opencode-skills-collection 3.1.7 → 3.1.9

package/bundled-skills/docs/contributors/skill-anatomy.md

@@ -45,10 +45,12 @@ The frontmatter is at the very top, wrapped in `---`:
 ---
 name: my-skill-name
 description: "Brief description of what this skill does"
+category: development
 risk: safe
 source: community
 source_repo: owner/repo
 source_type: community
+date_added: "YYYY-MM-DD"
 ---
 ```
 
@@ -66,6 +68,12 @@ source_type: community
 - **Length:** Keep it under 200 characters
 - **Example:** `"Stripe payment integration patterns including checkout, subscriptions, and webhooks"`
 
+#### `category`
+- **What it is:** Primary grouping used by generated indexes and catalog surfaces
+- **Format:** Lowercase category label
+- **Example:** `category: development`
+- **Note:** Tooling can infer a category for legacy skills, but new skills should declare one explicitly.
+
 #### `risk`
 - **What it is:** The safety classification of the skill
 - **Values:** `none` | `safe` | `critical` | `offensive` | `unknown`
@@ -95,6 +103,12 @@ source_type: community
 - **Examples:** `source_type: official`, `source_type: community`
 - **Rule:** `self` means no external README repo credit is required
 
+#### `date_added`
+- **What it is:** Date the skill entered this repository
+- **Format:** `YYYY-MM-DD`
+- **Example:** `date_added: "2026-03-06"`
+- **Note:** Validation treats this as advisory for legacy content, but new contributions should include it.
+
 ### Optional Fields
 
 Some skills include additional metadata:
@@ -103,10 +117,12 @@ Some skills include additional metadata:
 ---
 name: my-skill-name
 description: "Brief description"
+category: development
 risk: safe
 source: community
 source_repo: owner/repo
 source_type: community
+date_added: "YYYY-MM-DD"
 author: "your-name-or-handle"
 tags: ["react", "typescript", "testing"]
 tools: [claude, cursor, gemini]
@@ -355,17 +371,17 @@ references/
 ## Skill Size Guidelines
 
 ### Minimum Viable Skill
-- **Frontmatter:** name + description
+- **Frontmatter:** standard fields (`name`, `description`, `category`, `risk`, `source`, `date_added`)
 - **Content:** 100-200 words
 - **Sections:** Overview + Instructions
 
 ### Standard Skill
-- **Frontmatter:** name + description
+- **Frontmatter:** standard fields (`name`, `description`, `category`, `risk`, `source`, `date_added`)
 - **Content:** 300-800 words
 - **Sections:** Overview + When to Use + Instructions + Examples
 
 ### Comprehensive Skill
-- **Frontmatter:** name + description + optional fields
+- **Frontmatter:** standard fields plus `source_repo`/`source_type` for external GitHub-derived skills and optional fields where useful
 - **Content:** 800-2000 words
 - **Sections:** All recommended sections
 - **Extras:** Scripts, examples, templates

package/bundled-skills/docs/integrations/jetski-cortex.md

@@ -1,9 +1,9 @@
 ---
 title: Jetski/Cortex + Gemini Integration Guide
-description: "Use antigravity-awesome-skills with Jetski/Cortex without hitting context-window overflow with 1,684+ skills."
+description: "Use antigravity-awesome-skills with Jetski/Cortex without hitting context-window overflow with 1,693+ skills."
 ---
 
-# Jetski/Cortex + Gemini: safe integration with 1,684+ skills
+# Jetski/Cortex + Gemini: safe integration with 1,693+ skills
 
 This guide shows how to integrate the `antigravity-awesome-skills` repository with an agent based on **Jetski/Cortex + Gemini** (or similar frameworks) **without exceeding the model context window**.
 
@@ -23,7 +23,7 @@ Never do:
 - concatenate all `SKILL.md` content into a single system prompt;
 - re-inject the entire library for **every** request.
 
-With 1,684+ skills, this approach fills the context window before user messages are even added, causing truncation.
+With 1,693+ skills, this approach fills the context window before user messages are even added, causing truncation.
 
 ---
 

package/bundled-skills/docs/integrations/jetski-gemini-loader/README.md

@@ -21,7 +21,7 @@ This example shows one way to integrate **antigravity-awesome-skills** with a Je
 - How to enforce a **maximum number of skills per turn** via `maxSkillsPerTurn`.
 - How to choose whether to **truncate or error** when too many skills are requested via `overflowBehavior`.
 
-This pattern avoids context overflow when you have 1,684+ skills installed.
+This pattern avoids context overflow when you have 1,693+ skills installed.
 
 Manifest contract references:
 

package/bundled-skills/docs/maintainers/categorization-implementation.md

@@ -5,14 +5,16 @@
 ### 1. **Intelligent Auto-Categorization Script**
 Created [`tools/scripts/auto_categorize_skills.py`](../../tools/scripts/auto_categorize_skills.py) that:
 - Analyzes skill names and descriptions
-- Matches against keyword libraries for 13 categories
+- Matches against keyword libraries that seeded the current generated category metadata
 - Automatically assigns meaningful categories
 - Removes "uncategorized" bulk assignment
 
-**Results:**
+**Historical initial-run result:**
 - ✅ 776 skills auto-categorized
 - ✅ 46 already had categories preserved
-- ✅ 124 remaining uncategorized (edge cases)
+- ✅ 124 remained uncategorized at the time of that run
+
+For current counts, use `skills_index.json`; the active repository has grown beyond this historical snapshot.
 
 ### 2. **Category Distribution**
 
@@ -26,20 +28,8 @@ security: 4
 
 **After:**
 ```
-Backend: 164          ████████████████
-Web Dev: 107          ███████████
-Automation: 103       ███████████
-DevOps: 83            ████████
-AI/ML: 79             ████████
-Content: 47           █████
-Database: 44          █████
-Testing: 38           ████
-Security: 36          ████
-Cloud: 33             ███
-Mobile: 21            ██
-Game Dev: 15          ██
-Data Science: 14      ██
-Uncategorized: 126    █
+Generated category metadata is now derived from the current skills_index.json.
+Do not preserve these historical counts in user-facing docs.
 ```
 
 ### 3. **Updated Index Generation**
@@ -54,16 +44,16 @@ Modified [`tools/scripts/generate_index.py`](../../tools/scripts/generate_index.
 **Home Page Changes:**
 - ✅ Categories sorted by skill count (most first)
 - ✅ "Uncategorized" moved to bottom
-- ✅ Each shows count: "Backend (164)", "Web Dev (107)"
+- ✅ Each shows counts computed from the generated index
 - ✅ Much easier to navigate
 
 **Updated Code:**
 - [`apps/web-app/src/pages/Home.tsx`](../../apps/web-app/src/pages/Home.tsx) - Smart category sorting
 - Sorts categories by count using categoryStats
 - Uncategorized always last
-- Displays count in dropdown
+- Displays generated counts in dropdown
 
-### 5. **Categorization Keywords** (13 Categories)
+### 5. **Categorization Keywords** (seed buckets)
 
 | Category | Key Keywords |
 |----------|--------------|
@@ -97,16 +87,16 @@ Created [`smart-auto-categorization.md`](smart-auto-categorization.md) with:
 
 ### Better UX
 1. **Smarter Filtering**: Categories sorted by relevance
-2. **Visual Cues**: Shows count "(164 skills)""
+2. **Visual Cues**: Shows current generated counts
 3. **Uncategorized Last**: Put bad options out of sight
 4. **Meaningful Groups**: Find skills by actual function
 
 ### Example Workflow
 User wants to find database skills:
 1. Opens web app
-2. Sees filter dropdown: "Backend (164) | Database (44) | Web Dev (107)..."
-3. Clicks "Database (44)"
-4. Gets 44 relevant SQL/MongoDB/Postgres skills
+2. Sees filter dropdown with generated category counts
+3. Clicks the current database-related category
+4. Gets the current matching SQL/MongoDB/Postgres skills
 5. Done! 🎉
 
 ## 🚀 Usage

package/bundled-skills/docs/maintainers/repo-growth-seo.md

@@ -6,7 +6,7 @@ This document keeps the repository's GitHub-facing discovery copy aligned with t
 
 Preferred positioning:
 
-> Installable GitHub library of 1,684+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.
+> Installable GitHub library of 1,693+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and other AI coding assistants.
 
 Key framing:
 
@@ -20,7 +20,7 @@ Key framing:
 
 Preferred description:
 
-> Installable GitHub library of 1,684+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
+> Installable GitHub library of 1,693+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
 
 Preferred homepage:
 
@@ -28,7 +28,7 @@ Preferred homepage:
 
 Preferred social preview:
 
-- use a clean preview image that says `1,684+ Agentic Skills`;
+- use a clean preview image that says `1,693+ Agentic Skills`;
 - mention Claude Code, Cursor, Codex CLI, and Gemini CLI;
 - avoid dense text and tiny logos that disappear in social cards.
 

package/bundled-skills/docs/maintainers/skills-update-guide.md

@@ -72,7 +72,7 @@ The update process refreshes:
 - Canonical skills index (`skills_index.json`)
 - Compatibility mirror (`data/skills_index.json`)
 - Web app skills data (`apps\web-app\public\skills.json`)
-- All 1,684+ skills from the skills directory
+- All 1,693+ skills from the skills directory
 
 ## When to Update
 

package/bundled-skills/docs/maintainers/smart-auto-categorization.md

@@ -9,26 +9,28 @@ The skill collection now uses intelligent auto-categorization to eliminate "unca
 ✅ Current repository indexed through the generated catalog
 - Most skills are in meaningful categories
 - A smaller tail still needs manual review or better keyword coverage
-- 11 primary categories
-- Categories sorted by skill count (most first)
+- `skills_index.json` is the source of truth for current category labels and counts
+- Category filters should be derived from the generated index at build time
 
 ## Category Distribution
 
-| Category | Count | Examples |
-|----------|-------|----------|
-| Backend | 164 | Node.js, Django, Express, FastAPI |
-| Web Development | 107 | React, Vue, Tailwind, CSS |
-| Automation | 103 | Workflow, Scripting, RPA |
-| DevOps | 83 | Docker, Kubernetes, CI/CD, Git |
-| AI/ML | 79 | TensorFlow, PyTorch, NLP, LLM |
-| Content | 47 | Documentation, SEO, Writing |
-| Database | 44 | SQL, MongoDB, PostgreSQL |
-| Testing | 38 | Jest, Cypress, Unit Testing |
-| Security | 36 | Encryption, Authentication |
-| Cloud | 33 | AWS, Azure, GCP |
-| Mobile | 21 | React Native, Flutter, iOS |
-| Game Dev | 15 | Unity, WebGL, 3D |
-| Data Science | 14 | Pandas, NumPy, Analytics |
+Do not copy fixed counts into user-facing docs. To inspect the current distribution, generate it from the index:
+
+```bash
+node - <<'NODE'
+const fs = require('fs');
+const skills = JSON.parse(fs.readFileSync('skills_index.json', 'utf8'));
+const counts = new Map();
+for (const skill of skills) {
+  const category = skill.category || 'uncategorized';
+  counts.set(category, (counts.get(category) || 0) + 1);
+}
+console.log(`skills=${skills.length} categories=${counts.size}`);
+for (const [category, count] of [...counts.entries()].sort((a, b) => b[1] - a[1]).slice(0, 12)) {
+  console.log(`${category}: ${count}`);
+}
+NODE
+```
 
 ## How It Works
 
@@ -91,20 +93,17 @@ Sample changes:
 
 **After:**
 - Categories sorted by skill count (most first, "uncategorized" last)
-- Shows count: "Backend (164)" "Web Development (107)"
+- Shows counts from the generated index instead of hard-coded documentation numbers
 - Much easier to browse
 
 ### Example Dropdowns
 
 **Sorted Order:**
 1. All Categories
-2. Backend (164)
-3. Web Development (107)
-4. Automation (103)
-5. DevOps (83)
-6. AI/ML (79)
-7. ... more categories ...
-8. Uncategorized (126) ← at the end
+2. Highest-count generated category
+3. Next generated category
+4. ... more generated categories ...
+5. Uncategorized, if present, at the end
 
 ## For Skill Creators
 

package/bundled-skills/docs/users/bundles.md

@@ -1061,4 +1061,4 @@ Found a skill that should be in a bundle? Or want to create a new bundle? [Open
 
 ---
 
-_Last updated: June 2026 | Total Skills: 1,684+ | Total Bundles: 59_
+_Last updated: June 2026 | Total Skills: 1,693+ | Total Bundles: 59_

package/bundled-skills/docs/users/claude-code-skills.md

@@ -12,7 +12,7 @@ Install the library into Claude Code, then invoke focused skills directly in the
 
 ## Why use this repo for Claude Code
 
-- It includes 1,684+ skills instead of a narrow single-domain starter pack.
+- It includes 1,693+ skills instead of a narrow single-domain starter pack.
 - It supports the standard `.claude/skills/` path and the Claude Code plugin marketplace flow.
 - It also ships generated bundle plugins so teams can install focused packs like `Essentials` or `Security Developer` from the marketplace metadata.
 - It includes onboarding docs, bundles, and workflows so new users do not need to guess where to begin.

package/bundled-skills/docs/users/faq.md

@@ -103,11 +103,11 @@ No. The public site is a static GitHub Pages deploy.
 
 We classify skills so you know what you're running. These values map directly to the `risk:` field in every `SKILL.md` frontmatter:
 
-- 🔵 **`none`**: Pure reference or planning content — no shell commands, no mutations, no network access.
-- ⚪ **`safe`**: Community skills that are non-destructive (read-only, planning, code review, analysis).
-- 🔴 **`critical`**: Skills that modify files, drop data, use network scanners, or perform destructive actions. **Use with caution.**
-- 🟣 **`offensive`**: Security-focused offensive techniques (pentesting, exploitation). **Authorized use only** — always confirm the target is in scope.
-- ⬜ **`unknown`**: Legacy or unclassified content. Review the skill manually before use.
+- ⚪ **`unknown`**: Legacy or unclassified content. Review the skill manually before use.
+- 🟢 **`none`**: Pure reference or planning content — no shell commands, no mutations, no network access.
+- 🔵 **`safe`**: Non-destructive guidance such as read-only commands, planning, code review, and analysis.
+- 🟠 **`critical`**: Skills that modify files, drop data, use network scanners, or perform destructive actions. **Use with caution.**
+- 🔴 **`offensive`**: Security-focused offensive techniques (pentesting, exploitation). **Authorized use only** — always confirm the target is in scope.
 
 ### Can these skills hack my computer?
 

package/bundled-skills/docs/users/gemini-cli-skills.md

@@ -12,7 +12,7 @@ Install into the Gemini skills path, then ask Gemini to apply one skill at a tim
 
 - It installs directly into the expected Gemini skills path.
 - It includes both core software engineering skills and deeper agent/LLM-oriented skills.
-- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,684+ files.
+- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,693+ files.
 - It is useful whether you want a broad internal skill library or a single repo to test many workflows quickly.
 
 ## Install Gemini CLI Skills

package/bundled-skills/docs/users/getting-started.md

@@ -1,4 +1,4 @@
-# Getting Started with Antigravity Awesome Skills (V13.2.0)
+# Getting Started with Antigravity Awesome Skills (V13.4.0)
 
 **New here? This guide will help you supercharge your AI Agent in 5 minutes.**
 

package/bundled-skills/docs/users/kiro-integration.md

@@ -18,7 +18,7 @@ Kiro is AWS's agentic AI IDE that combines:
 
 Kiro's agentic capabilities are enhanced by skills that provide:
 
-- **Domain expertise** across 1,684+ specialized areas
+- **Domain expertise** across 1,693+ specialized areas
 - **Best practices** from Anthropic, OpenAI, Google, Microsoft, and AWS
 - **Workflow automation** for common development tasks
 - **AWS-specific patterns** for serverless, infrastructure, and cloud architecture

package/bundled-skills/docs/users/local-config.md

@@ -1,7 +1,7 @@
-# Local Skills Configuration
+# Local Skills Configuration Snapshot
 
-> **Current Status**: All 96 skills are available in the repository.  
-> **This Document**: Recommends 35 high-priority skills for typical usage.
+> **Historical snapshot**: This page preserves an older 35-skill local configuration recommendation from 2026-01-16. It is not the current repository catalog.
+> **Current catalog**: Use [`../../skills_index.json`](../../skills_index.json), [`../../CATALOG.md`](../../CATALOG.md), or the installer filters in the README for the active 1,684+ skill library.
 
 ## 📊 Recommended High-Priority Skills (35)
 
@@ -67,17 +67,17 @@ Skills actively used for your specific projects:
 
 ---
 
-## 🗂️ Repository Structure
+## 🗂️ Snapshot Structure
 
 ```
-skills/
-├── [96 active skills]     ← All skills available
-└── [4 symlinks]           ← docx, pdf, pptx, xlsx → official versions
+local snapshot/
+├── [96 active skills in this snapshot]
+└── [4 symlinks in this snapshot]
 ```
 
 ---
 
-## 📚 Other Available Skills (61)
+## 📚 Other Snapshot Skills (61)
 
 All other skills in the repository are available for use as needed. Some notable categories:
 
@@ -140,13 +140,13 @@ Miscellaneous:
 ## 🎯 Benefits of This Recommendation
 
 ✅ **Focused Guidance** - 35 high-priority skills for common workflows  
-✅ **Full Availability** - All 96 skills accessible when needed  
+✅ **Snapshot Availability** - All 96 skills from this older local set were accessible when needed
 ✅ **Balanced Coverage** - Core dev + AI/automation + frontend excellence  
 ✅ **Easy Discovery** - Categorized list of all other available skills
 
 ---
 
-**Last Updated**: 2026-01-16  
+**Snapshot Date**: 2026-01-16
 **Recommended Skills**: 35 high-priority  
-**Total Available**: 96 skills + 4 symlinks = 100 total  
+**Snapshot Total**: 96 skills + 4 symlinks = 100 total
 **Recent Additions to Recommendations**: `senior-fullstack`, `concise-planning`, `address-github-comments`, `javascript-mastery`, `workflow-automation`, `llm-app-patterns`, `autonomous-agent-patterns`, `prompt-library`

package/bundled-skills/docs/users/specialized-plugin-roadmap.md

@@ -17,9 +17,9 @@ That makes specialized plugins the better default product shape. A root plugin c
 
 ## Selection Method
 
-This pass evaluated the full local catalog in `data/skills_index.json`:
+This snapshot pass evaluated the then-current local catalog. For current catalog checks, use the canonical root `skills_index.json` and treat `data/skills_index.json` only as the compatibility mirror:
 
-- Total skills evaluated: 1,678.
+- Total skills evaluated in this snapshot: 1,678.
 - Broadest categories: development, cloud, AI/ML, security, business, workflow, content, marketing, automation, and web development.
 - Existing editorial bundles are all small and mostly plugin-compatible, which makes them a good starting point.
 - The stronger opportunity is to turn the best bundles into first-class product plugins with sharper names, richer descriptions, and optional app/MCP extensions.
@@ -71,7 +71,7 @@ These are promising and should be hardened after Tier 1.
 3. Rename or reframe bundle plugins as product plugins where the job is clear.
 4. Add richer `interface` metadata to the strongest plugin manifests: display name, short description, brand color, and default prompt.
 5. Add per-plugin quality gates:
-   - every skill exists in `data/skills_index.json`;
+  - every skill exists in canonical `skills_index.json`;
    - every skill is Codex-supported before Codex publication;
    - every skill is Claude-supported before Claude publication;
    - every plugin has a 5-10 skill target range unless it has a concrete reason to be larger;

package/bundled-skills/docs/users/usage.md

@@ -14,7 +14,7 @@ If you came in through a **Claude Code** or **Codex** plugin instead of a full l
 
 When you ran `npx antigravity-awesome-skills` or cloned the repository, you:
 
-✅ **Downloaded 1,684+ skill files** to your computer (default: `~/.agents/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)
+✅ **Downloaded 1,693+ skill files** to your computer (default: `~/.agents/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)
 ✅ **Made them available** to your AI assistant  
 ❌ **Did NOT enable them all automatically** (they're just sitting there, waiting)
 
@@ -34,7 +34,7 @@ Bundles are **curated groups** of skills organized by role. They help you decide
 
 **Analogy:**
 
-- You installed a toolbox with 1,684+ tools (✅ done)
+- You installed a toolbox with 1,693+ tools (✅ done)
 - Bundles are like **labeled organizer trays** saying: "If you're a carpenter, start with these 10 tools"
 - You can either **pick skills from the tray** or install that tray as a focused marketplace bundle plugin
 
@@ -212,7 +212,7 @@ Let's actually use a skill right now. Follow these steps:
 
 ## Step 5: Picking Your First Skills (Practical Advice)
 
-Don't try to use all 1,684+ skills at once. Here's a sensible approach:
+Don't try to use all 1,693+ skills at once. Here's a sensible approach:
 
 If you want a tool-specific starting point before choosing skills, use:
 
@@ -343,7 +343,7 @@ Usually no, but if your AI doesn't recognize a skill:
 
 ### "Can I load all skills into the model at once?"
 
-No. Even though you have 1,684+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
+No. Even though you have 1,693+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
 
 The intended pattern is:
 

package/bundled-skills/docs/users/visual-guide.md

@@ -34,7 +34,7 @@ antigravity-awesome-skills/
 ├── 📄 CONTRIBUTING.md                  ← Contributor workflow
 ├── 📄 CATALOG.md                       ← Full generated catalog
 │
-├── 📁 skills/                          ← 1,684+ skills live here
+├── 📁 skills/                          ← 1,693+ skills live here
 │   │
 │   ├── 📁 brainstorming/
 │   │   └── 📄 SKILL.md                 ← Skill definition
@@ -47,7 +47,7 @@ antigravity-awesome-skills/
 │   │   └── 📁 2d-games/
 │   │       └── 📄 SKILL.md             ← Nested skills also supported
 │   │
-│   └── ... (1,684+ total)
+│   └── ... (1,693+ total)
 │
 ├── 📁 apps/
 │   └── 📁 web-app/                     ← Interactive browser
@@ -100,7 +100,7 @@ antigravity-awesome-skills/
 
 ```
                     ┌─────────────────────────┐
-                    │  1,684+ SKILLS          │
+                    │  1,693+ SKILLS          │
                     └────────────┬────────────┘
                                  │
         ┌────────────────────────┼────────────────────────┐
@@ -201,7 +201,7 @@ If you want a workspace-style manual install instead, cloning into `.agent/skill
 │   ├── 📁 brainstorming/                 │
 │   ├── 📁 stripe-integration/            │
 │   ├── 📁 react-best-practices/          │
-│   └── ... (1,684+ total)                │
+│   └── ... (1,693+ total)                │
 └─────────────────────────────────────────┘
 ```
 

package/bundled-skills/docs/vietnamese/BUNDLES.vi.md

@@ -121,4 +121,4 @@ _Để tạo ra những trải nghiệm hoàn hảo đến từng pixel._
 
 ---
 
-_Để sử dụng một gói kỹ năng, chỉ cần copy tên các skill vào thư mục `.agent/skills` của bạn hoặc yêu cầu trợ lý AI sử dụng chúng._
+_Để sử dụng một gói kỹ năng, hãy cài repository một lần bằng `npx antigravity-awesome-skills`, rồi yêu cầu trợ lý AI sử dụng các skill được liệt kê trong gói._

package/bundled-skills/docs/vietnamese/CONTRIBUTING.vi.md

@@ -1,15 +1,15 @@
-# 🤝 Hướng dẫn Đóng góp - Phiên bản V3 Enterprise
+# 🤝 Hướng dẫn Đóng góp
 
 **Cảm ơn bạn đã muốn làm cho repository này trở nên tốt hơn!** Hướng dẫn này sẽ chỉ cho bạn chính xác cách thức đóng góp, ngay cả khi bạn là người mới đối với mã nguồn mở.  
-Với phiên bản V3, chúng tôi đã nâng cao các tiêu chuẩn về chất lượng. Vui lòng đọc kỹ **Tiêu chuẩn Chất lượng mới** bên dưới.
+Chúng tôi duy trì tiêu chuẩn chất lượng tự động cho skill và tài liệu. Vui lòng đọc kỹ **Quality Bar** bên dưới.
 
 ---
 
-## 🧐 "Quy chuẩn Chất lượng" (Quality Bar - Tiêu chuẩn V3)
+## 🧐 "Quy chuẩn Chất lượng" (Quality Bar)
 
-**Quan trọng đối với các skill mới:** Mỗi skill được gửi đi phải vượt qua **5 bước Kiểm tra Chất lượng** (xem `docs/vietnamese/QUALITY_BAR.md` để biết chi tiết):
+**Quan trọng đối với các skill mới:** Mỗi skill được gửi đi phải vượt qua **5 bước Kiểm tra Chất lượng** (xem `docs/vietnamese/QUALITY_BAR.vi.md` để biết chi tiết):
 
-1.  **Siêu dữ liệu (Metadata)**: Phần Frontmatter chính xác (`name`, `description`).
+1.  **Siêu dữ liệu (Metadata)**: Phần frontmatter chính xác (`name`, `description`, `category`, `risk`, `source`, `date_added`; thêm `source_repo` và `source_type` cho skill bắt nguồn từ GitHub bên ngoài).
 2.  **An toàn (Safety)**: Không chứa các lệnh gây hại mà không có nhãn rủi ro ("Risk").
 3.  **Rõ ràng (Clarity)**: Có phần "Khi nào nên dùng" (When to use) rõ ràng.
 4.  **Ví dụ (Examples)**: Ít nhất một ví dụ sử dụng có thể sao chép và dùng được ngay.
@@ -81,6 +81,9 @@ Mỗi kỹ năng đều cần cấu trúc cơ bản này. **Hãy sao chép mẫu
 ---
 name: my-awesome-skill
 description: "Mô tả ngắn gọn về chức năng của skill này"
+risk: safe
+source: community
+date_added: 2026-06-25
 ---
 
 # Tiêu đề Skill
@@ -112,16 +115,16 @@ code ví dụ ở đây
 - ❌ Không nên làm điều này
 ```
 
-#### Bước 4: Xác thực (BƯỚC V3 QUAN TRỌNG)
+#### Bước 4: Xác thực
 
 Chạy script xác thực (validation) tại máy của bạn. **Chúng tôi sẽ không chấp nhận các Pull Request (PR) thất bại ở bước kiểm tra này.**
 
 ```bash
-# Chế độ nhẹ (chỉ cảnh báo)
-python3 scripts/validate_skills.py
+# Chế độ thông thường
+npm run validate
 
 # Chế độ nghiêm ngặt (chế độ mà hệ thống CI sẽ chạy)
-python3 scripts/validate_skills.py --strict
+npm run validate:strict
 ```
 
 Bước này sẽ kiểm tra:
@@ -149,6 +152,9 @@ Tiết kiệm thời gian! Hãy sao chép bản mẫu này:
 ---
 name: your-skill-name
 description: "Mô tả trong một câu về chức năng của skill và khi nào cần dùng"
+risk: safe
+source: community
+date_added: 2026-06-25
 ---
 
 # Tên Kỹ năng của bạn