasePath, 'utf-8')
+        : '';
+
+    const workflowContent = [gateWorkflowContent, createSpecContent, createTestcaseContent].filter(Boolean).join('\n\n---\n\n');
+
     const separator = `\n\n---\n\n`;
     const skillRegistry = await generateSkillRegistry(projectDir);
 
@@ -1047,6 +1092,7 @@ async function init(options) {
         await verifySuperpowersSkills(versionDir);
         await updateSymlinks(projectDir, versionDir);
         await copyDocsToProject(projectDir);
+        await setupClaudeCommands(projectDir);
 
         const selectedTools = options.aiTools || Object.keys(AI_TOOL_FILES);
         for (const fw of frameworks) {
@@ -1103,6 +1149,7 @@ module.exports.AI_TOOL_FILES = AI_TOOL_FILES;
 module.exports.detectRtk = detectRtk;
 module.exports.isRtkHookConfigured = isRtkHookConfigured;
 module.exports.isGitNexusConfigured = isGitNexusConfigured;
+module.exports.setupClaudeCommands = setupClaudeCommands;
 module.exports.setupFramework = setupFramework;
 module.exports.ensureAiflowGitignored = ensureAiflowGitignored;
 module.exports.resolveWorkflowFile = resolveWorkflowFile;

package/scripts/review.js

@@ -0,0 +1,91 @@
+'use strict';
+
+const fs = require('fs-extra');
+const path = require('path');
+
+const REVIEW_DIR = '.aiflow/review';
+
+function reviewFilePath(gate, ticketId) {
+    return path.join(process.cwd(), REVIEW_DIR, `gate-${gate}-${ticketId}.md`);
+}
+
+/**
+ * Parse a gate review file and return checkbox state.
+ *
+ * @param {number} gate
+ * @param {string} ticketId
+ * @returns {Promise<{exists: boolean, passed?: boolean, total?: number, unchecked?: string[], commented?: Array<{item: string, comment: string}>}>}
+ */
+async function checkReviewFile(gate, ticketId) {
+    const filePath = reviewFilePath(gate, ticketId);
+
+    if (!(await fs.pathExists(filePath))) {
+        return { exists: false };
+    }
+
+    const content = await fs.readFile(filePath, 'utf-8');
+    const lines = content.split('\n');
+
+    const unchecked = [];
+    const commented = [];
+    let total = 0;
+
+    for (let i = 0; i < lines.length; i++) {
+        const line = lines[i];
+        const checkboxMatch = line.match(/^- \[([ xX])\] (.+)/);
+        if (!checkboxMatch) continue;
+
+        total++;
+        const isChecked = checkboxMatch[1].toLowerCase() === 'x';
+        const itemText = checkboxMatch[2].trim();
+
+        if (!isChecked) {
+            let comment = null;
+            let commentBuffer = '';
+            let inComment = false;
+            for (let j = i + 1; j < lines.length; j++) {
+                const nextLine = lines[j].trim();
+                if (!inComment && nextLine.match(/^- \[/)) break;
+                if (!inComment && nextLine === '---') break;
+                if (!inComment) {
+                    const singleLineMatch = nextLine.match(/<!--([\s\S]+?)-->/);
+                    if (singleLineMatch) {
+                        comment = singleLineMatch[1].trim();
+                        break;
+                    }
+                    if (nextLine.includes('<!--')) {
+                        inComment = true;
+                        commentBuffer = nextLine.replace(/^.*<!--/, '');
+                        if (commentBuffer.includes('-->')) {
+                            comment = commentBuffer.replace(/-->.*$/, '').trim();
+                            break;
+                        }
+                        continue;
+                    }
+                } else {
+                    if (nextLine.includes('-->')) {
+                        commentBuffer += ' ' + nextLine.replace(/-->.*$/, '');
+                        comment = commentBuffer.trim();
+                        break;
+                    }
+                    commentBuffer += ' ' + nextLine;
+                }
+            }
+            if (comment) {
+                commented.push({ item: itemText, comment });
+            } else {
+                unchecked.push(itemText);
+            }
+        }
+    }
+
+    return {
+        exists: true,
+        passed: unchecked.length === 0 && commented.length === 0,
+        total,
+        unchecked,
+        commented,
+    };
+}
+
+module.exports = { checkReviewFile, reviewFilePath };

package/scripts/update.js

@@ -110,13 +110,16 @@ module.exports = async function update(options = {}) {
 
     // Sync instruction files with the updated skills.
     // Support both old 'framework' (singular string) and new 'frameworks' (array).
-    const { setupFramework, AI_TOOL_FILES, ensureAiflowGitignored } = require('./init');
+    const { setupFramework, AI_TOOL_FILES, ensureAiflowGitignored, setupClaudeCommands } = require('./init');
     const frameworks = state.frameworks || (state.framework ? [state.framework] : []);
     const selectedTools = state.aiTools || Object.keys(AI_TOOL_FILES);
     for (const fw of frameworks) {
         await setupFramework(projectDir, fw, frameworks.length > 1, selectedTools, { force: true });
     }
 
+    // Install / refresh Claude Code custom commands (.claude/commands/)
+    await setupClaudeCommands(projectDir);
+
     // Ensure all aiflow files are gitignored (especially for projects upgrading from older versions)
     await ensureAiflowGitignored(projectDir);
 

package/scripts/use.js

@@ -11,6 +11,8 @@ const CATEGORY_COLOR = {
   Testing:  chalk.green,
   Analysis: chalk.yellow,
   Document: chalk.magenta,
+  BA:       chalk.blue,
+  QA:       chalk.greenBright,
 };
 const td = (label, cat, desc) => {
   const pad = " ".repeat(Math.max(0, 20 - stringWidth(label)));
@@ -625,14 +627,16 @@ async function promptForTaskType(detectedDefault) {
   return await select({
     message: "Task type:",
     choices: [
-      { name: td("🐛 Bug Fix",         "Coding",   "Fix bugs, crashes, regressions"),       value: "bug-fix" },
-      { name: td("✨ Feature",          "Coding",   "Build new features, user stories"),     value: "feature" },
-      { name: td("🔄 Refactor",         "Coding",   "Improve code without behavior change"), value: "refactor" },
-      { name: td("🔬 Testing",           "Testing",  "Write tests, QA, coverage"),            value: "testing" },
-      { name: td("▶️  Execute Test",     "Testing",  "Run existing TC scripts (4-gate flow)"), value: "execute" },
-      { name: td("🔍 Investigation",    "Analysis", "Investigate, analyze root cause"),      value: "investigation" },
-      { name: td("📊 Impact Analysis",  "Analysis", "Assess scope and risk of changes"),     value: "impact-analysis" },
-      { name: td("📖 Documentation",    "Document", "Write docs, README, API reference"),    value: "documentation" },
+      { name: td("🐛 Bug Fix",         "Coding",   "Fix bugs, crashes, regressions"),                    value: "bug-fix" },
+      { name: td("✨ Feature",          "Coding",   "Build new features, user stories"),                  value: "feature" },
+      { name: td("🔄 Refactor",         "Coding",   "Improve code without behavior change"),              value: "refactor" },
+      { name: td("🔬 Testing",          "Testing",  "Write tests, QA, coverage"),                         value: "testing" },
+      { name: td("▶️  Execute Test",    "Testing",  "Run existing TC scripts (4-gate flow)"),             value: "execute" },
+      { name: td("📋 Create Spec",      "BA",       "Create UC Spec from raw requirements (4-gate BA)"),  value: "create-spec" },
+      { name: td("✅ Create TestCase",  "QA",       "Create Test Cases from requirements (4-gate QA)"),   value: "create-testcase" },
+      { name: td("🔍 Investigation",    "Analysis", "Investigate, analyze root cause"),                   value: "investigation" },
+      { name: td("📊 Impact Analysis",  "Analysis", "Assess scope and risk of changes"),                  value: "impact-analysis" },
+      { name: td("📖 Documentation",    "Document", "Write docs, README, API reference"),                 value: "documentation" },
     ],
     default: detectedDefault || "feature",
   });
@@ -697,14 +701,16 @@ async function manualContext(prefillId = "") {
   const taskType = await select({
     message: "Task type:",
     choices: [
-      { name: td("🐛 Bug Fix",         "Coding",   "Fix bugs, crashes, regressions"),       value: "bug-fix" },
-      { name: td("✨ Feature",          "Coding",   "Build new features, user stories"),     value: "feature" },
-      { name: td("🔄 Refactor",         "Coding",   "Improve code without behavior change"), value: "refactor" },
-      { name: td("🔬 Testing",           "Testing",  "Write tests, QA, coverage"),            value: "testing" },
-      { name: td("▶️  Execute Test",     "Testing",  "Run existing TC scripts (4-gate flow)"), value: "execute" },
-      { name: td("🔍 Investigation",    "Analysis", "Investigate, analyze root cause"),      value: "investigation" },
-      { name: td("📊 Impact Analysis",  "Analysis", "Assess scope and risk of changes"),     value: "impact-analysis" },
-      { name: td("📖 Documentation",    "Document", "Write docs, README, API reference"),    value: "documentation" },
+      { name: td("🐛 Bug Fix",         "Coding",   "Fix bugs, crashes, regressions"),                    value: "bug-fix" },
+      { name: td("✨ Feature",          "Coding",   "Build new features, user stories"),                  value: "feature" },
+      { name: td("🔄 Refactor",         "Coding",   "Improve code without behavior change"),              value: "refactor" },
+      { name: td("🔬 Testing",          "Testing",  "Write tests, QA, coverage"),                         value: "testing" },
+      { name: td("▶️  Execute Test",    "Testing",  "Run existing TC scripts (4-gate flow)"),             value: "execute" },
+      { name: td("📋 Create Spec",      "BA",       "Create UC Spec from raw requirements (4-gate BA)"),  value: "create-spec" },
+      { name: td("✅ Create TestCase",  "QA",       "Create Test Cases from requirements (4-gate QA)"),   value: "create-testcase" },
+      { name: td("🔍 Investigation",    "Analysis", "Investigate, analyze root cause"),                   value: "investigation" },
+      { name: td("📊 Impact Analysis",  "Analysis", "Assess scope and risk of changes"),                  value: "impact-analysis" },
+      { name: td("📖 Documentation",    "Document", "Write docs, README, API reference"),                 value: "documentation" },
     ],
     default: existing.taskType || undefined,
   });