specweave 0.1.8 → 0.3.0

package/README.md

@@ -3,7 +3,7 @@
 > **Spec-Driven Development Framework** - Where specifications and documentation are the source of truth
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Version](https://img.shields.io/badge/version-0.1.8-blue.svg)](https://github.com/anton-abyzov/specweave/releases/tag/v0.1.8)
+[![Version](https://img.shields.io/badge/version-0.2.0-blue.svg)](https://github.com/anton-abyzov/specweave/releases/tag/v0.2.0)
 [![Status](https://img.shields.io/badge/status-beta-blue.svg)]()
 [![Website](https://img.shields.io/badge/website-spec--weave.com-green.svg)](https://spec-weave.com)
 
@@ -28,15 +28,18 @@
 
 ## ✨ Key Features
 
-- 🤖 **10 Specialized Agents** - PM, Architect, DevOps, QA, Security, SRE, Tech Lead, and more (all pre-installed!)
-- 🎯 **35+ AI Skills** - Technology stacks, integrations, utilities (all pre-installed!)
-- 📦 **Pre-Installed Components** - Everything ready immediately after `specweave init`
-- 🧪 **4-Level Testing** - Specification → Feature → Component → Automated tests
-- 📝 **Living Documentation** - Auto-updates via Claude Code hooks
-- 🎨 **Diagram Generation** - C4 Model diagrams (Context, Container, Component)
+- 🤖 **Autonomous & Smart** - Just works! Agents ask clarifying questions, review output, validate quality—minimal interaction required
+- ⚡ **Seamless Workflow** - Auto-resume, auto-close, progress tracking—natural flow without overhead
+- 🎯 **10 Agents + 35+ Skills** - PM, Architect, DevOps, QA, Security work in parallel (minimizes context usage). Easily extensible!
+- 🔧 **Universal Support** - Works with Claude (native), Cursor, Gemini CLI, Codex, Copilot, and ANY AI tool (100% market coverage)
+  - **Claude Code**: Native agents/skills pre-installed in `.claude/`
+  - **Other tools**: Accessible via universal AGENTS.md adapter
+- 🧪 **Complete Test Coverage** - 4-level strategy from specs to integration tests (APIs, UIs, CLIs, libraries)
+- 📚 **Living Documentation** - Specs auto-update after every operation and test—always in sync with code
+- 🎨 **Visual Architecture** - C4 Model diagrams (Context, Container, Component)
 - 🔄 **Tool Integration** - Sync with JIRA, Azure DevOps, GitHub
-- 🏢 **Brownfield Ready** - Analyze and document existing codebases
-- 🌐 **Framework Agnostic** - Works with TypeScript, Python, Go, Rust, Java, C#
+- 🏢 **Brownfield Excellence** - The hardest problem solved: merge with existing docs, create complex architecture (ADRs, HLDs, RFCs), maintain living documentation, safe regression prevention
+- 🌐 **Framework Agnostic** - Works with TypeScript, Python, Go, Rust, Java, C#—any tech stack
 
 ---
 
@@ -46,7 +49,13 @@
 
 - **Node.js 18+** (`node --version`)
 - **npm 9+** (`npm --version`)
-- **Claude Code** (Claude Sonnet 4.5 recommended)
+- **Any AI coding tool**:
+  - Claude Code (Claude Sonnet 4.5 - full automation)
+  - Cursor (Claude Sonnet 3.7 / GPT-4 - semi-automation)
+  - Gemini CLI (Gemini 2.5 Pro, 1M context - semi-automation)
+  - Codex (GPT-5-Codex - semi-automation)
+  - GitHub Copilot (OpenAI models - basic automation)
+  - Or ANY AI (ChatGPT web, Gemini web, Claude web, etc. - manual workflow)
 
 ### Quick Install
 
@@ -90,12 +99,15 @@ specweave init my-saas
 ### Available Commands
 
 ```bash
-specweave init [project]           # Create new project with ALL components
+specweave init [project]           # Create new project in subdirectory
+specweave init .                   # Initialize in current directory (brownfield)
 specweave --version                # Show version
 specweave --help                   # Show help
 ```
 
-**Note**: All 10 agents and 35+ skills are copied to your project during `init` - ready to use immediately!
+**Note**:
+- **Claude Code**: All 10 agents and 35+ skills installed natively in `.claude/` - ready to use immediately!
+- **Other tools**: Universal AGENTS.md adapter generated - works with Cursor, Gemini CLI, Codex, Copilot, and ANY AI!
 
 ---
 
@@ -104,20 +116,21 @@ specweave --help                   # Show help
 **CRITICAL**: SpecWeave uses **EXPLICIT SLASH COMMANDS** - type them to activate the framework!
 
 ```bash
-# Initialize project - ALL components pre-installed!
+# Initialize project (Claude Code native installation)
 npx specweave init my-app
 cd my-app
 
-# Everything ready immediately:
+# For Claude Code - everything native and ready immediately:
 # ✅ 10 agents in .claude/agents/
 # ✅ 35+ skills in .claude/skills/
 # ✅ 10 slash commands in .claude/commands/
+# (Other tools get AGENTS.md adapter instead)
 
 # Open Claude Code and use slash commands:
 
-User: /inc "Next.js authentication with email and OAuth"
+User: /specweave inc "Next.js authentication with email and OAuth"
     ↓
-SpecWeave: 🔷 SpecWeave Active (/increment)
+SpecWeave: 🔷 SpecWeave Active (/specweave.increment)
 
            🚀 Creating increment 0001-user-authentication...
            📝 Using nextjs skill (already installed!)
@@ -143,23 +156,33 @@ SpecWeave: 🤖 Implementing based on specifications
 ✅ Tests: tests/auth/
 ✅ Docs: Updated automatically
 
-User: /done 0001  # Close increment with slash command
+User: /specweave done 0001  # Close increment with slash command
 ✅ Increment 0001 closed successfully
 ```
 
-**How it works** (append-only increment workflow: 0001 → 0002 → 0003):
-1. `specweave init` → ALL components pre-installed (10 agents + 35+ skills)
-2. **Use `/inc "feature"`** → PM creates specs + plan + auto-generates tasks
-3. **Use `/build 0001`** → Execute implementation (hooks after EVERY task)
-4. **Use `/validate 0001`** → Optional quality check (LLM-as-judge)
-5. **Use `/done 0001`** → PM validates 3 gates (tasks ✅ + tests ✅ + docs ✅)
-6. All components ready - no waiting, no installation
-
-**Why slash commands?** Auto-activation doesn't work reliably - slash commands ensure SpecWeave ALWAYS activates when you want it.
+**How it works** (smart append-only workflow: 0001 → 0002 → 0003):
+1. `specweave init` → Detects your AI tool and configures appropriately
+   - **Claude Code**: Native components installed (10 agents + 35+ skills)
+   - **Other tools**: Universal AGENTS.md adapter generated
+2. **Use `/specweave inc "feature"`** (Claude) or "Read AGENTS.md and create increment" (other tools)
+   - PM creates specs + plan + auto-generates tasks
+   - **Smart**: Auto-closes previous increment if PM gates pass
+3. **Use `/specweave do` or `/specweave do 0001`** → Execute implementation (hooks after EVERY task in Claude)
+   - **Smart**: Auto-resumes from next incomplete task
+4. **Use `/specweave progress`** → Check status, task completion %, next action
+5. **Use `/specweave validate 0001`** → Optional quality check (LLM-as-judge)
+6. Repeat: `/specweave inc "next"` → Auto-closes if ready, creates next increment
+
+**Why smart workflow?**
+- ✅ No manual `/specweave done` needed (auto-closes on next `/specweave inc`)
+- ✅ No task tracking needed (`/specweave do` auto-resumes)
+- ✅ `/specweave progress` shows exactly where you are
+- ✅ Natural flow: finish → start next
+- ✅ Namespaced commands avoid collisions in brownfield projects
 
 ---
 
-## 🤖 Agents (10 Total - All Pre-Installed!)
+## 🤖 Agents (10 Total)
 
 SpecWeave includes **10 specialized AI agents** that work with slash commands and during implementation:
 
@@ -176,17 +199,19 @@ SpecWeave includes **10 specialized AI agents** that work with slash commands an
 | **performance** | Performance Engineer - optimization | Performance issues, profiling |
 | **diagrams-architect** | Diagram Expert - C4 Model, Mermaid | Creating diagrams (via diagrams-generator skill) |
 
-**All agents pre-installed** in `.claude/agents/` after `specweave init` - ready to use immediately!
+**Agent Access**:
+- **Claude Code**: All agents pre-installed natively in `.claude/agents/` - ready to use immediately!
+- **Other tools**: Agents documented in universal AGENTS.md - reference roles manually
 
 ---
 
-## 🎯 Skills (35+ Total - All Pre-Installed!)
+## 🎯 Skills (35+ Total)
 
 SpecWeave includes **35+ AI skills** that work with slash commands:
 
 ### Core Framework Skills
 - **specweave-detector** - Slash command documentation
-- **increment-planner** - Plan features via `/inc` or `/increment` command
+- **increment-planner** - Plan features via `/specweave inc` command
 - **skill-router** - Route requests to appropriate skills
 - **context-loader** - Load relevant specifications
 - **role-orchestrator** - Coordinate multiple agents
@@ -216,7 +241,11 @@ SpecWeave includes **35+ AI skills** that work with slash commands:
 - **brownfield-analyzer** - Analyze existing codebases
 - **brownfield-onboarder** - Merge existing documentation
 
-**And many more!** All skills pre-installed in `.claude/skills/` after `specweave init`.
+**And many more!**
+
+**Skill Access**:
+- **Claude Code**: All skills pre-installed natively in `.claude/skills/` - ready to use immediately!
+- **Other tools**: Skills documented in universal AGENTS.md - reference capabilities manually
 
 **See**: [Complete skill list](https://spec-weave.com/docs/skills) on spec-weave.com
 
@@ -227,7 +256,6 @@ SpecWeave includes **35+ AI skills** that work with slash commands:
 ```
 specweave/
 ├── .specweave/                  # Framework configuration
-│   ├── config.yaml              # Project configuration
 │   ├── cache/                   # Performance cache
 │   ├── docs/                    # 5-pillar documentation structure
 │   │   ├── README.md
@@ -239,7 +267,7 @@ specweave/
 │   │   │   ├── delivery/        # Roadmap, release plans
 │   │   │   ├── operations/      # Runbooks, SLOs, monitoring
 │   │   │   └── governance/      # Security, compliance
-│   │   └── public/              # Published docs (MkDocs)
+│   │   └── public/              # Published docs (Docusaurus)
 │   │       ├── overview/
 │   │       ├── guides/
 │   │       ├── api/
@@ -297,47 +325,110 @@ specweave/
 # Option A: Comprehensive (Enterprise) - 500-600+ pages upfront
 # Option B: Incremental (Startup) - Build as you go
 
-# 2. Plan increment with slash command (PM-led process)
-/inc "user authentication"
-# Alias for /increment
+# 2. Plan increment (PM-led, auto-closes previous if ready)
+/specweave inc "user authentication"
+# Alias: /specweave increment
 # PM-led: Market research → spec.md → plan.md → auto-generate tasks.md
-# Creates: spec.md, plan.md, tasks.md (auto-generated!), tests.md
+# Smart: Auto-closes previous increment if PM gates pass
 
-# 3. Build it (hooks run after EVERY task)
-/build 0001
-# Executes tasks sequentially
+# 3. Execute implementation (smart resume, hooks after EVERY task)
+/specweave do
+# Or: /specweave do 0001
+# Smart: Auto-resumes from next incomplete task
 # Hooks automatically update CLAUDE.md, README.md, CHANGELOG.md
 
-# 4. Validate quality (optional)
-/validate 0001 --quality
+# 4. Check progress anytime
+/specweave progress
+# Shows: task completion %, PM gates status, next action
+# No increment ID needed - finds active increment automatically
+
+# 5. Validate quality (optional)
+/specweave validate 0001 --quality
 # LLM-as-judge quality assessment
 
-# 5. Close increment (PM validates 3 gates)
-/done 0001
-# Gate 1: Tasks completed (P1 required)
-# Gate 2: Tests passing (>80% coverage)
-# Gate 3: Documentation updated
+# 6. Start next feature (auto-closes previous)
+/specweave inc "payment processing"
+# Auto-closes 0001 if gates pass, creates 0002
+# No manual /done needed!
 
-# 6. Sync with tools (optional)
-/sync-github  # Sync to GitHub issues
+# 7. Sync with tools (optional)
+/specweave sync-github  # Sync to GitHub issues
 ```
 
-### For Brownfield Projects
+### For Brownfield Projects (The Hardest Challenge)
 
-```bash
-# 1. Analyze existing code
-"Analyze my authentication module"
+**Why brownfield is the most complicated:**
+- Existing codebase with no documentation
+- Tribal knowledge scattered across the team
+- Risk of breaking production systems
+- Need to merge with existing docs/wikis
+- Complex architecture that needs retroactive documentation
 
-# 2. Generate specs from code
-# SpecWeave creates retroactive specifications
+**SpecWeave solves all of this:**
 
-# 3. Create baseline tests
-"Create tests for current behavior"
+```bash
+# 1. Initialize in existing project
+cd my-existing-project
+npx specweave init .
 
-# 4. Now safe to modify
-"Add OAuth to authentication"
+# 2. Merge existing documentation
+"Read brownfield-onboarder skill and merge my existing docs/"
+# SpecWeave intelligently merges existing documentation:
+# - Extracts project-specific knowledge from docs, wikis, CLAUDE.md backups
+# - Distributes content to appropriate SpecWeave folders
+# - Preserves historical context and team conventions
+# - No bloat - smart content organization
+
+# 3. Analyze and document existing code
+"Analyze my authentication module and create comprehensive documentation"
+# SpecWeave creates retroactive specifications:
+# - Generates specs (WHAT/WHY) from existing code
+# - Creates architecture diagrams (HLDs, C4 Context/Container/Component)
+# - Documents decision rationale (ADRs)
+# - Maps dependencies and integration points
+# - Creates RFCs for understood patterns
+
+# 4. Create complex architecture documentation
+"Create complete architecture documentation for the auth system"
+# SpecWeave generates:
+# - High-Level Design (HLD) documents
+# - Architecture Decision Records (ADRs) for key choices
+# - C4 Context diagrams (system boundaries)
+# - C4 Container diagrams (services, databases)
+# - C4 Component diagrams (internal structure)
+# - Sequence diagrams (flows)
+# - ER diagrams (data models)
+
+# 5. Establish baseline tests (regression prevention)
+"Create comprehensive tests for current auth behavior"
+# Creates baseline test suite to prevent regression
+
+# 6. Set up living documentation
+# From now on, all changes auto-update documentation:
+# - specs stay in sync with code
+# - ADRs updated from Proposed → Accepted
+# - Architecture diagrams reflect current state
+# - No documentation drift ever again
+
+# 7. Now safe to modify and evolve
+"Add OAuth 2.0 to authentication system"
+# SpecWeave:
+# - Updates existing specs with new requirements
+# - Extends architecture docs (ADRs, HLDs)
+# - Updates diagrams automatically
+# - Maintains living documentation
+# - Prevents regression with baseline tests
 ```
 
+**The SpecWeave Brownfield Advantage:**
+- ✅ **Merge existing docs** - Intelligently consolidates wikis, docs, legacy CLAUDE.md files
+- ✅ **Create complex architecture** - HLDs, ADRs, RFCs, C4 diagrams for existing systems
+- ✅ **Living documentation** - Auto-updates after every change (via hooks)
+- ✅ **Structure evolution** - Documentation grows with your codebase
+- ✅ **Regression prevention** - Baseline tests before any modifications
+- ✅ **Compliance-ready** - Complete audit trail for regulated industries
+- ✅ **Knowledge preservation** - No more tribal knowledge or context loss
+
 **See [CLAUDE.md#development-workflow](CLAUDE.md#development-workflow)** for complete guide.
 
 ---
@@ -354,15 +445,16 @@ SpecWeave implements **4 Levels of Testing**:
    - Test coverage matrix
    - Maps TC-0001 to implementations
 
-3. **Level 3: Component Tests** (src/)
-   - Agent test cases: `src/agents/{name}/test-cases/`
-   - Skill test cases: `src/skills/{name}/test-cases/`
+3. **Level 3: Component Tests** (tests/)
+   - Integration tests: `tests/integration/{integration-name}/`
+   - Skill tests: `tests/specs/{skill-name}/`
    - **Minimum 3 tests per component** (MANDATORY)
+   - **Centralized location** for better organization and CI/CD
 
 4. **Level 4: Automated Tests** (tests/)
    - Unit tests (Jest)
-   - Integration tests
-   - E2E tests (Playwright) when UI exists
+   - Integration tests (Jira, GitHub, ADO sync)
+   - E2E tests (Playwright) for UI/CLI validation
 
 **See [CLAUDE.md#testing-philosophy](CLAUDE.md#testing-philosophy)** for complete testing guide.
 
@@ -407,29 +499,21 @@ SpecWeave includes **automated C4 diagram generation**:
 
 ### JIRA Integration
 
-```yaml
-# .specweave/config.yaml
-sync:
-  jira:
-    enabled: true
-    url: "https://company.atlassian.net"
-    project: "PROJ"
-```
-
 ```bash
 # Sync increment to JIRA
 /sync-jira --increment 0001
 
 # Maps: Increment → Epic, Tasks → Stories
+# Configuration auto-detected from environment or prompts
 ```
 
 ### Azure DevOps Integration
 
-```yaml
-sync:
-  ado:
-    enabled: true
-    url: "https://dev.azure.com/company/MyProject"
+```bash
+# Sync increment to Azure DevOps
+/sync-ado --increment 0001
+
+# Configuration auto-detected from environment or prompts
 ```
 
 ### GitHub Integration
@@ -522,32 +606,121 @@ npm test
 
 ## 📖 Quick Start
 
-### Initialize New Project
+### 🎯 NEW: Multi-Tool Support!
+
+**SpecWeave now works with ANY AI coding tool!** Auto-detects Claude, Cursor, Gemini CLI, Codex, Copilot, or Generic.
+
+**Architecture**:
+- **Claude Code** = Native/Baseline (no adapter needed - full automation)
+- **All other tools** = Adapters that approximate Claude's native capabilities
+
+```bash
+# List available adapters
+npx specweave adapters
+
+# Auto-detect your AI tool
+npx specweave init my-saas           # Automatically detects and configures
+
+# Or explicitly choose:
+npx specweave init my-saas --adapter claude    # Native (no adapter!)
+npx specweave init my-saas --adapter cursor    # Adapter (semi-automation)
+npx specweave init my-saas --adapter gemini    # Adapter (semi-automation, 1M context!)
+npx specweave init my-saas --adapter codex     # Adapter (semi-automation, GPT-5-Codex)
+npx specweave init my-saas --adapter copilot   # Adapter (basic automation)
+npx specweave init my-saas --adapter generic   # Adapter (manual, ANY AI)
+```
+
+### For Claude Code (Native - Full Automation)
+
+**Claude is the BASELINE** - no adapter needed! Native skills, agents, hooks work out of the box.
 
 ```bash
-# Create new project (all components pre-installed!)
 npx specweave init my-saas
 cd my-saas
 
-# Everything ready:
+# Native components installed:
 # ✅ 10 agents in .claude/agents/
 # ✅ 35+ skills in .claude/skills/
 # ✅ 10 slash commands in .claude/commands/
+# ✅ Hooks for auto-updates
+
+# Open Claude Code and type slash commands:
+/specweave inc "User authentication with JWT"
+/specweave do
+/specweave progress
+```
 
-# Open Claude Code and start building:
-# "Create user authentication with JWT"
-# "Add subscription billing with Stripe"
-# "Build admin dashboard with analytics"
+### For Gemini CLI / Codex / Cursor (Adapter - Semi-Automation)
+
+**Uses universal AGENTS.md** that works across all tools (follows [agents.md](https://agents.md/) standard).
+
+```bash
+npx specweave init my-project --adapter gemini  # or codex, cursor
+cd my-project
+
+# Adapter creates:
+# ✅ AGENTS.md (universal instructions - works with ALL tools!)
+# ✅ Tool-specific folder (.gemini/, .codex/, .cursor/)
+
+# Example with Gemini CLI:
+gemini "Read AGENTS.md and create increment for user authentication"
+
+# Example with Codex:
+codex "Read AGENTS.md and create increment for payments"
+
+# Example with Cursor:
+# Open in Cursor, say: "Read AGENTS.md and create increment for auth"
+```
+
+### For GitHub Copilot (Adapter - Basic Automation)
+
+**Uses universal AGENTS.md** for workspace instructions.
+
+```bash
+npx specweave init my-project --adapter copilot
+cd my-project
+
+# Adapter creates:
+# ✅ AGENTS.md (universal instructions)
+# ✅ .github/copilot/ (Copilot-specific config)
+
+# Open in VS Code with Copilot:
+# Copilot reads AGENTS.md automatically
+# Start creating increment folders and files
+```
+
+### For ANY Other AI (Adapter - Manual)
+
+**Uses universal AGENTS.md** that works with ChatGPT, Claude web, Gemini web, etc.
+
+```bash
+npx specweave init my-project --adapter generic
+cd my-project
+
+# Adapter creates:
+# ✅ AGENTS.md (universal instructions)
+# ✅ SPECWEAVE.md (detailed manual workflow)
+
+# Follow manual workflow:
+# 1. Read AGENTS.md in your AI tool (ChatGPT, Claude web, etc.)
+# 2. Say: "Create increment for user authentication following SpecWeave"
+# 3. Copy generated content to files
 ```
 
 ### For Existing Projects
 
 ```bash
-# Add SpecWeave to existing project
+# Add SpecWeave to existing project (brownfield)
 cd my-existing-project
 npx specweave init .
 
-# Analyze existing code
+# SpecWeave initializes in current directory:
+# ✅ Detects existing files and prompts for confirmation
+# ✅ Preserves your existing code and git history
+# ✅ Adds .specweave/ and .claude/ directories
+# ✅ Uses directory name as project name (or prompts if invalid)
+
+# Now analyze existing code
 # "Analyze my authentication module"
 # SpecWeave creates retroactive specifications
 
@@ -569,7 +742,9 @@ npx specweave init .
 | **Components** | Manual setup | Pre-installed (10 agents + 35+ skills) |
 | **Regression** | Frequent breaks | Prevention-first |
 | **Onboarding** | Weeks | Hours (specs explain everything) |
-| **Brownfield** | Risky | Safe (document first) |
+| **Brownfield** | Risky, undocumented | Safe, documented, living architecture (most complicated solved) |
+| **Architecture** | Scattered tribal knowledge | HLDs, ADRs, C4 diagrams auto-updated |
+| **Doc Maintenance** | Manual, becomes stale | Auto-updated via hooks, always current |
 
 ### vs Other Frameworks
 

package/bin/install-all.sh

@@ -45,5 +45,5 @@ echo "Next steps:"
 echo "  1. Restart Claude Code to load agents, skills, and commands"
 echo "  2. Try: 'Create a product vision for X' (activates PM agent)"
 echo "  3. Try: 'Plan implementation for feature Y' (activates increment-planner skill)"
-echo "  4. Try: '/create-project' to bootstrap a new project"
+echo "  4. Try: '/specweave inc' to plan a new increment"
 echo ""

package/bin/install-commands.sh

@@ -47,9 +47,9 @@ echo ""
 echo "Usage: Type /command-name in Claude Code"
 echo ""
 echo "Examples:"
-echo "  /create-project"
-echo "  /create-increment \"user authentication\""
-echo "  /review-docs"
+echo "  specweave init my-project    # CLI command to create project"
+echo "  /specweave inc \"user authentication\""
+echo "  /specweave review-docs"
 echo "  /sync-github"
 echo ""
 

package/bin/specweave.js

@@ -7,24 +7,36 @@
  * Provides commands for initializing projects, creating increments, and managing skills.
  */
 
-const { Command } = require('commander');
-const chalk = require('chalk');
-const package = require('../package.json');
+import { Command } from 'commander';
+import chalk from 'chalk';
+import { createRequire } from 'module';
+import { fileURLToPath } from 'url';
+import { dirname } from 'path';
+
+// ESM equivalents for __dirname and __filename
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = dirname(__filename);
+
+// For importing package.json (need createRequire in ESM)
+const require = createRequire(import.meta.url);
+const packageJson = require('../package.json');
 
 const program = new Command();
 
 program
   .name('specweave')
   .description('Spec-Driven Development framework with AI-powered autonomous agents')
-  .version(package.version);
+  .version(packageJson.version);
 
 // Init command - Create new SpecWeave project
 program
   .command('init [project-name]')
   .description('Initialize a new SpecWeave project')
   .option('-t, --template <type>', 'Project template (saas, api, fullstack)', 'saas')
+  .option('-a, --adapter <tool>', 'AI tool adapter (claude, cursor, copilot, generic)', undefined)
+  .option('--tech-stack <language>', 'Technology stack (nodejs, python, etc.)', undefined)
   .action(async (projectName, options) => {
-    const { initCommand } = require('../dist/cli/commands/init');
+    const { initCommand } = await import('../dist/cli/commands/init.js');
     await initCommand(projectName, options);
   });
 
@@ -45,7 +57,7 @@ program
   .option('-g, --global', 'Install globally to ~/.claude/')
   .option('-l, --local', 'Install locally to .claude/ (default)')
   .action(async (componentName, options) => {
-    const { installCommand } = require('../dist/cli/commands/install');
+    const { installCommand } = await import('../dist/cli/commands/install.js');
     await installCommand(componentName, options);
   });
 
@@ -55,21 +67,39 @@ program
   .description('List available and installed components')
   .option('--installed', 'Show only installed components')
   .action(async (options) => {
-    const { listCommand } = require('../dist/cli/commands/list');
+    const { listCommand } = await import('../dist/cli/commands/list.js');
     await listCommand(options);
   });
 
+// Adapters command - List available adapters
+program
+  .command('adapters')
+  .description('List available AI tool adapters')
+  .action(async () => {
+    const { AdapterLoader } = await import('../dist/adapters/adapter-loader.js');
+    const loader = new AdapterLoader();
+    await loader.listAdapters();
+  });
+
 // Help text
 program.on('--help', () => {
   console.log('');
   console.log('Examples:');
-  console.log('  $ specweave init my-saas                    # Create new project');
+  console.log('  $ specweave init my-saas                    # Create new project (auto-detect tool)');
+  console.log('  $ specweave init my-saas --adapter cursor   # Create project for Cursor');
+  console.log('  $ specweave adapters                        # List available AI tool adapters');
   console.log('  $ specweave install pm --local              # Install PM agent locally');
   console.log('  $ specweave install --global                # Install all (interactive)');
   console.log('  $ specweave list                            # List all available components');
   console.log('  $ specweave list --installed                # Show installed components');
   console.log('');
-  console.log('For more information, visit: https://github.com/specweave/specweave');
+  console.log('Supported AI Tools:');
+  console.log('  - Claude Code (full automation) - Native skills, agents, hooks');
+  console.log('  - Cursor (semi-automation) - .cursorrules, @ shortcuts');
+  console.log('  - GitHub Copilot (basic) - Workspace instructions');
+  console.log('  - Generic (manual) - Works with ANY AI (ChatGPT, Gemini, etc.)');
+  console.log('');
+  console.log('For more information, visit: https://spec-weave.com');
 });
 
 // Parse arguments

package/dist/adapters/adapter-base.d.ts

@@ -4,7 +4,7 @@
  * Provides common functionality for all adapters.
  * Concrete adapters extend this class and implement tool-specific logic.
  */
-import { IAdapter, AdapterOptions, RequirementsResult, AdapterFile, AutomationLevel } from './adapter-interface';
+import { IAdapter, AdapterOptions, RequirementsResult, AdapterFile, AutomationLevel } from './adapter-interface.js';
 export declare abstract class AdapterBase implements IAdapter {
     abstract name: string;
     abstract description: string;

package/dist/adapters/adapter-base.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"adapter-base.d.ts","sourceRoot":"","sources":["../../src/adapters/adapter-base.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAIH,OAAO,EACL,QAAQ,EACR,cAAc,EACd,kBAAkB,EAClB,WAAW,EACX,eAAe,EAChB,MAAM,qBAAqB,CAAC;AAE7B,8BAAsB,WAAY,YAAW,QAAQ;IACnD,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,QAAQ,CAAC,eAAe,EAAE,eAAe,CAAC;IAE1C;;OAEG;IACG,MAAM,IAAI,OAAO,CAAC,OAAO,CAAC;IAIhC;;;OAGG;IACG,iBAAiB,IAAI,OAAO,CAAC,kBAAkB,CAAC;IA2BtD;;OAEG;IACH,QAAQ,CAAC,QAAQ,IAAI,WAAW,EAAE;IAElC;;OAEG;IACG,OAAO,CAAC,OAAO,EAAE,cAAc,GAAG,OAAO,CAAC,IAAI,CAAC;IAuBrD;;OAEG;IACG,WAAW,CAAC,OAAO,EAAE,cAAc,GAAG,OAAO,CAAC,IAAI,CAAC;IAKzD;;OAEG;IACH,QAAQ,CAAC,eAAe,IAAI,MAAM;IAElC;;OAEG;cACa,aAAa,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAAC,OAAO,CAAC;IAUhE;;OAEG;cACa,UAAU,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC,OAAO,CAAC;IAS9D;;OAEG;cACa,YAAY,CAC1B,YAAY,EAAE,MAAM,EACpB,SAAS,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAChC,OAAO,CAAC,MAAM,CAAC;CAUnB"}
+{"version":3,"file":"adapter-base.d.ts","sourceRoot":"","sources":["../../src/adapters/adapter-base.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAKH,OAAO,EACL,QAAQ,EACR,cAAc,EACd,kBAAkB,EAClB,WAAW,EACX,eAAe,EAChB,MAAM,wBAAwB,CAAC;AAKhC,8BAAsB,WAAY,YAAW,QAAQ;IACnD,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,QAAQ,CAAC,eAAe,EAAE,eAAe,CAAC;IAE1C;;OAEG;IACG,MAAM,IAAI,OAAO,CAAC,OAAO,CAAC;IAIhC;;;OAGG;IACG,iBAAiB,IAAI,OAAO,CAAC,kBAAkB,CAAC;IA0BtD;;OAEG;IACH,QAAQ,CAAC,QAAQ,IAAI,WAAW,EAAE;IAElC;;OAEG;IACG,OAAO,CAAC,OAAO,EAAE,cAAc,GAAG,OAAO,CAAC,IAAI,CAAC;IAuBrD;;OAEG;IACG,WAAW,CAAC,OAAO,EAAE,cAAc,GAAG,OAAO,CAAC,IAAI,CAAC;IAKzD;;OAEG;IACH,QAAQ,CAAC,eAAe,IAAI,MAAM;IAElC;;OAEG;cACa,aAAa,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAAC,OAAO,CAAC;IAUhE;;OAEG;cACa,UAAU,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC,OAAO,CAAC;IAS9D;;OAEG;cACa,YAAY,CAC1B,YAAY,EAAE,MAAM,EACpB,SAAS,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAChC,OAAO,CAAC,MAAM,CAAC;CAUnB"}