packwise-skills 1.0.0 → 1.2.0

package/README.md

@@ -1,295 +1,404 @@
-# packwise-skills
-
-> One skill that turns your AI into a build consultant — scan, recommend, package, and audit any project.
-
-<p align="center">
-  <a href="https://github.com/Thomas520TOM/packwise-skills/commits/main">
-    <img src="https://img.shields.io/github/last-commit/Thomas520TOM/packwise-skills?style=flat-square&logo=github" alt="last commit">
-  </a>
-  <a href="https://github.com/Thomas520TOM/packwise-skills/blob/main/LICENSE">
-    <img src="https://img.shields.io/badge/license-MIT-blue?style=flat-square&logo=github" alt="license">
-  </a>
-  <a href="https://github.com/Thomas520TOM/packwise-skills/tree/main/sub-skills">
-    <img src="https://img.shields.io/badge/skills-44-brightgreen?style=flat-square" alt="skills">
-  </a>
-  <a href="#supported-platforms">
-    <img src="https://img.shields.io/badge/platforms-20%2B-orange?style=flat-square" alt="platforms">
-  </a>
-  <a href="#supported-platforms">
-    <img src="https://img.shields.io/badge/frameworks-40%2B-purple?style=flat-square" alt="frameworks">
-  </a>
-  <a href="#tested-framework-versions">
-    <img src="https://img.shields.io/badge/tested-10-success?style=flat-square" alt="tested">
-  </a>
-  <a href="#installation">
-    <img src="https://img.shields.io/badge/works%20with-Claude%20Code%20%7C%20OpenCode%20%7C%20Cursor-yellow?style=flat-square" alt="works with">
-  </a>
-</p>
-
----
-
-**Packwise** is a universal build & packaging skill for AI-assisted development.  Instead of your AI guessing at build commands and hoping for the best, Packwise gives it a structured, consultant-grade workflow that scans your project, asks the right questions, recommends solutions with reasoning, and executes builds with mandatory security audits — across 20+ platforms and 40+ frameworks.
-
----
-
-## Why This Exists
-
-Packaging software is where most AI coding assistants fail. They suggest outdated flags, forget platform-specific quirks, skip credential scans, and have no concept of a proper build plan. **Packwise fixes this** by turning your AI into a structured build consultant with real domain knowledge.
-
-<div align="center">
-
-| Without Packwise | With Packwise |
-|:---:|:---:|
-| `"Try running npm run build"` | Scans project → identifies framework/version → recommends with reasoning |
-| No security checks | Mandatory credential scan, `.env` detection, source map cleanup |
-| Guesses platform differences | Asks target platform, arch, signing, output — all upfront |
-| One-shot answer | Full workflow: recommend → alternatives → confirm → execute |
-| No post-build verification | Mandatory audit: credentials, integrity, file structure |
-
-</div>
-
----
-
-## How It Works
-
-Packwise runs a **consultant-style 8-step workflow** — the same process a human build engineer would follow:
-
-| Step | Action | Result |
-|:----:|--------|--------|
-| **1** | **Scan** — detect framework, language, dependencies, `.env` files | Project analysis |
-| **2** | **Intake** — report findings, ask 12 structured questions | User preferences |
-| **3** | **Analyze** — combine scan + answers + online research (if needed) | Strategy options |
-| **4** | **Recommend** — present best approach with reasoning + alternatives | Decision support |
-| **5** | **Confirm** — user selects, final build plan generated | Confirmed plan |
-| **6** | **Execute** — load sub-skill, run build commands | Installers / packages |
-| **7** | **Audit** — credentials, `.env`, `.map`, package integrity | Security report |
-| **8** | **Report** — structured final build report | Delivery |
-
----
-
-## Key Advantages
-
-Packwise is more than a build script. It's a **complete packaging intelligence layer** that works across your entire stack.
-
-| Capability | What It Means |
-|------------|---------------|
-| **44 sub-skills** | Deep, platform-specific knowledge — not generic advice |
-| **20+ platforms** | Desktop, mobile, web, backend, AI/ML, CLI, plugins, embedded, cloud |
-| **Mandatory security** | Every build ends with a credential and integrity audit |
-| **Consultant workflow** | Recommend → confirm → execute, never auto-builds without approval |
-| **Version-verified** | Build commands checked against npm, PyPI, crates.io, official registries |
-| **CI/CD templates** | GitHub Actions and GitLab CI configs included in every sub-skill |
-| **Cross-tool support** | Works with Claude Code, OpenCode, Cursor, Codex CLI, and more |
-
----
-
-## Installation
-
-### npm (Recommended)
-
-```bash
-npm install -g packwise-skills
-```
-
-Then invoke in your AI agent:
-
-```
-> package my Electron app for Windows
-```
-
-<details>
-<summary><strong>Git clone</strong> — install from source</summary>
-
-```bash
-# User-level (all projects)
-cd ~/.claude/
-git clone https://github.com/Thomas520TOM/packwise-skills.git skills/packwise
-
-# Project-level (this project only)
-cd your-project/
-mkdir -p .claude/skills/
-git clone https://github.com/Thomas520TOM/packwise-skills.git .claude/skills/packwise
-```
-</details>
-
-<details>
-<summary><strong>Curl one-liner</strong> — install with a single command</summary>
-
-```bash
-curl -fsSL https://raw.githubusercontent.com/Thomas520TOM/packwise-skills/main/install.sh | bash
-```
-</details>
-
-<details>
-<summary><strong>Other AI tools</strong> — OpenCode, Cursor, Hermes, Codex CLI, WorkBuddy</summary>
-
-**OpenCode** — copy to `.opencode/skills/packwise/` and reference in prompts:
-```bash
-mkdir -p .opencode/skills/packwise/
-cp skill.md audit.md .opencode/skills/packwise/
-cp -r sub-skills/ .opencode/skills/packwise/
-```
-
-**Cursor** — add to `.cursor/skills/` or reference via `@packwise` in prompts.
-
-**Hermes / LangChain Agents** — add to `hermes.config.yaml`:
-```yaml
-skills:
-  - path: /path/to/packwise/
-    name: packwise
-```
-
-**Codex CLI** — copy to project root as `PACKWISE.md` (auto-read as context).
-
-**WorkBuddy** — copy to `~/.workbuddy/skills/` or use `/project:packwise`.
-
-**Any LLM agent** — copy `skill.md` + `sub-skills/` to your project and prompt:
-```
-Read skills/package-skill.md and help me package this project
-```
-
-Full instructions: [INSTALL.md](INSTALL.md)
-</details>
-
----
-
-## Supported Platforms
-
-| Category | Frameworks | Build Verified |
-|----------|-----------|:--------------:|
-| **Desktop** | Electron 43, Tauri 2.11, Qt, Flutter Desktop, Pake, Neutralinojs | Electron, Tauri |
-| **Mobile** | Android (Kotlin), iOS/iPadOS, HarmonyOS NEXT, Flutter 3.44, React Native 0.86, Capacitor 8 | — |
-| **Web** | Vite 8, Next.js 16, PWA, Serverless/Edge, Monorepo, WebAssembly | Vite, Next.js |
-| **Backend** | Node.js 26, Python 3.12, Go 1.26, Rust, Java/Spring Boot 3.5, PHP/Laravel | Node, Python, Rust, Java |
-| **AI/ML** | PyTorch, TensorFlow, ONNX Runtime, Ollama, llama.cpp, vLLM | — |
-| **CLI/SDK** | PyInstaller, Nuitka, npm/PyPI/crates.io publishing | PyInstaller |
-| **Plugins** | Chrome/Firefox Extensions, VS Code, JetBrains | — |
-| **Embedded** | ESP32, STM32, ROS/ROS2, Car Infotainment | — |
-| **Cloud** | Docker, Kubernetes, CI/CD (GitHub Actions) | — |
-| **Wearables** | watchOS, Wear OS, Galaxy Watch | — |
-
-> Checked = build tested on real projects. — = documentation verified against official sources.
-
----
-
-## Architecture
-
-```
-skill.md (Main Orchestrator)
-│
-├─ Step 1: Project Scan ─────── Detect framework, language, deps, env
-│
-├─ Step 2: Intake ───────────── Ask 12 questions (platform, arch, signing...)
-│  ├─ Part A: Project Summary    ← scan results displayed
-│  ├─ Part B: Questions          ← interactive options with defaults
-│  └─ Part C: Confirmation       ← summary table for user approval
-│
-├─ Step 3: Analyze & Research ── Combine data + online research if needed
-│
-├─ Step 4: Recommend ⭐ ──────── Best solution + alternatives + reasoning
-│
-├─ Step 5: Confirm ───────────── User selects → final build plan
-│
-├─ Step 6: Execute ───────────── Load sub-skill → run build commands
-│  ├─ sub-skills/desktop/       Electron, Tauri, Qt, games, VR...
-│  ├─ sub-skills/mobile/        Android, iOS, Flutter, RN, watchOS...
-│  ├─ sub-skills/web/           Vite, Next.js, PWA, WASM...
-│  ├─ sub-skills/backend/       Node, Python, Go, Rust, Java, PHP
-│  ├─ sub-skills/ai/            PyTorch, Ollama, llama.cpp
-│  ├─ sub-skills/cli/           PyInstaller, npm/PyPI publishing
-│  ├─ sub-skills/plugins/       Chrome, VS Code, JetBrains
-│  ├─ sub-skills/embedded/      ESP32, STM32, ROS, car
-│  ├─ sub-skills/security/      Pentest tools, scanners
-│  ├─ sub-skills/cloud/         Docker, K8s, CI/CD
-│  └─ sub-skills/cross-platform/ .NET MAUI, KMP
-│
-├─ Step 7: Audit (mandatory) ── Credentials, .env, .map, package check
-│
-└─ Step 8: Final Report ─────── Build report with all results
-```
-
----
-
-## Security Model
-
-Packwise enforces security at every stage — no build completes without a clean audit.
-
-| Stage | Check |
-|-------|-------|
-| **Pre-build scan** | Detect `.env` files, hardcoded API keys, secrets in source |
-| **Build execution** | Delete source maps, exclude `.env` from package, clean test data |
-| **Post-build audit** | Verify no credentials, `.map` files, or `.env` in final package |
-| **Network check** | Optional: verify no unexpected outbound connections |
-
----
-
-## What's Inside
-
-### 44 Sub-Skills — Every Major Platform Covered
-
-Each sub-skill contains:
-- **Version-verified** build commands (checked against official registries)
-- **Step-by-step** packaging workflows with copy-paste examples
-- **Common pitfalls** table with solutions (from real build testing)
-- **CI/CD** configuration templates (GitHub Actions, GitLab CI)
-- **Security** best practices specific to the platform
-
-### Tested Framework Versions
-
-| Framework | Version | Verified |
-|-----------|:-------:|:--------:|
-| Electron | 43.x | ✅ |
-| Tauri | 2.11.x | ✅ |
-| Vite | 8.1.3 | ✅ |
-| Next.js | 16.2.10 | ✅ |
-| Node.js | 26 LTS | ✅ |
-| Python | 3.12 | ✅ |
-| Rust | 1.96 | ✅ |
-| Java | 21 LTS | ✅ |
-| React Native | 0.86.x | — |
-| Flutter | 3.44.x | — |
-| Capacitor | 8.x | — |
-| Go | 1.26 | — |
-
----
-
-## Contributing
-
-Contributions are welcome. Before submitting, please:
-
-1. Write all instructions in **English** only
-2. Verify framework versions against **official registries** (npm, PyPI, GitHub Releases)
-3. Include a **Common Pitfalls** table in every new sub-skill
-4. Test build commands when possible
-5. Never commit secrets, API keys, or credentials
-
-```bash
-git clone https://github.com/YOUR_USER/packwise-skills.git
-cd packwise-skills
-git checkout -b feat/my-improvement
-# edit skill.md or sub-skills/
-git commit -m "feat: add [framework] support"
-git push origin feat/my-improvement
-# open a PR against main
-```
-
----
-
-## License
-
-<div align="center">
-
-[![License: MIT](https://img.shields.io/badge/License-MIT-blue?style=flat-square&logo=github)](https://opensource.org/licenses/MIT)
-
-This project is licensed under the [MIT License](LICENSE).
-
-</div>
-
----
-
-<div align="center">
-  Built with care for the AI-assisted development community.
-  <br><br>
-  <a href="https://github.com/Thomas520TOM/packwise-skills">GitHub</a> · <a href="https://github.com/Thomas520TOM/packwise-skills/issues">Issues</a> · <a href="https://github.com/Thomas520TOM/packwise-skills/blob/main/INSTALL.md">Install Guide</a>
-  <br>
-</div>
+# packwise-skills
+
+> One skill that turns your AI into a build consultant — scan, recommend, package, and audit any project.
+
+<p align="center">
+  <a href="https://github.com/Thomas520TOM/packwise-skills/commits/main">
+    <img src="https://img.shields.io/github/last-commit/Thomas520TOM/packwise-skills?style=flat-square&logo=github" alt="last commit">
+  </a>
+  <a href="https://github.com/Thomas520TOM/packwise-skills/blob/main/LICENSE">
+    <img src="https://img.shields.io/badge/license-MIT-blue?style=flat-square&logo=github" alt="license">
+  </a>
+  <a href="https://github.com/Thomas520TOM/packwise-skills/tree/main/sub-skills">
+    <img src="https://img.shields.io/badge/skills-44-brightgreen?style=flat-square" alt="skills">
+  </a>
+  <a href="#supported-platforms">
+    <img src="https://img.shields.io/badge/platforms-20%2B-orange?style=flat-square" alt="platforms">
+  </a>
+  <a href="#supported-platforms">
+    <img src="https://img.shields.io/badge/frameworks-40%2B-purple?style=flat-square" alt="frameworks">
+  </a>
+  <a href="#tested-framework-versions">
+    <img src="https://img.shields.io/badge/tested-10-success?style=flat-square" alt="tested">
+  </a>
+  <a href="#installation">
+    <img src="https://img.shields.io/badge/works%20with-Claude%20Code%20%7C%20Cursor%20%7C%20OpenCode%20%7C%20Copilot-yellow?style=flat-square" alt="works with">
+  </a>
+</p>
+
+---
+
+**Packwise** is a universal build & packaging skill pack that gives your AI a structured, consultant-grade workflow — scanning, recommending, and executing builds with mandatory security audits across 20+ platforms.
+
+---
+
+## Why This Exists
+
+Most AI coding assistants treat build as an afterthought — they suggest a command and hope for the best. **Packwise** gives your AI a real packaging workflow.
+
+<div align="center">
+
+| Without Packwise | With Packwise |
+|:---:|:---:|
+| `npm run build` and pray | Scans project, identifies framework/version, recommends with reasoning |
+| No security checks | Mandatory credential scan, `.env` detection, source map cleanup |
+| Ignores platform specifics | Asks target platform, arch, signing, output upfront |
+| One-shot, no follow-up | Recommend → confirm → execute, with alternatives |
+
+</div>
+
+---
+
+## Quick Demo
+
+```
+You:  > package my Electron app for Windows and macOS
+
+AI:   Scan Results:
+      - Framework: Electron 31 + React 18 + Express + SQLite
+      - Language: TypeScript | Complexity: L2
+      Is this correct? [Correct / Add / Exclude / Correct]
+
+You:  Correct
+
+AI:   [Popup] Target users? → General consumers
+      [Popup] Platform? → Windows + macOS
+      [Popup] Architecture? → Win x64 | macOS Universal
+      ... (17 interactive questions via popups)
+
+AI:   RECOMMENDED: Electron 31 + electron-builder
+      Alternative A: Tauri (3-10MB, needs Rust rewrite)
+      Which approach? [Recommended / Alt A / Alt B / Custom]
+
+You:  1
+
+AI:   FINAL BUILD PLAN | Reply 'yes' to start
+
+You:  yes
+
+AI:   [Popup] Logo? → /path/to/icon.png | Crop corners? → Yes
+      [Popup] Output? → ./release/
+      [Popup] Config changes: [1] Add electron-builder.yml [2] ...
+      [Popup] Approve? → Approve all
+
+AI:   Building... Done
+      Audit: No credentials, no .env, no .map
+      Output:
+        MyApp-v1.0.0-windows-x64.exe
+        MyApp-v1.0.0-macos-universal.dmg
+```
+
+---
+
+## How It Works
+
+A **9-step build workflow**:
+
+| Step | Action | Result |
+|:----:|--------|--------|
+| **1** | **Scan** — detect framework, language, dependencies, `.env` files | Project analysis |
+| **2** | **Intake** — build overview confirmation, then 18 questions (some per-platform) | User preferences |
+| **3** | **Analyze** — combine scan + answers + online research (if needed) | Strategy options |
+| **4** | **Recommend** — present best approach with reasoning + alternatives | Decision support |
+| **5** | **Confirm** — user selects, final build plan generated | Confirmed plan |
+| **6** | **Prepare** — detect config gaps, propose fixes, user approves each | Ready-to-build project |
+| **7** | **Execute** — load sub-skill, run build commands | Installers / packages |
+| **8** | **Audit** — credentials, `.env`, `.map`, package integrity | Security report |
+| **9** | **Report** — structured final build report | Delivery |
+
+---
+
+## Key Advantages
+
+What makes Packwise different from a generic build command:
+
+| Capability | What It Means |
+|------------|---------------|
+| **44 sub-skills** | Platform-specific knowledge, not generic advice |
+| **20+ platforms** | Desktop, mobile, web, backend, AI/ML, CLI, plugins, embedded, cloud |
+| **Mandatory security** | Every build ends with a credential and integrity audit |
+| **Consultant workflow** | Recommends, confirms, then executes — no auto-builds |
+| **Version-verified** | Build commands checked against npm, PyPI, crates.io, official registries |
+| **Selective install** | Install only the skills you need via `--only` |
+| **11 agents** | Claude Code, Cursor, OpenCode, Copilot, and 7 more |
+| **Interactive Q&A** | All questions via popup UI, not text dumps |
+
+---
+
+## Installation
+
+### npx (No Install Required)
+
+Run directly without installing globally:
+
+```bash
+npx packwise-skills
+```
+
+### npm (Recommended)
+
+```bash
+npm install -g packwise-skills
+```
+
+### Curl One-liner
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/Thomas520TOM/packwise-skills/main/install.sh | bash
+```
+
+### Git Clone
+
+```bash
+# User-level (all projects)
+cd ~/.claude/
+git clone https://github.com/Thomas520TOM/packwise-skills.git skills/packwise
+
+# Project-level (this project only)
+cd your-project/
+mkdir -p .claude/skills/
+git clone https://github.com/Thomas520TOM/packwise-skills.git .claude/skills/packwise
+```
+
+Then invoke in your AI agent:
+
+```
+> package my Electron app for Windows
+```
+
+### Updating
+
+```bash
+npx packwise-skills update
+```
+
+This automatically detects your installation method and updates to the latest version.
+
+---
+
+### Selective Installation
+
+Install only the sub-skills you need with `--only`. Core files (`skill.md`, `audit.md`, `CLAUDE.md`) are always installed.
+
+**By category:**
+```bash
+npx packwise-skills --only desktop,mobile
+npx packwise-skills --only backend,cloud
+```
+
+**By specific framework:**
+```bash
+npx packwise-skills --only electron,tauri,react-native
+npx packwise-skills --only docker,kubernetes
+```
+
+**Mix both:**
+```bash
+npx packwise-skills --only electron,mobile
+```
+
+Works with curl too:
+```bash
+curl -fsSL https://raw.githubusercontent.com/Thomas520TOM/packwise-skills/main/install.sh | bash -s -- --only electron,mobile
+```
+
+**Categories:** `desktop` `mobile` `web` `backend` `ai` `cli` `plugins` `embedded` `security` `cloud` `cross-platform`
+
+**Frameworks:** `electron` `tauri` `android` `ios` `react-native` `flutter-mobile` `docker` `kubernetes` `spa` `ssr` and [more](bin/packwise.js)
+
+---
+
+<details>
+<summary><strong>Other AI tools</strong> — OpenCode, Cursor, Codex CLI, OpenClaw, WorkBuddy, Trae, Hermes, GitHub Copilot</summary>
+
+**OpenCode** — copy to `.opencode/skills/packwise/` and reference in prompts:
+```bash
+mkdir -p .opencode/skills/packwise/
+cp skill.md audit.md .opencode/skills/packwise/
+cp -r sub-skills/ .opencode/skills/packwise/
+```
+
+**Cursor** — add to `.cursor/skills/` or reference via `@packwise` in prompts.
+
+**Codex CLI** — copy to project root as `PACKWISE.md` (auto-read as context).
+
+**OpenClaw** — copy to `.openclaw/skills/packwise/` and reference in prompts:
+```bash
+mkdir -p .openclaw/skills/packwise/
+cp skill.md audit.md .openclaw/skills/packwise/
+cp -r sub-skills/ .openclaw/skills/packwise/
+```
+
+**WorkBuddy** — copy to `~/.workbuddy/skills/` or use `/project:packwise`.
+
+**Trae** — copy to `.trae/skills/packwise/` and reference in prompts:
+```bash
+mkdir -p .trae/skills/packwise/
+cp skill.md audit.md .trae/skills/packwise/
+cp -r sub-skills/ .trae/skills/packwise/
+```
+
+**Hermes / LangChain Agents** — add to `hermes.config.yaml`:
+```yaml
+skills:
+  - path: /path/to/packwise/
+    name: packwise
+```
+
+**GitHub Copilot** — copy to `.copilot/skills/packwise/` and reference in prompts:
+```bash
+mkdir -p .copilot/skills/packwise/
+cp skill.md audit.md .copilot/skills/packwise/
+cp -r sub-skills/ .copilot/skills/packwise/
+```
+
+**Any LLM agent** — copy `skill.md` + `sub-skills/` to your project and prompt:
+```
+Read skills/skill.md and help me package this project
+```
+
+Full instructions: [INSTALL.md](INSTALL.md)
+</details>
+
+---
+
+## Supported Platforms
+
+| Category | Frameworks | Build Verified |
+|----------|-----------|:--------------:|
+| **Desktop** | Electron 43, Tauri 2.11, Qt, Flutter Desktop, Pake, Neutralinojs | Electron, Tauri |
+| **Mobile** | Android (Kotlin), iOS/iPadOS, HarmonyOS NEXT, Flutter 3.44, React Native 0.86, Capacitor 8 | — |
+| **Web** | Vite 8, Next.js 16, PWA, Serverless/Edge, Monorepo, WebAssembly | Vite, Next.js |
+| **Backend** | Node.js 26, Python 3.12, Go 1.26, Rust, Java/Spring Boot 3.5, PHP/Laravel | Node, Python, Rust, Java |
+| **AI/ML** | PyTorch, TensorFlow, ONNX Runtime, Ollama, llama.cpp, vLLM | — |
+| **CLI/SDK** | PyInstaller, Nuitka, npm/PyPI/crates.io publishing | PyInstaller |
+| **Plugins** | Chrome/Firefox Extensions, VS Code, JetBrains | — |
+| **Embedded** | ESP32, STM32, ROS/ROS2, Car Infotainment | — |
+| **Cloud** | Docker, Kubernetes, CI/CD (GitHub Actions) | — |
+| **Wearables** | watchOS, Wear OS, Galaxy Watch | — |
+
+> Checked = build tested on real projects. — = documentation verified against official sources.
+
+---
+
+## Architecture
+
+```
+skill.md (Main Orchestrator)
+│
+├─ 1. Scan ─────────── Detect framework, language, deps, env
+│
+├─ 2. Intake ────────── Build overview → confirm scope → ask 18 questions
+│
+├─ 3. Analyze ───────── Combine scan + answers + online research
+│
+├─ 4. Recommend ⭐ ──── Best approach + alternatives + reasoning
+│
+├─ 5. Confirm ───────── User selects → final build plan
+│
+├─ 6. Prepare ───────── Logo + output location → detect config gaps → user approves
+│
+├─ 7. Execute ───────── Load sub-skill → run platform-specific build
+│  │
+│  ├─ desktop/ ──────── Electron, Tauri, Qt, Flutter Desktop, games, VR
+│  ├─ mobile/ ───────── Android, iOS, HarmonyOS, Flutter, React Native
+│  ├─ web/ ──────────── Vite, Next.js, PWA, Serverless, WASM
+│  ├─ backend/ ──────── Node.js, Python, Go, Rust, Java, PHP
+│  ├─ ai/ ───────────── PyTorch, Ollama, llama.cpp, vLLM
+│  ├─ cli/ ──────────── PyInstaller, npm/PyPI publishing
+│  ├─ plugins/ ──────── Chrome, VS Code, JetBrains
+│  ├─ embedded/ ─────── ESP32, STM32, ROS, car infotainment
+│  ├─ cloud/ ────────── Docker, Kubernetes, CI/CD
+│  ├─ security/ ─────── Pentest tools, scanners
+│  └─ cross-platform/ ─ .NET MAUI, Kotlin Multiplatform
+│
+├─ 8. Audit 🔒 ──────── Credentials, .env, .map, package integrity
+│
+└─ 9. Report ────────── Structured final build report
+```
+
+---
+
+## Security Model
+
+Packwise enforces security at every stage — no build completes without a clean audit.
+
+| Stage | Check |
+|-------|-------|
+| **Pre-build scan** | Detect `.env` files, hardcoded API keys, secrets in source |
+| **Build execution** | Delete source maps, exclude `.env` from package, clean test data |
+| **Post-build audit** | Verify no credentials, `.map` files, or `.env` in final package |
+| **Network check** | Optional: verify no unexpected outbound connections |
+
+---
+
+## What's Inside
+
+### 44 Sub-Skills — Every Major Platform Covered
+
+Each sub-skill contains:
+- **Version-verified** build commands (checked against official registries)
+- **Step-by-step** packaging workflows with copy-paste examples
+- **Common pitfalls** table with solutions (from real build testing)
+- **CI/CD** configuration templates (GitHub Actions, GitLab CI)
+- **Security** best practices specific to the platform
+
+### Tested Framework Versions
+
+| Framework | Version | Verified |
+|-----------|:-------:|:--------:|
+| Electron | 43.x | ✅ |
+| Tauri | 2.11.x | ✅ |
+| Vite | 8.1.3 | ✅ |
+| Next.js | 16.2.10 | ✅ |
+| Node.js | 26 LTS | ✅ |
+| Python | 3.12 | ✅ |
+| Rust | 1.96 | ✅ |
+| Java | 21 LTS | ✅ |
+| React Native | 0.86.x | — |
+| Flutter | 3.44.x | — |
+| Capacitor | 8.x | — |
+| Go | 1.26 | — |
+
+---
+
+## Contributing
+
+Contributions are welcome. Before submitting, please:
+
+1. Write all instructions in **English** only
+2. Verify framework versions against **official registries** (npm, PyPI, GitHub Releases)
+3. Include a **Common Pitfalls** table in every new sub-skill
+4. Test build commands when possible
+5. Never commit secrets, API keys, or credentials
+
+```bash
+git clone https://github.com/YOUR_USER/packwise-skills.git
+cd packwise-skills
+git checkout -b feat/my-improvement
+# edit skill.md or sub-skills/
+git commit -m "feat: add [framework] support"
+git push origin feat/my-improvement
+# open a PR against main
+```
+
+---
+
+## License
+
+<div align="center">
+
+[![License: MIT](https://img.shields.io/badge/License-MIT-blue?style=flat-square&logo=github)](https://opensource.org/licenses/MIT)
+
+This project is licensed under the [MIT License](LICENSE).
+
+</div>
+
+---
+
+<div align="center">
+  Built with care for the AI-assisted development community.
+  <br><br>
+  <a href="https://github.com/Thomas520TOM/packwise-skills">GitHub</a> · <a href="https://github.com/Thomas520TOM/packwise-skills/issues">Issues</a> · <a href="https://github.com/Thomas520TOM/packwise-skills/blob/main/INSTALL.md">Install Guide</a>
+  <br>
+</div>