@qubiit/lmagent 2.5.0 → 2.5.6

package/CLAUDE.md

@@ -120,3 +120,5 @@ lmagent install   # Instalar skills, rules y workflows en el IDE
 lmagent doctor    # Verificar configuración
 lmagent version   # Mostrar versión
 ```
+
+> **Nota**: Si ejecutas sin instalar: `npx @qubiit/lmagent init`

package/README.md

@@ -19,41 +19,66 @@
 
 ## 🚀 Quick Start Guide
 
-Get your agent infrastructure up and running in less than 2 minutes.
+Get your universal agent infrastructure up and running in minutes.
 
-### Option A: Direct Execution (No Install)
-The fastest way to enhance your current project.
+### 📋 Prerequisites
+- **Node.js 18+** installed.
+- An existing project (or create one with `npm init`).
+
+### Option A: Per-Project Setup (Recommended)
+Use `npx` to run LMAgent without installing it globally. This ensures you always use the latest version and keeps your project dependencies clean.
+
+```bash
+# 1. Initialize LMAgent (Copies AGENTS.md, CLAUDE.md & Configs)
+#    This gives your AI Agent the "Context" it needs to understand the skills.
+npx @qubiit/lmagent init
+
+# 2. Install Skills & Rules to your IDE
+#    This configures .cursor, .vscode, or .windsurf with the actual executable prompts.
+npx @qubiit/lmagent install
+
+# 3. Verify System Status
+npx @qubiit/lmagent doctor
+```
+
+### Option B: Global Installation
+If you prefer having the `lmagent` command available globally in your terminal:
 
 ```bash
-# Initialize project (copies CLAUDE.md, AGENTS.md, config, etc.)
-npx lmagent init
+# 1. Install Global Package
+npm install -g @qubiit/lmagent
 
-# Install skills, rules & workflows into your IDE
-npx lmagent install
+# 2. Run Commands Directly
+lmagent init
+lmagent install
+lmagent doctor
+```
 
-# Verify everything is correctly configured
-npx lmagent doctor
+### Option C: Local Development (Contributors)
+If you are developing the LMAgent framework itself:
+
+```bash
+git clone https://github.com/QuBit/lmagent.git
+cd lmagent
+npm install
+npm link
+lmagent install
 ```
 
-### Option B: Local Development Setup
-If you want to contribute or fork the project:
+---
 
-1.  **Clone the Repository**
-    ```bash
-    git clone https://github.com/QuBit/lmagent.git
-    cd lmagent
-    ```
+## 🛠️ CLI Reference
 
-2.  **Install Dependencies**
-    ```bash
-    npm install
-    ```
+LMAgent includes a powerful CLI to manage your AI context.
 
-3.  **Link Globally**
-    ```bash
-    npm link
-    lmagent install
-    ```
+| Command | Usage | Description |
+| :--- | :--- | :--- |
+| **`init`** | `npx @qubiit/lmagent init` | Initializes the project. Copies `AGENTS.md` (catalog) and `CLAUDE.md` to your root. |
+| **`install`** | `npx @qubiit/lmagent install` | **Core Command**. Installs selected Skills, Rules & Workflows into your IDE configuration (Cursor, VSCode, Windsurf, etc.). |
+| **`update`** | `npx @qubiit/lmagent update` | Alias for `install`. Use this to refresh your skills when new versions are released. |
+| **`doctor`** | `npx @qubiit/lmagent doctor` | Verifies your environment, checking for correct file structures using `validate_skills` logic. |
+| **`validate`** | `npx @qubiit/lmagent validate` | Scans all `SKILL.md` files for syntax errors or missing required fields. |
+| **`create-skill`** | `npx @qubiit/lmagent create-skill` | Interactive wizard to generate a new Skill structure best practices. |
 
 ---
 
@@ -84,12 +109,19 @@ graph TD
 | Skill Name | Description | Tools Included |
 | :--- | :--- | :--- |
 | **ai-agent-engineer** | Expert in building LLM-based systems & MCP servers. | `create-agent`, `scaffold-mcp` |
+| **api-designer** | Design REST/GraphQL contracts, OpenAPI standards. | `scaffold-api`, `lint-openapi` |
 | **architect** | System design, scalable patterns, cloud infrastructure. | `design-system`, `review-architecture` |
 | **automation-engineer** | n8n workflows, Zapier integration, scripting. | `deploy-n8n`, `check-webhook` |
 | **backend-engineer** | API design, Database schema, Authentication. | `scaffold-api`, `optimize-query` |
+| **bmad-methodology** | Scale-Adaptive Intelligence, project kickoff, complexity classification. | `classify-level`, `kickoff-project` |
+| **browser-agent** | Web automation, scraping, UI testing with Playwright. | `scrape-site`, `automate-flow` |
+| **code-reviewer** | Static analysis, logic verification, clean code standards. | `review-pr`, `analyze-complexity` |
 | **data-engineer** | ETL pipelines, SQL optimization, Data warehousing. | `analyze-schema`, `run-migration` |
 | **devops-engineer** | CI/CD, Docker, Kubernetes, Terraform. | `docker-build`, `k8s-deploy` |
+| **document-generator** | Programmatic PDF/DOCX/XLSX generation. | `gen-pdf`, `gen-report` |
 | **frontend-engineer** | React, Next.js, Tailwind, State Management. | `scaffold-component`, `check-accessibility` |
+| **git-workflow** | Branch management, conventional commits, release flow. | `feature-start`, `release-prep` |
+| **mcp-builder** | Build MCP servers, tools, and resources. | `new-mcp-server`, `test-tool` |
 | **mobile-engineer** | React Native, Expo, iOS/Android build pipelines. | `build-ios`, `debug-android` |
 | **orchestrator** | High-level task planning and agent coordination. | `plan-task`, `delegate-subtask` |
 | **performance-engineer** | Profiling, load testing, optimization. | `run-lighthouse`, `profile-memory` |
@@ -98,12 +130,15 @@ graph TD
 | **qa-engineer** | E2E testing (Playwright), Unit tests, QA strategy. | `run-playwright`, `generate-test-plan` |
 | **scrum-master** | Agile ceremonies, sprint planning, retrospective. | `start-sprint`, `generate-retro` |
 | **security-analyst** | Vulnerability scanning, code auditing, OWASP. | `scan-vulnerabilities`, `audit-code` |
+| **seo-auditor** | Technical SEO, Core Web Vitals, accessibility audit. | `audit-seo`, `check-meta` |
+| **spec-driven-dev** | Spec-first development pipeline: SPECIFY → PLAN → TASKS → IMPLEMENT → VERIFY. | `create-spec`, `validate-spec` |
+| **supabase-expert** | Supabase architecture, RLS, Edge Functions. | `init-supabase`, `deploy-edge` |
+| **swe-agent** | Autonomous issue resolution, trajectory logging, Edit-Lint-Test loops. | `resolve-issue`, `trajectory-log` |
+| **systematic-debugger** | Methodical 4-phase debugging (RCA). | `debug-session`, `analyze-logs` |
 | **tech-lead** | Code review, technical decision making, mentoring. | `review-pr`, `enforce-standards` |
 | **technical-writer** | Documentation, API refs, user guides. | `generate-docs`, `update-readme` |
+| **testing-strategist** | Test planning, pyramid strategy, coverage goals. | `plan-testing`, `define-coverage` |
 | **ux-ui-designer** | Design systems, user flow, prototyping. | `analyze-ux`, `generate-palette` |
-| **bmad-methodology** | Scale-Adaptive Intelligence, project kickoff, complexity classification. | `classify-level`, `kickoff-project` |
-| **swe-agent** | Autonomous issue resolution, trajectory logging, Edit-Lint-Test loops. | `resolve-issue`, `trajectory-log` |
-| **spec-driven-dev** | Spec-first development pipeline: SPECIFY → PLAN → TASKS → IMPLEMENT → VERIFY. | `create-spec`, `validate-spec` |
 
 
 ### 2. 📜 Rules (Context & Guardrails)
@@ -155,18 +190,42 @@ LMAgent creates a **Single Source of Truth** in your home directory.
 
 ### 🧩 Multi-IDE Support
 
-| IDE / Agent | Support Level | Config Path |
-| :--- | :--- | :--- |
+
 | **Cursor** | ✅ Full | `.cursor/` |
 | **Windsurf** | ✅ Full | `.windsurf/` |
 | **VSCode / Copilot** | ✅ Full | `.github/` |
 | **Zed** | ✅ Full | `.rules/` |
 | **Continue** | ✅ Full | `.continue/` |
 | **Trae** | ✅ Full | `.trae/` |
-| **Antigravity** | ✅ Full | `.antigravity/` |
-| **Cline / Roo Code** | ✅ Full | `.clinerules/` |
+| **Antigravity** | ✅ Full | `.agent/` |
+| **Cline / Roo Code** | ✅ Full | `.clinerules/` / `.roo/` |
 | **Claude Code** | ✅ Full | `.claude/` |
 | **Qodo** | ✅ Full | `agents/` |
+| **Amp / Kimi / Replit** | ✅ Full | `.agents/` |
+| **Augment** | ✅ Full | `.augment/` |
+| **OpenHands** | ✅ Full | `.openhands/` |
+| **Goose** | ✅ Full | `.goose/` |
+| **Mistral Vibe** | ✅ Full | `.vibe/` |
+| **Envoid (OpenClaw)** | ✅ Full | `openclaw.json` |
+| **CodeBuddy** | ✅ Full | `.codebuddy/` |
+| **Command Code** | ✅ Full | `.commandcode/` |
+| **Crush** | ✅ Full | `.crush/` |
+| **Droid** | ✅ Full | `.factory/` |
+| **Junie** | ✅ Full | `.junie/` |
+| **iFlow** | ✅ Full | `.iflow/` |
+| **Kilo Code** | ✅ Full | `.kilocode/` |
+| **Kiro** | ✅ Full | `.kiro/` |
+| **Kode** | ✅ Full | `.kode/` |
+| **MCPJam** | ✅ Full | `.mcpjam/` |
+| **Mux** | ✅ Full | `.mux/` |
+| **Pi** | ✅ Full | `.pi/` |
+| **Qoder** | ✅ Full | `.qoder/` |
+| **Qwen Code** | ✅ Full | `.qwen/` |
+| **Trae CN** | ✅ Full | `.trae-cn/` |
+| **Zencoder** | ✅ Full | `.zencoder/` |
+| **Neovate** | ✅ Full | `.neovate/` |
+| **Pochi** | ✅ Full | `.pochi/` |
+| **AdaL** | ✅ Full | `.adal/` |
 
 ---
 
@@ -180,10 +239,10 @@ Need a custom agent? Use the interactive generator:
 
 ```bash
 # Verify structure of existing skills
-python validate_skills.py
+npx @qubiit/lmagent validate
 
 # Create a new skill interactively
-python create_skill.py
+npx @qubiit/lmagent create-skill
 ```
 This will generate the standard directory structure and `SKILL.md` template for you.
 

package/install.js

@@ -1,4 +1,4 @@
-#!/usr/bin/env node
+#!/usr/bin/env node
 
 const fs = require('fs');
 const path = require('path');
@@ -335,9 +335,9 @@ const IDE_CONFIGS = [
 ];
 
 program
-    .name('lmagent-skills')
+    .name('lmagent')
     .description('CLI para instalar skills y reglas de LMAgent')
-    .version('2.5.0'); // Version bump
+    .version('2.5.6'); // Version bump
 
 program.command('install')
     .description('Instalar skills, rules y workflows en el IDE del proyecto')

package/package.json

@@ -3,7 +3,7 @@
   "publishConfig": {
     "access": "public"
   },
-  "version": "2.5.0",
+  "version": "2.5.6",
   "description": "CLI to install LMAgent skills and rules into your IDE",
   "main": "install.js",
   "bin": {
@@ -32,4 +32,4 @@
     "gradient-string": "^3.0.0",
     "inquirer": "^8.2.6"
   }
-}
+}

package/scripts/create_skill.js

@@ -1,7 +1,7 @@
 #!/usr/bin/env node
 
 /**
- * LMAgent Skill Generator — v2.3.0
+ * LMAgent Skill Generator — v2.5.6
  * 
  * Genera la estructura completa de un nuevo skill interactivamente.
  * 
@@ -212,7 +212,7 @@ Antes de considerar una tarea terminada, verifica TODO:
 
 // ─── Main ─────────────────────────────────────────────────────
 async function main() {
-    console.log(c.bold('\n🛠️  LMAgent Skill Generator v2.3.0\n'));
+    console.log(c.bold('\n🛠️  LMAgent Skill Generator v2.5.6\n'));
 
     const prompt = createPrompt();
 

package/scripts/validate_skills.js

@@ -1,7 +1,7 @@
 #!/usr/bin/env node
 
 /**
- * LMAgent Skills Validator — v2.3.0
+ * LMAgent Skills Validator — v2.5.6
  * 
  * Valida la integridad de todos los skills del framework.
  * Verifica: frontmatter YAML, campos obligatorios, estructura de directorio.