@leejungkiin/awkit 1.6.4 → 1.6.6

package/README.md

@@ -1,41 +1,42 @@
-# AWKit — Antigravity Workflow Kit v12.5
+# AWKit — Antigravity Workflow Kit
 
-> **v12.5** · Single Source of Truth · Symphony-First · Mindful Execution
+> Antigravity v12.5 · npm package v1.6.5 · Single Source of Truth · Symphony-first · Mindful execution
 
-AWKit là framework điều phối AI agent chuyên nghiệp. Đây là **nơi duy nhất** chứa toàn bộ workflows, skills, GEMINI.md và cấu hình — không còn phân tán giữa nhiều repo.
-AWKit giúp tối ưu context khi làm việc, có khả năng quản lý task, đồng bộ Trello và báo cáo lên Telegram, ngoài ra Awkit còn sử dụng cơ chế checkpoint để dev dừng đúng lúc tránh tâm lý tối ưu hóa quá mức (over-optimization) một vấn đề phổ biến khi làm việc với AI.
+AWKit is a professional AI-agent orchestration framework. This repository is the single source of truth for workflows, skills, core rules (GEMINI.md), and installation tooling (no more scattered configs across multiple repos).
+
+AWKit focuses on predictable execution: task management via Symphony, optional Trello sync and Telegram notifications, plus mindful checkpoints that help agents (and humans) stop at the right time and avoid over-optimizing.
 
 ---
 
-## 🧠 Gstack Core Principles
+## Core Principles
 
-AWKit (Antigravity v12+) thực thi 8 nguyên tắc lõi (Gstack-inspired) nhằm đảm bảo AI hoạt động an toàn và hiệu quả:
+AWKit (Antigravity v12+) enforces a small set of non-negotiable principles to keep AI work safe and effective:
 
-1. **Anti-sycophancy:** AI phải phản biện các hướng tiếp cận có rủi ro, không đồng ý mù quáng khi có red flags.
-2. **Search Before Building (3-layer):** Tìm kiếm NeuralMemory/codebase → Tìm standard libraries/SDKs → Chỉ code mới nếu 2 bước trên thất bại.
-3. **Completion Status Protocol:** 4 trạng thái rõ ràng: `DONE`, `DONE_WITH_CONCERNS`, `BLOCKED`, `NEEDS_CONTEXT`.
-4. **6 Decision Principles:** Complete > Shortcuts, Evidence > Assumptions, Standard > Custom, Explicit > Implicit, Test > Trust, Small > Big.
-5. **3-Strike Escalation:** Sau 3 lần thử fix bug thất bại → STOP, báo cáo context và chờ user quyết định.
-6. **Scope Freeze:** Khi debugging: KHÔNG sửa code không liên quan, KHÔNG refactor. Chỉ tập trung root cause.
-7. **Boil-the-Lake Checklist:** Checklist trước khi báo DONE: error handling, edge cases, logging, cleanup, input validation...
-8. **Safety Guardrails:** Chặn auto-run cho các lệnh nguy hiểm (`rm -rf`, `git push --force`, deploy production). Bắt buộc double-confirm.
-9. **Mindful Execution (v12.5+):** Chống AI "brain fry" bằng Iteration Counter (dừng sau 3 lần polish), Scope Guard, và Milestone Rest.
+1. **Anti-sycophancy**: push back when an approach has red flags; do not agree blindly.
+2. **Search before building (3-layer)**: check NeuralMemory/codebase first → then standard libraries/SDKs → only write new code as a last resort.
+3. **Completion status protocol**: use one of `DONE`, `DONE_WITH_CONCERNS`, `BLOCKED`, `NEEDS_CONTEXT`.
+4. **Decision principles**: Complete > Shortcuts, Evidence > Assumptions, Standard > Custom, Explicit > Implicit, Test > Trust, Small > Big.
+5. **3-strike escalation**: after 3 failed attempts at fixing the same issue, stop and report context for a decision.
+6. **Scope freeze for debugging**: no unrelated edits, no refactors; focus on root cause.
+7. **"Boil-the-lake" checklist before DONE**: error handling, edge cases, logging, cleanup, input validation, etc.
+8. **Safety guardrails**: block dangerous commands by default; require double confirmation.
+9. **Mindful execution (v12.5+)**: iteration counter, scope guard, milestone rest.
 
 ---
 
-## 🚀 Quick Start
+## Quick Start
 
-### Cài đặt (3 bước)
+### Install (3 steps)
 
 ```bash
-# 1. AWKit Core (CLI + workflows + skills)
+# 1) AWKit Core (CLI + workflows + skills)
 npm install -g @leejungkiin/awkit
 awkit install
 
-# 2. Symphony (Task Management & Multi-Agent Orchestration)
+# 2) Symphony (Task Management & Multi-Agent Orchestration)
 npm install -g @leejungkiin/awkit-symphony
 
-# 3. Optional: NeuralMemory pack (AI Memory Engine — requires Python >= 3.11)
+# 3) Optional: NeuralMemory (AI Memory Engine — requires Python >= 3.11)
 pip install neural-memory
 nmem init
 
@@ -45,163 +46,162 @@ symphony --version
 nmem --version
 ```
 
-> 💡 `awkit install` giờ chỉ cài **core runtime profile** cho **active platform** mặc định để giữ context nhẹ và tránh generate artifact không cần thiết cho Cline/Claude.
-> Các skill chuyên sâu theo domain sẽ được bật sau bằng `awkit enable-pack <name>`.
-> Dùng `awkit install --all` chỉ khi anh/chị thực sự muốn regenerate tất cả platform cùng lúc.
+Notes:
+
+- `awkit install` installs only the core runtime profile for the active platform by default (keeps context lean).
+- Enable domain-heavy packs later via `awkit enable-pack <name>`.
+- Use `awkit install --all` only if you explicitly want to regenerate every supported platform.
 
+---
 
-## 📦 Commands
+## CLI Commands
 
 | Command | Description |
 |---------|-------------|
-| `awkit install` | Deploy AWKit core runtime vào active platform hiện tại |
-| `awkit install --all` | Deploy AWKit core runtime cho mọi platform được hỗ trợ |
-| `awkit update` | Update lên version mới nhất |
-| `awkit init` | Khởi tạo project mới (tạo .project-identity, CODEBASE.md, etc.) |
+| `awkit install` | Install AWKit core runtime to the active platform |
+| `awkit install --all` | Install AWKit core runtime for all supported platforms |
+| `awkit update` | Update to the latest version |
+| `awkit init` | Initialize a new project (creates `.project-identity`, `CODEBASE.md`, etc.) |
 | `awkit sync` | Full sync: harvest + install (one shot) |
-| `awkit status` | So sánh repo vs installed (diff view) |
-| `awkit harvest` | Pull từ `~/.gemini/antigravity/` về repo |
-| `awkit doctor` | Kiểm tra sức khoẻ installation |
-| `awkit enable-pack <name>` | Kích hoạt skill pack |
-| `awkit disable-pack <name>` | Vô hiệu skill pack |
-| `awkit list-packs` | Xem danh sách skill packs |
-| `awkit tg setup` | Cài đặt Telegram Bot Token, Chat ID & Topic |
-| `awkit tg send <msg>` | Gửi tin nhắn qua Telegram |
-| `awkit version` | Show version |
+| `awkit status` | Compare repo vs installed runtime (diff view) |
+| `awkit harvest` | Pull from `~/.gemini/antigravity/` back into this repo |
+| `awkit doctor` | Health checks for installation |
+| `awkit list-packs` | List optional skill packs |
+| `awkit enable-pack <name>` | Enable a skill pack |
+| `awkit disable-pack <name>` | Disable a skill pack |
+| `awkit gate ...` | Execute gated automation (git/trello/telegram) |
+| `awkit tg setup` | Configure Telegram bot token, chat id, and topic |
+| `awkit tg send <msg>` | Send a Telegram message |
+| `awkit version` | Print version |
 
 ### Typical Workflow
 
 ```bash
-# 1. Check what's out of sync
+# 1) Check what's out of sync
 awkit status
 
-# 2a. You edited in ~/.gemini/ → pull back to repo
+# 2a) You edited in ~/.gemini/antigravity/ → pull back to repo
 awkit harvest
 
-# 2b. You edited in repo → deploy to active runtime
+# 2b) You edited in repo → deploy to active runtime
 awkit install
 
-# 2b-alt. Regenerate every platform on purpose
-awkit install --all
-
-# 2c. Both directions (full round-trip)
+# 2c) Both directions (full round-trip)
 awkit sync
 
-# 3. Commit the snapshot
-git add -A && git commit -m "chore: sync AWKit v1.5.0"
+# 3) Commit safely (gated)
+awkit gate git auto "chore: sync AWKit snapshot"
 ```
 
+---
 
-
-```
-main-awf/ (AWKit v1.5.x — Source of Truth)
-├── bin/
-│   ├── awk.js                  ← CLI entry point
-│   └── awf.js                  ← (legacy, kept for reference)
-├── core/
-│   ├── GEMINI.md               ← Master AI config (v6.4+)
-│   ├── AGENTS.md               ← Agent rules
-│   └── orchestrator.md         ← Orchestrator skill
-├── workflows/                  ← 75+ workflows, categorized
-│   ├── lifecycle/              plan, code, debug, deploy...
-│   ├── context/                recap, next, save-brain...
-│   ├── quality/                audit, performance, ux...
-│   ├── ui/                     visualize, design-to-ui...
-│   ├── ads/                    ads-audit, optimize...
-│   ├── mobile/                 maestro, turbo-build...
-│   ├── expert/                 planExpert, codeExpert...
-│   ├── git/                    commit, hotfix, rollback...
-│   ├── roles/                  tech-lead, pm, qa...
-│   ├── meta/                   customize, file-protection...
-│   └── _uncategorized/         misc files
-├── skills/                     ← Source skill library
-│   ├── orchestrator/
-│   ├── memory-sync/
-│   ├── brainstorm-agent/
-│   ├── symphony-orchestrator/
-│   ├── awf-session-restore/
-│   └── ...
-├── skill-packs/                ← Optional add-ons, installed on demand
-│   ├── mobile-ios/
-│   ├── mobile-android/
-│   ├── marketing/
-│   ├── creator-studio/
-│   ├── neural-memory/
-│   └── superpowers/
-├── schemas/                    ← JSON schemas
-├── templates/                  ← Project templates
-├── scripts/
-│   └── harvest.js              ← Migration: pull from ~/.gemini/
-├── VERSION                     → 1.5.0
-└── package.json                (@leejungkiin/awkit)
+## Repository Layout
+
+```text
+main-awf/ (Source of Truth)
+├── bin/                        # CLI entry points
+├── core/                       # Core rules/routing for agents
+├── workflows/                  # Workflow library
+├── skills/                     # Source skill library
+├── skill-packs/                # Optional add-ons, installed on demand
+├── schemas/                    # JSON schemas
+├── templates/                  # Project templates
+├── scripts/                    # Harvest, automation gate, tooling
+└── package.json                # @leejungkiin/awkit
 ```
 
-## 🌾 Harvest (Migration)
+---
 
-Nếu bạn chỉnh sửa trực tiếp trong `~/.gemini/antigravity/` và muốn sync về repo:
+## Harvest (Migration)
+
+If you edited files directly in `~/.gemini/antigravity/` and want to sync them back to this repo:
 
 ```bash
-# Xem trước (không thay đổi file)
+# Preview (no changes)
 node scripts/harvest.js --dry-run
 
-# Thực thi harvest
+# Execute harvest
 node scripts/harvest.js
 ```
 
-## 🔄 Workflow
+---
+
+## Runtime Model
 
-```
+```text
 main-awf/ (edit here)
-    │
-    ▼  awkit install
+    |
+    |  awkit install
+    v
 ~/.gemini/antigravity/ (runtime)
-    │
-    ▼  AI reads from here
-Gemini / Claude / Any AI
+    |
+    v
+Gemini / Claude / Any AI reads from runtime
 ```
 
-## 🪶 Lean Runtime
+---
+
+## Lean Runtime
+
+`awkit install` does not copy the entire source skill library into runtime by default.
 
-`awkit install` no longer copies the full source skill library into runtime by default.
+- Default install = core work profile only (orchestration, planning, debugging, verification, review, coordination).
+- Default target = active platform only, keeping platform-specific generated artifacts untouched unless explicitly requested.
+- Domain-heavy packs (reverse engineering, marketing/ASO, media production, etc.) are excluded until you opt in.
+- `awkit status` compares runtime against the core profile + enabled packs (optional packs do not create false drift).
 
-- Default install = **core work profile** only: orchestration, planning, debugging, verification, review, and project coordination.
-- Default target = **active platform only**, which keeps repo-local generated files like `CLAUDE.md` and `.clinerules/*` untouched unless you explicitly choose them.
-- Domain-heavy skills like mobile reverse engineering, ASO/marketing, and media production stay out of runtime until you opt in.
-- `awkit status` now compares runtime against the active core profile + enabled packs, so optional skills no longer show as false drift.
-- Re-running `awkit install` archives old managed optional skills from runtime, which helps shrink the skill catalog exposed to the agent.
+---
 
-## 📨 Telegram Integration
+## Automation Gate
 
-Bạn có thể cấu hình AWKit gửi thông báo tự động (deploy xong, test pass...) qua Telegram:
+AWKit provides a gated automation layer that reads `.project-identity` and enforces `automation.*` before executing:
 
 ```bash
-# 1. Setup Bot Token, Chat ID và Message Thread ID (Topic)
+awkit gate git commit "chore: update"
+awkit gate git push
+awkit gate git auto "chore: update"
+
+awkit gate trello complete "Task Name"
+awkit gate trello comment "Progress note..."
+awkit gate trello block "Reason"
+
+awkit gate telegram send "Message"
+```
+
+---
+
+## Telegram Integration
+
+Configure AWKit to send notifications (e.g., after pushes, tests, deploys):
+
+```bash
+# Setup bot token, chat id, and thread id (topic)
 awkit tg setup
 
-# 2. Gửi thử tin nhắn kiểm tra
+# Send a test message
 awkit tg send "Hello from AWKit!"
 
-# 3. Gửi đến chat/topic cụ thể
+# Send to a specific chat/topic
 awkit tg send "Hello" --chat -100123456789 --topic 1234
 ```
 
-## 🧠 GitNexus Code Intelligence
+---
 
-AWKit (từ bản cập nhật tích hợp mới) sử dụng **GitNexus** làm engine cung cấp Code Intelligence & Knowledge Graph cho AI Agent. Sau khi chạy `npm install` AWKit, GitNexus sẽ sẵn sàng để dùng ngay.
+## GitNexus Code Intelligence
 
-Để kích hoạt GitNexus trên bất kỳ project nào anh/chị đang code:
+AWKit integrates GitNexus for code intelligence and knowledge graphs.
 
 ```bash
-# 1. Quét toàn bộ project để tạo knowledge graph (chỉ cần chạy lần đầu hoặc khi cấu trúc code thay đổi lớn)
+# 1) Build a knowledge graph for a project (first run or after major structure changes)
 npx @duytransipher/gitnexus analyze
 
-# 2. Setup MCP servers và skills tự động cho Antigravity và các editors khác:
+# 2) Setup MCP servers and editor integrations
 npx @duytransipher/gitnexus setup
 ```
 
-AI agent của hệ thống cũng tự động gọi qua cổng GitNexus bằng MCP Tools để tự phân tích rủi ro trước khi commit!
+---
 
-## 📦 Skill Packs
+## Skill Packs
 
 ```bash
 awkit list-packs
@@ -212,17 +212,8 @@ awkit enable-pack marketing
 awkit enable-pack creator-studio
 ```
 
-## 🏗️ Versioning
-
-| Version | Name | Notes |
-|---------|------|-------|
-| 4.x | AWF v4 | Shell-based, `awf-` prefix skills |
-| 5.x | Antigravity v5 | Node.js, Symphony integration |
-| 6.x | AWF v6 | main-awf, multiple sources |
-| **1.1.x** | **AWKit v1.1.9** | **Single source of truth, Native CLI, Telegram Integration** |
-| **1.5.x** | **AWKit v1.5.0** | **Unified Orchestration, Symphony 1.5.0, 7-Gate Intelligence** |
-| **12.5.x** | **Antigravity v12.5** | **Mindful Checkpoints (TP-ITER, TP-SCOPE, TP-REST), @duytransipher/gitnexus** |
-
 ---
 
-*AWKit Antigravity Workflow Kit · Created by leejungkiin*
+## License
+
+MIT

package/bin/awk.js

@@ -38,7 +38,9 @@ const HOME = process.env.HOME || process.env.USERPROFILE;
 const { generateClineRules, generateClineWorkflows, generateClineSkills } = require('./cline-generators');
 const { generateCodexAgentsMd, generateCodexSkills, generateCodexAgents } = require('./codex-generators');
 const { generateClaudeRules, generateClaudeSkills } = require('./claude-generators');
+const { generateCursorRules, generateCursorSkills } = require('./cursor-generators');
 const { cmdGate } = require('../scripts/automation-gate');
+const { cmdObsidian } = require('../scripts/obsidian-sync');
 
 // ─── Platform Definitions ──────────────────────────────────────────────────
 
@@ -85,6 +87,24 @@ const PLATFORMS = {
         dirs: {
             skills: '.claude/skills',
         },
+    },
+    qwen: {
+        name: 'Qwen Code',
+        globalRoot: path.join(HOME, '.qwen'),
+        rulesFile: null,
+        versionFile: path.join(HOME, '.qwen', 'awk_version'),
+        dirs: {
+            skills: 'skills',
+        },
+    },
+    cursor: {
+        name: 'Cursor AI',
+        globalRoot: process.cwd(), // Local to project
+        rulesFile: '.cursor/rules/antigravity-rules.mdc',
+        versionFile: '.cursor/awk_version',
+        dirs: {
+            skills: '.cursor/rules',
+        },
     }
 };
 
@@ -516,6 +536,8 @@ function cmdInstall(args = []) {
         if (args.includes('--cline') || args.includes('cline')) selectedPlatforms.push('cline');
         if (args.includes('--codex') || args.includes('-x')) selectedPlatforms.push('codex');
         if (args.includes('--claude-code') || args.includes('--claude') || args.includes('-c') || args.includes('claude')) selectedPlatforms.push('claude');
+        if (args.includes('--qwen') || args.includes('--qwen-code') || args.includes('-q') || args.includes('qwen')) selectedPlatforms.push('qwen');
+        if (args.includes('--cursor') || args.includes('cursor')) selectedPlatforms.push('cursor');
 
         const pIdx = args.indexOf('--platform');
         let legacyArg = null;
@@ -534,25 +556,29 @@ function cmdInstall(args = []) {
         if (isUpdate) {
             selectedPlatforms = [getActivePlatform()];
         } else {
-            const platformOrder = ['antigravity', 'cline', 'codex', 'claude'];
+            const platformOrder = ['antigravity', 'cline', 'codex', 'claude', 'qwen', 'cursor'];
             const defaultPlatform = getActivePlatform();
             const defaultChoice = String(Math.max(platformOrder.indexOf(defaultPlatform), 0) + 1);
-            log(`${C.cyan}Select platforms to install (e.g., type "1,2", "all", or "1,2,3,4"):${C.reset}`);
+            log(`${C.cyan}Select platforms to install (e.g., type "1,2", "all", or "1-6"):${C.reset}`);
             log(`  1. Gemini Code Assist (antigravity)`);
             log(`  2. Cline (VS Code)`);
             log(`  3. Codex CLI (codex)`);
             log(`  4. Claude Code (.claude/)`);
-            log(`  5. All of the above`);
+            log(`  5. Qwen Code (~/.qwen/)`);
+            log(`  6. Cursor AI (.cursor/rules/)`);
+            log(`  7. All of the above`);
             log(`${C.gray}Press Enter to install only the active platform: ${PLATFORMS[defaultPlatform].name}.${C.reset}`);
             const choice = promptChoice('Choice', defaultChoice).trim().toLowerCase();
 
-            if (choice === '5' || choice === 'all') {
+            if (choice === '7' || choice === 'all') {
                 selectedPlatforms = Object.keys(PLATFORMS);
             } else {
                 if (choice.includes('1')) selectedPlatforms.push('antigravity');
                 if (choice.includes('2')) selectedPlatforms.push('cline');
                 if (choice.includes('3')) selectedPlatforms.push('codex');
                 if (choice.includes('4')) selectedPlatforms.push('claude');
+                if (choice.includes('5')) selectedPlatforms.push('qwen');
+                if (choice.includes('6')) selectedPlatforms.push('cursor');
             }
         }
     }
@@ -614,6 +640,10 @@ function cmdInstall(args = []) {
             const claudeTemplateSrc = path.join(AWK_ROOT, 'core', 'CLAUDE.md');
             const claudeRulesDest = path.join(target, plat.rulesFile);
             generateClaudeRules(claudeTemplateSrc, claudeRulesDest);
+        } else if (platform === 'cursor') {
+            info('Generating Cursor AI .mdc rules...');
+            const cursorRulesDest = path.join(target, plat.rulesFile);
+            generateCursorRules(path.join(AWK_ROOT, 'core', 'GEMINI.md'), cursorRulesDest);
         }
 
         // 3. Backup and install workflows
@@ -668,7 +698,11 @@ function cmdInstall(args = []) {
                 const agentsDest = path.join(target, plat.dirs.agents);
                 generateCodexAgents(skillsSrc, agentsDest, coreSkills);
             } else if (platform === 'claude') {
-                generateClaudeSkills(skillsSrc, skillsDest, coreSkills);
+                generateClaudeSkills(skillsSrc, skillsDest, coreSkills, 'Claude Code');
+            } else if (platform === 'qwen') {
+                generateClaudeSkills(skillsSrc, skillsDest, coreSkills, 'Qwen Code'); // Shares the same format with Claude
+            } else if (platform === 'cursor') {
+                generateCursorSkills(skillsSrc, skillsDest, coreSkills);
             } else {
                 const skillCount = copySelectedSkillDirs(skillsSrc, skillsDest, coreSkills);
                 ok(`${skillCount} core skill files installed`);
@@ -2298,6 +2332,25 @@ function buildProjectIdentity(projectName, projectType, cwd, date) {
             list: 'Your List Name',
             card: 'Your Card Name',
         },
+        automation: {
+            autoQA: true,
+            maxSelfCorrectionLoops: 3,
+            telegram: {
+                enabled: true,
+                chatId: "",
+                topicId: "",
+                triggers: { git_push: true, task_complete: false, deploy: true }
+            },
+            trello: {
+                enabled: true,
+                autoSync: true,
+                triggers: { task_complete: true, milestone: true, blocked: true }
+            },
+            git: {
+                autoCommit: true,
+                autoPush: true
+            }
+        },
         projectStage: 'development',
         codingStandards: cfg.codingStandards,
         projectGoals: [],
@@ -2505,6 +2558,8 @@ async function cmdInit(forceFlag = false) {
         const currentIdentity = JSON.parse(fs.readFileSync(identityPath, 'utf8'));
         if (!currentIdentity.automation) {
             currentIdentity.automation = {
+                autoQA: true,
+                maxSelfCorrectionLoops: 3,
                 telegram: {
                     enabled: true,
                     chatId: "",
@@ -2523,6 +2578,12 @@ async function cmdInit(forceFlag = false) {
             };
             fs.writeFileSync(identityPath, JSON.stringify(currentIdentity, null, 2) + '\n');
             ok('Added Automation config placeholder to .project-identity');
+        } else if (currentIdentity.automation.autoQA === undefined) {
+            // Update existing automation block with new QA fields
+            currentIdentity.automation.autoQA = true;
+            currentIdentity.automation.maxSelfCorrectionLoops = 3;
+            fs.writeFileSync(identityPath, JSON.stringify(currentIdentity, null, 2) + '\n');
+            ok('Updated Automation config with autoQA defaults in .project-identity');
         }
     } catch (_) { /* ignore */ }
 
@@ -3867,6 +3928,10 @@ const [, , command, ...args] = process.argv;
         case 'gate':
             cmdGate(args);
             break;
+        case 'obsidian':
+        case 'obs':
+            cmdObsidian(args);
+            break;
         case 'admin':
             cmdAdmin();
             break;

package/bin/claude-generators.js

@@ -25,7 +25,7 @@ function generateClaudeRules(sourcePath, destPath) {
  * Preserves full directory structure: <skill-name>/SKILL.md + scripts/ + templates/
  * Injects YAML frontmatter if missing.
  */
-function generateClaudeSkills(srcDir, destDir, selectedSkills = null) {
+function generateClaudeSkills(srcDir, destDir, selectedSkills = null, platformName = 'Claude Code') {
     if (!fs.existsSync(srcDir)) return;
 
     fs.mkdirSync(destDir, { recursive: true });
@@ -51,7 +51,7 @@ function generateClaudeSkills(srcDir, destDir, selectedSkills = null) {
 
         count++;
     }
-    console.log(`✅ Generated ${count} Claude Code skills in ${destDir}`);
+    console.log(`✅ Generated ${count} ${platformName} skills in ${destDir}`);
 }
 
 /**