@relipa/ai-flow-kit 0.1.4 → 0.1.5-beta.1

package/docs/common/workflows/feature.md

@@ -1,123 +1,123 @@
-# Feature Development Workflow
-
-> See the full workflow at [AIFLOW.md](../../AIFLOW.md)
-> **Gates must pass in order: 1 → 2 → 3 → 4 → 5**
-
----
-
-## Step 1: Load ticket & AI analyzes (Gate 1)
-
-```bash
-aiflow use PROJ-33                    # from Backlog/Jira
-claude                                # AI auto-starts Gate 1
-```
-
-AI will **automatically**:
-1. Load ticket info from Backlog/Jira
-2. Read source code — understand architecture, related files, patterns
-3. Ask clarifying questions if anything is unclear (one at a time)
-4. Output `plan/[ticket-id]/requirement.md` containing:
-   - Requirements summary (AI's understanding)
-   - Source code analysis (related files, data flow)
-   - **Proposed solution** with options and recommendation
-   - **Impact analysis** — affected areas, risks
-   - **Effort estimate** (S/M/L/XL)
-   - Testing plan
-
-**PM needs to prepare on the ticket:**
-```markdown
-## Description
-Clear business requirement. Who uses it, and for what purpose.
-
-## Acceptance Criteria
-- [ ] [Condition for completion 1]
-- [ ] [Condition for completion 2]
-
-## Mockup / Wireframe
-[Link or UI description]
-
-## Context
-Constraints, business rules specially requiring attention.
-```
-
-**If ticket content is unclear:** AI will ask questions based on source code analysis — not just checking format.
-
-**When satisfied with the requirement document, type:**
-```
-APPROVED
-```
-
----
-
-## Step 2: Review Implementation Plan (Gate 2)
-
-AI generates a detailed implementation plan:
-- TDD task breakdown (test first → implement → verify)
-- Commit strategy (small, focused commits)
-- Test commands
-
-**When agreed, type:**
-```
-APPROVED
-```
-
-**CODE WILL NOT BE GENERATED BEFORE RECEIVING "APPROVED".**
-
----
-
-## Step 3: AI Generate Code (Gate 3)
-
-AI performs automatically:
-1. Complex feature (3+ files): `superpowers:subagent-driven-development`
-2. Write tests FIRST → run → confirm FAIL
-3. Implement → tests PASS
-4. Commit each small step
-
-Developer doesn't need to do anything at this step — just monitor.
-
----
-
-## Step 4: Review Summary (Gate 4)
-
-AI runs:
-1. `superpowers:verification-before-completion` — all tests PASS
-2. `impact-analysis` — no breaking changes outside of scope
-3. Review checklist — all items ticked
-4. Create `plan/[ticket-id]/summary.md`
-
-AI displays summary and waits for developer review.
-
-**If OK, type:**
-```
-APPROVED
-```
-
-**If there are bugs, type:**
-```
-BUG: [specific description]
-```
-- Coding bug → AI fixes → repeat Gate 4
-- Requirement bug → AI returns to Gate 1, update requirement doc
-
----
-
-## Step 5: Peer Review & PR (Gate 5)
-
-AI invokes `superpowers:requesting-code-review` and guides PR creation.
-
-```bash
-git push origin feature/PROJ-33-feature-name
-# Create PR with full description following the template in AIFLOW.md
-```
-
-Peer reviewer uses the `superpowers:receiving-code-review` skill during review.
-
----
-
-## Completion Checklist
-
-- [ ] Gate 1 APPROVED — requirement doc with solution, impact, estimate
-- [ ] Gate 2 APPROVED — implementation plan confirmed by developer
-- [ ] Gate 3 done — code + tests are green
-- [ ] Gate 4 APPROVED — summary + checklist complete
-- [ ] Gate 5 done — PR is peer-reviewed and merged
+# Feature Development Workflow
+
+> See the full workflow at [AIFLOW.md](../../AIFLOW.md)
+> **Gates must pass in order: 1 → 2 → 3 → 4 → 5**
+
+---
+
+## Step 1: Load ticket & AI analyzes (Gate 1)
+
+```bash
+aiflow use PROJ-33                    # from Backlog/Jira
+claude                                # AI auto-starts Gate 1
+```
+
+AI will **automatically**:
+1. Load ticket info from Backlog/Jira
+2. Read source code — understand architecture, related files, patterns
+3. Ask clarifying questions if anything is unclear (one at a time)
+4. Output `04.Coding/01.Requirements/[functionId]/[ticketId].md` containing:
+   - Requirements summary (AI's understanding)
+   - Source code analysis (related files, data flow)
+   - **Proposed solution** with options and recommendation
+   - **Impact analysis** — affected areas, risks
+   - **Effort estimate** (S/M/L/XL)
+   - Testing plan
+
+**PM needs to prepare on the ticket:**
+```markdown
+## Description
+Clear business requirement. Who uses it, and for what purpose.
+
+## Acceptance Criteria
+- [ ] [Condition for completion 1]
+- [ ] [Condition for completion 2]
+
+## Mockup / Wireframe
+[Link or UI description]
+
+## Context
+Constraints, business rules specially requiring attention.
+```
+
+**If ticket content is unclear:** AI will ask questions based on source code analysis — not just checking format.
+
+**When satisfied with the requirement document, type:**
+```
+APPROVED
+```
+
+---
+
+## Step 2: Review Implementation Plan (Gate 2)
+
+AI generates a detailed implementation plan:
+- TDD task breakdown (test first → implement → verify)
+- Commit strategy (small, focused commits)
+- Test commands
+
+**When agreed, type:**
+```
+APPROVED
+```
+
+**CODE WILL NOT BE GENERATED BEFORE RECEIVING "APPROVED".**
+
+---
+
+## Step 3: AI Generate Code (Gate 3)
+
+AI performs automatically:
+1. Complex feature (3+ files): `superpowers:subagent-driven-development`
+2. Write tests FIRST → run → confirm FAIL
+3. Implement → tests PASS
+4. Commit each small step
+
+Developer doesn't need to do anything at this step — just monitor.
+
+---
+
+## Step 4: Review Summary (Gate 4)
+
+AI runs:
+1. `superpowers:verification-before-completion` — all tests PASS
+2. `impact-analysis` — no breaking changes outside of scope
+3. Review checklist — all items ticked
+4. Create `04.Coding/04.Reviews/[functionId]/[ticketId].md`
+
+AI displays summary and waits for developer review.
+
+**If OK, type:**
+```
+APPROVED
+```
+
+**If there are bugs, type:**
+```
+BUG: [specific description]
+```
+- Coding bug → AI fixes → repeat Gate 4
+- Requirement bug → AI returns to Gate 1, update requirement doc
+
+---
+
+## Step 5: Peer Review & PR (Gate 5)
+
+AI invokes `superpowers:requesting-code-review` and guides PR creation.
+
+```bash
+git push origin feature/PROJ-33-feature-name
+# Create PR with full description following the template in AIFLOW.md
+```
+
+Peer reviewer uses the `superpowers:receiving-code-review` skill during review.
+
+---
+
+## Completion Checklist
+
+- [ ] Gate 1 APPROVED — requirement doc with solution, impact, estimate
+- [ ] Gate 2 APPROVED — implementation plan confirmed by developer
+- [ ] Gate 3 done — code + tests are green
+- [ ] Gate 4 APPROVED — summary + checklist complete
+- [ ] Gate 5 done — PR is peer-reviewed and merged

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@relipa/ai-flow-kit",
-  "version": "0.1.4",
+  "version": "0.1.5-beta.1",
   "description": "All-in-one AI Flow Kit for team development with Claude AI - skills, templates, and MCP adapters",
   "author": "Example Team",
   "publishConfig": {

package/scripts/create-score-excel.js

@@ -39,8 +39,8 @@ function parseLog(filePath) {
     if (!user || user === '-' || user === '') continue;
 
     const timestamp = cols[0] || '';
-    const command   = cols[6] || '';
-    const ticket    = cols[9] || '';
+    const command = cols[6] || '';
+    const ticket = cols[9] || '';
 
     const date = timestamp.split(' ')[0]; // dd/MM/yyyy
 
@@ -74,10 +74,10 @@ function calcScore(u) {
   if (events === 0) return 0;
 
   // Gate aggregation
-  const gateStarted   = new Set(); // gate numbers
-  const gateApproved  = new Set();
-  const ticketsStarted    = new Set();
-  const ticketsCompleted  = new Set(); // gate4.approved or gate5.start
+  const gateStarted = new Set(); // gate numbers
+  const gateApproved = new Set();
+  const ticketsStarted = new Set();
+  const ticketsCompleted = new Set(); // gate4.approved or gate5.start
 
   for (const g of gateCmds) {
     const hasTicket = g.ticket && g.ticket !== '-' && g.ticket !== '';
@@ -97,9 +97,9 @@ function calcScore(u) {
     }
   }
 
-  const hasUse     = USE_CMDS.has('use') && rawCmds.has('use');
-  const hasPrompt  = rawCmds.has('prompt');
-  const hasGuide   = rawCmds.has('guide') || rawCmds.has('guideline') || rawCmds.has('sync-skills');
+  const hasUse = USE_CMDS.has('use') && rawCmds.has('use');
+  const hasPrompt = rawCmds.has('prompt');
+  const hasGuide = rawCmds.has('guide') || rawCmds.has('guideline') || rawCmds.has('sync-skills');
   const hasGateHighApproved = gateApproved.has(3) || gateApproved.has(4);
 
   // Score 5: gate 3-5 approved + ≥ 3 tickets completed
@@ -122,9 +122,9 @@ function calcScore(u) {
 }
 
 const SCORE_LABELS = [
-  'Không hoạt động',
-  'Mới khám phá',
-  'Bắt đầu dùng',
+  'Trong tuần không sử dụng lần nào',
+  'Rất ít dùng',
+  'Có sử dụng nhưng chưa bắt đầu workflow nào cả',
   'Dùng có workflow',
   'Hoàn thành workflow',
   'Sử dụng thường xuyên workflow',
@@ -149,19 +149,19 @@ function buildRow(email, u) {
     .sort();
 
   // Compact gate summary
-  const startedGates  = [...new Set(gateCmds.filter(g => g.type === 'start').map(g => g.gateNum))].sort((a, b) => a - b);
+  const startedGates = [...new Set(gateCmds.filter(g => g.type === 'start').map(g => g.gateNum))].sort((a, b) => a - b);
   const approvedGates = [...new Set(gateCmds.filter(g => g.type === 'approved').map(g => g.gateNum))].sort((a, b) => a - b);
 
-  const ticketsStarted   = [...new Set(gateCmds.filter(g => g.type === 'start'   && g.ticket && g.ticket !== '-').map(g => g.ticket))];
-  const ticketsApproved  = [...new Set(gateCmds.filter(g => g.type === 'approved' && g.ticket && g.ticket !== '-').map(g => g.ticket))];
+  const ticketsStarted = [...new Set(gateCmds.filter(g => g.type === 'start' && g.ticket && g.ticket !== '-').map(g => g.ticket))];
+  const ticketsApproved = [...new Set(gateCmds.filter(g => g.type === 'approved' && g.ticket && g.ticket !== '-').map(g => g.ticket))];
   const ticketsCompleted = [...new Set(gateCmds.filter(g =>
     ((g.type === 'approved' && g.gateNum >= 4) || (g.gateNum === 5 && g.type === 'start'))
     && g.ticket && g.ticket !== '-'
   ).map(g => g.ticket))];
 
-  const gateStartStr    = startedGates.length ? `G${startedGates.join(',')} / ${ticketsStarted.length} ticket(s)` : '';
+  const gateStartStr = startedGates.length ? `G${startedGates.join(',')} / ${ticketsStarted.length} ticket(s)` : '';
   const gateApprovedStr = approvedGates.length ? `G${approvedGates.join(',')} / ${ticketsApproved.length} ticket(s)` : '';
-  const ticketsStr      = ticketsCompleted.length ? ticketsCompleted.join(', ') : '';
+  const ticketsStr = ticketsCompleted.length ? ticketsCompleted.join(', ') : '';
 
   // Notes
   const onlyExploreCmds = [...rawCmds].every(c => EXPLORE_CMDS.has(c));
@@ -207,20 +207,20 @@ async function writeExcel(rows, outputPath, sheetLabel, fromLabel, toLabel) {
   const sheet = workbook.addWorksheet(`Score ${sheetLabel}`);
 
   sheet.columns = [
-    { key: 'no',           width: 5  },
-    { key: 'email',        width: 30 },
-    { key: 'events',       width: 8  },
-    { key: 'activeDays',   width: 10 },
-    { key: 'keyCommands',  width: 40 },
-    { key: 'gateStart',    width: 24 },
+    { key: 'no', width: 5 },
+    { key: 'email', width: 30 },
+    { key: 'events', width: 8 },
+    { key: 'activeDays', width: 10 },
+    { key: 'keyCommands', width: 40 },
+    { key: 'gateStart', width: 24 },
     { key: 'gateApproved', width: 24 },
-    { key: 'tickets',      width: 44 },
-    { key: 'depthScore',   width: 8  },
-    { key: 'depthLabel',   width: 28 },
-    { key: 'impactScore',  width: 8  },
-    { key: 'impactLabel',  width: 18 },
-    { key: 'totalScore',   width: 8  },
-    { key: 'notes',        width: 54 },
+    { key: 'tickets', width: 44 },
+    { key: 'depthScore', width: 8 },
+    { key: 'depthLabel', width: 28 },
+    { key: 'impactScore', width: 8 },
+    { key: 'impactLabel', width: 18 },
+    { key: 'totalScore', width: 8 },
+    { key: 'notes', width: 54 },
   ];
 
   const border = {
@@ -232,9 +232,9 @@ async function writeExcel(rows, outputPath, sheetLabel, fromLabel, toLabel) {
   sheet.addRow([`AI Flow Kit — Weekly Score Report: ${fromLabel} – ${toLabel}`]);
   sheet.mergeCells('A1:N1');
   const title = sheet.getCell('A1');
-  title.font      = { bold: true, size: 13, color: { argb: 'FF1F3864' } };
+  title.font = { bold: true, size: 13, color: { argb: 'FF1F3864' } };
   title.alignment = { vertical: 'middle', horizontal: 'center' };
-  title.fill      = { type: 'pattern', pattern: 'solid', fgColor: { argb: 'FFD6DCE4' } };
+  title.fill = { type: 'pattern', pattern: 'solid', fgColor: { argb: 'FFD6DCE4' } };
   sheet.getRow(1).height = 28;
 
   // Header row
@@ -247,10 +247,10 @@ async function writeExcel(rows, outputPath, sheetLabel, fromLabel, toLabel) {
   const hRow = sheet.addRow(HEADERS);
   hRow.height = 36;
   hRow.eachCell(cell => {
-    cell.fill      = { type: 'pattern', pattern: 'solid', fgColor: { argb: 'FF4472C4' } };
-    cell.font      = { bold: true, color: { argb: 'FFFFFFFF' }, size: 11 };
+    cell.fill = { type: 'pattern', pattern: 'solid', fgColor: { argb: 'FF4472C4' } };
+    cell.font = { bold: true, color: { argb: 'FFFFFFFF' }, size: 11 };
     cell.alignment = { vertical: 'middle', horizontal: 'center', wrapText: true };
-    cell.border    = border;
+    cell.border = border;
   });
 
   // Score → row color
@@ -276,7 +276,7 @@ async function writeExcel(rows, outputPath, sheetLabel, fromLabel, toLabel) {
     const fill = { type: 'pattern', pattern: 'solid', fgColor: { argb: COLORS[row.depthScore] || 'FFFFFFFF' } };
     r.eachCell({ includeEmpty: true }, (cell, col) => {
       cell.border = border;
-      cell.fill   = fill;
+      cell.fill = fill;
       cell.alignment = (col <= 4 || (col >= 9 && col <= 13))
         ? { vertical: 'middle', horizontal: 'center' }
         : { vertical: 'middle', horizontal: 'left', wrapText: false };
@@ -286,7 +286,7 @@ async function writeExcel(rows, outputPath, sheetLabel, fromLabel, toLabel) {
     r.getCell(13).value = { formula: `I${excelRowNum}+K${excelRowNum}` };
   });
 
-  sheet.views      = [{ state: 'frozen', ySplit: 2 }];
+  sheet.views = [{ state: 'frozen', ySplit: 2 }];
   sheet.autoFilter = { from: 'A2', to: 'N2' };
 
   await workbook.xlsx.writeFile(outputPath);
@@ -295,17 +295,14 @@ async function writeExcel(rows, outputPath, sheetLabel, fromLabel, toLabel) {
 
 // ── Canonical user list (fixed order) ─────────────────────────────────────
 const CANONICAL_USERS = [
-  'anhtt@relipasoft.com',
   'hoangdv@relipasoft.com',
   'chinhtt@relipasoft.com',
-  'hieptv@relipasoft.com',
   'phongnx@relipasoft.com',
   'dungha@relipasoft.com',
   'thangnv@relipasoft.com',
   'nguyenlt@relipasoft.com',
   'thuongvv@relipasoft.com',
   'yenvtb@relipasoft.com',
-  'tructh@relipasoft.com',
   'thainq@relipasoft.com',
   'tuoittx@relipasoft.com',
   'hungdv@relipasoft.com',
@@ -314,7 +311,7 @@ const CANONICAL_USERS = [
   'huynq@relipasoft.com',
   'thinhvq@relipasoft.com',
   'banv@relipasoft.com',
-  'duongnt@relipasoft.com',
+  'duongnt1@relipasoft.com',
   'anhnt@relipasoft.com',
   'khanhdd@relipasoft.com',
   'hieunv@relipasoft.com',
@@ -322,9 +319,7 @@ const CANONICAL_USERS = [
 
 // Log email → canonical email (for slight mismatches)
 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) => ({
@@ -343,15 +338,14 @@ const EMPTY_USER = (email) => ({
     ? [dateMatch[1].replace(/-/g, '/'), dateMatch[2].replace(/-/g, '/')]
     : ['?', '?'];
   const sheetLabel = dateMatch
-    ? `${dateMatch[1].slice(0,5).replace(/-/g,'.')}-${dateMatch[2].slice(0,5).replace(/-/g,'.')}.${dateMatch[1].slice(6,10)}`
+    ? `${dateMatch[1].slice(0, 5).replace(/-/g, '.')}-${dateMatch[2].slice(0, 5).replace(/-/g, '.')}.${dateMatch[1].slice(6, 10)}`
     : stem;
 
-  const logFile    = path.join(__dirname, '..', 'tellog', stem);
+  const logFile = path.join(__dirname, '..', 'tellog', stem);
   const outputFile = path.join(__dirname, '..', 'tellog', `${stem}.xlsx`);
 
   const rawUsers = parseLog(logFile);
 
-  // Re-key log users using alias map (tructh → tructth, duongnt1 → duongnt)
   const users = {};
   for (const [logEmail, data] of Object.entries(rawUsers)) {
     const canonical = LOG_EMAIL_ALIAS[logEmail] || logEmail;

package/scripts/hooks/session-start.js

@@ -215,14 +215,16 @@ function buildContextPrompt(ctx, taskState) {
 
         if (currentGate === 2) {
             lines.push('Gate 1 is already APPROVED. The requirement document is at:');
-            lines.push(`  plan/${ctx.taskId}/requirement.md`);
+            lines.push(`  04.Coding/01.Requirements/[functionId]/${ctx.taskId}.md`);
+            lines.push(`  ([functionId] — look it up in 04.Coding/00.Overview/_Index.md or the folder containing ${ctx.taskId}.md)`);
             lines.push('');
             lines.push('Proceed to Gate 2: create the implementation plan.');
             lines.push(buildModeInstruction(mode, 2));
         } else if (currentGate === 3) {
             lines.push('Gates 1 and 2 are already APPROVED. Plans are at:');
-            lines.push(`  plan/${ctx.taskId}/requirement.md`);
-            lines.push(`  plan/${ctx.taskId}/plan.md`);
+            lines.push(`  04.Coding/01.Requirements/[functionId]/${ctx.taskId}.md`);
+            lines.push(`  04.Coding/02.Plans/[functionId]/${ctx.taskId}.md`);
+            lines.push(`  ([functionId] — look it up in 04.Coding/00.Overview/_Index.md)`);
             lines.push('');
             lines.push('Proceed to Gate 3: implement code following the plan (TDD).');
             lines.push(buildModeInstruction(mode, 3));
@@ -246,23 +248,26 @@ function buildContextPrompt(ctx, taskState) {
 
         if (mode === 'fast') {
             lines.push('**MODE: fast** — Use the FAST TRACK path in the skill:');
+            lines.push('- Pre-flight: determine functionId first (from context / input UC Spec file / ask DEV to confirm) — see the DEV workflow Pre-flight step');
             lines.push('- Read ticket + identify changed files only (no deep source scan)');
             lines.push('- Skip Q&A unless there is a critical blocking ambiguity');
-            lines.push('- Output a lite requirement doc (Sections 1, 3, 5 only)');
+            lines.push('- Output a lite requirement doc (Sections 1, 3, 5 only) to 04.Coding/01.Requirements/[functionId]/' + ctx.taskId + '.md');
             lines.push('- Target: Gate 1 complete in < 5 minutes');
         } else {
             lines.push('Gate 1 process:');
+            lines.push('0. Pre-flight: determine functionId (from context / input UC Spec file / ask DEV to confirm) + ensure 04.Coding/ tree exists — see the DEV workflow Pre-flight step. DO NOT continue without functionId.');
             lines.push('1. Read the ticket context above');
             lines.push('2. Read CLAUDE.md — understand project architecture and conventions');
             lines.push('3. Read source code — identify related files, data flow, patterns');
             lines.push('4. If anything is unclear — ask ONE question at a time');
-            lines.push('5. Output plan/' + ctx.taskId + '/requirement.md');
+            lines.push('5. Output 04.Coding/01.Requirements/[functionId]/' + ctx.taskId + '.md');
             lines.push('6. Display GATE 1 prompt and wait for APPROVED');
         }
 
         lines.push('');
         lines.push('DO NOT wait for the developer to ask. START NOW.');
         lines.push('If you have not started automatically, begin as soon as the developer types **"start"**.');
+        lines.push('(If a later ticket switch does not seem to trigger this — e.g. `ak use` was run in another terminal while this chat was already open — the developer can run **`/coding`** to load it manually.)');
     }
 
     lines.push('</ACTIVE_TASK>');

package/scripts/init.js

@@ -305,6 +305,11 @@ async function setupClaudeCommands(projectDir) {
             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/.',
         },
+        {
+            src: path.join(PKG_DIR, 'custom', 'templates', 'shared', 'coding-workflow.md'),
+            dest: 'coding.md',
+            description: 'Manual trigger for the DEV 5-Gate Coding Workflow (bug-fix / feature / refactor / investigation / documentation). Use this when the SessionStart auto-start message was missed — e.g. a ticket was loaded with `ak use` while this chat session was already open.',
+        },
     ];
 
     for (const cmd of commands) {