Add comprehensive MCP setup guide and integration test template

**Documentation Added:**
- docs/MCP_SETUP.md: Complete 400+ line setup guide
  - Prerequisites and installation steps
  - Configuration examples for Claude Code
  - Verification and troubleshooting
  - 3 usage examples and advanced configuration
  - End-to-end workflow and quick reference

- tests/mcp_integration_test.md: Comprehensive test template
  - 10 test cases covering all MCP tools
  - Performance metrics table
  - Issue tracking and environment setup
  - Setup and cleanup scripts

- .claude/mcp_config.example.json: Example MCP configuration

**Documentation Updated:**
- STRUCTURE.md: Complete monorepo structure documentation
- CLAUDE.md: All Python script paths updated to cli/ prefix
- docs/USAGE.md: All command examples updated for monorepo
- TODO.md: Current sprint status and completed tasks

**Summary:**
- Issues #2 and #3 handled (MCP setup guide + integration tests)
- All documentation now reflects monorepo structure (cli/ + mcp/)
- Tests: 71/71 passing (100%)
- Ready for MCP server testing with Claude Code

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
yusyus
2025-10-19 17:01:37 +03:00
parent ba7cacdb4c
commit b69f57b60a
7 changed files with 1404 additions and 141 deletions

View File

@@ -0,0 +1,12 @@
{
"mcpServers": {
"skill-seeker": {
"command": "python3",
"args": [
"/REPLACE/WITH/YOUR/PATH/Skill_Seekers/mcp/server.py"
],
"cwd": "/REPLACE/WITH/YOUR/PATH/Skill_Seekers",
"env": {}
}
}
}

View File

@@ -27,11 +27,11 @@ export ANTHROPIC_API_KEY=sk-ant-...
```bash
# Scrape and build with a preset configuration
python3 doc_scraper.py --config configs/godot.json
python3 doc_scraper.py --config configs/react.json
python3 doc_scraper.py --config configs/vue.json
python3 doc_scraper.py --config configs/django.json
python3 doc_scraper.py --config configs/fastapi.json
python3 cli/doc_scraper.py --config configs/godot.json
python3 cli/doc_scraper.py --config configs/react.json
python3 cli/doc_scraper.py --config configs/vue.json
python3 cli/doc_scraper.py --config configs/django.json
python3 cli/doc_scraper.py --config configs/fastapi.json
```
### First-Time User Workflow (Recommended)
@@ -41,15 +41,15 @@ python3 doc_scraper.py --config configs/fastapi.json
pip3 install requests beautifulsoup4
# 2. Estimate page count BEFORE scraping (fast, no data download)
python3 estimate_pages.py configs/godot.json
python3 cli/estimate_pages.py configs/godot.json
# Time: ~1-2 minutes, shows estimated total pages and recommended max_pages
# 3. Scrape with local enhancement (uses Claude Code Max, no API key)
python3 doc_scraper.py --config configs/godot.json --enhance-local
python3 cli/doc_scraper.py --config configs/godot.json --enhance-local
# Time: 20-40 minutes scraping + 60 seconds enhancement
# 4. Package the skill
python3 package_skill.py output/godot/
python3 cli/package_skill.py output/godot/
# Result: godot.zip ready to upload to Claude
```
@@ -58,21 +58,21 @@ python3 package_skill.py output/godot/
```bash
# Step-by-step configuration wizard
python3 doc_scraper.py --interactive
python3 cli/doc_scraper.py --interactive
```
### Quick Mode (Minimal Config)
```bash
# Create skill from any documentation URL
python3 doc_scraper.py --name react --url https://react.dev/ --description "React framework for UIs"
python3 cli/doc_scraper.py --name react --url https://react.dev/ --description "React framework for UIs"
```
### Skip Scraping (Use Cached Data)
```bash
# Fast rebuild using previously scraped data
python3 doc_scraper.py --config configs/godot.json --skip-scrape
python3 cli/doc_scraper.py --config configs/godot.json --skip-scrape
# Time: 1-3 minutes (instant rebuild)
```
@@ -81,27 +81,27 @@ python3 doc_scraper.py --config configs/godot.json --skip-scrape
**LOCAL Enhancement (Recommended - No API Key Required):**
```bash
# During scraping
python3 doc_scraper.py --config configs/react.json --enhance-local
python3 cli/doc_scraper.py --config configs/react.json --enhance-local
# Standalone after scraping
python3 enhance_skill_local.py output/react/
python3 cli/enhance_skill_local.py output/react/
```
**API Enhancement (Alternative - Requires API Key):**
```bash
# During scraping
python3 doc_scraper.py --config configs/react.json --enhance
python3 cli/doc_scraper.py --config configs/react.json --enhance
# Standalone after scraping
python3 enhance_skill.py output/react/
python3 enhance_skill.py output/react/ --api-key sk-ant-...
python3 cli/enhance_skill.py output/react/
python3 cli/enhance_skill.py output/react/ --api-key sk-ant-...
```
### Package the Skill
```bash
# Package skill directory into .zip file
python3 package_skill.py output/godot/
python3 cli/package_skill.py output/godot/
# Result: output/godot.zip
```
@@ -110,22 +110,22 @@ python3 package_skill.py output/godot/
```bash
# Delete cached data and re-scrape from scratch
rm -rf output/godot_data/
python3 doc_scraper.py --config configs/godot.json
python3 cli/doc_scraper.py --config configs/godot.json
```
### Estimate Page Count (Before Scraping)
```bash
# Quick estimation - discover up to 100 pages
python3 estimate_pages.py configs/react.json --max-discovery 100
python3 cli/estimate_pages.py configs/react.json --max-discovery 100
# Time: ~30-60 seconds
# Full estimation - discover up to 1000 pages (default)
python3 estimate_pages.py configs/godot.json
python3 cli/estimate_pages.py configs/godot.json
# Time: ~1-2 minutes
# Deep estimation - discover up to 2000 pages
python3 estimate_pages.py configs/vue.json --max-discovery 2000
python3 cli/estimate_pages.py configs/vue.json --max-discovery 2000
# Time: ~3-5 minutes
# What it shows:
@@ -148,12 +148,12 @@ python3 estimate_pages.py configs/vue.json --max-discovery 2000
```
Skill_Seekers/
├── doc_scraper.py # Main tool (single-file, ~790 lines)
├── estimate_pages.py # Page count estimator (fast, no data)
├── enhance_skill.py # AI enhancement (API-based)
├── enhance_skill_local.py # AI enhancement (LOCAL, no API)
├── package_skill.py # Skill packager
├── run_tests.py # Test runner (71 tests)
├── cli/doc_scraper.py # Main tool (single-file, ~790 lines)
├── cli/estimate_pages.py # Page count estimator (fast, no data)
├── cli/enhance_skill.py # AI enhancement (API-based)
├── cli/enhance_skill_local.py # AI enhancement (LOCAL, no API)
├── cli/package_skill.py # Skill packager
├── cli/run_tests.py # Test runner (71 tests)
├── configs/ # Preset configurations
│ ├── godot.json
│ ├── react.json
@@ -284,7 +284,7 @@ See: `create_enhanced_skill_md()` in doc_scraper.py:426-542
```bash
# 1. Scrape + Build + AI Enhancement (LOCAL, no API key)
python3 doc_scraper.py --config configs/godot.json --enhance-local
python3 cli/doc_scraper.py --config configs/godot.json --enhance-local
# 2. Wait for enhancement terminal to close (~60 seconds)
@@ -292,7 +292,7 @@ python3 doc_scraper.py --config configs/godot.json --enhance-local
cat output/godot/SKILL.md
# 4. Package
python3 package_skill.py output/godot/
python3 cli/package_skill.py output/godot/
# Result: godot.zip ready for Claude
# Time: 20-40 minutes (scraping) + 60 seconds (enhancement)
@@ -302,11 +302,11 @@ python3 package_skill.py output/godot/
```bash
# 1. Use existing data + Local Enhancement
python3 doc_scraper.py --config configs/godot.json --skip-scrape
python3 enhance_skill_local.py output/godot/
python3 cli/doc_scraper.py --config configs/godot.json --skip-scrape
python3 cli/enhance_skill_local.py output/godot/
# 2. Package
python3 package_skill.py output/godot/
python3 cli/package_skill.py output/godot/
# Time: 1-3 minutes (build) + 60 seconds (enhancement)
```
@@ -315,10 +315,10 @@ python3 package_skill.py output/godot/
```bash
# 1. Scrape + Build (no enhancement)
python3 doc_scraper.py --config configs/godot.json
python3 cli/doc_scraper.py --config configs/godot.json
# 2. Package
python3 package_skill.py output/godot/
python3 cli/package_skill.py output/godot/
# Note: SKILL.md will be basic template - enhancement recommended
# Time: 20-40 minutes
@@ -328,7 +328,7 @@ python3 package_skill.py output/godot/
**Option 1: Interactive**
```bash
python3 doc_scraper.py --interactive
python3 cli/doc_scraper.py --interactive
# Follow prompts, it creates the config for you
```
@@ -344,7 +344,7 @@ nano configs/myframework.json
# Set "max_pages": 20 in config
# Use it
python3 doc_scraper.py --config configs/myframework.json
python3 cli/doc_scraper.py --config configs/myframework.json
```
## Testing & Verification
@@ -431,7 +431,7 @@ cat output/godot_data/summary.json | grep url | head -20
**Solution:** Force re-scrape:
```bash
rm -rf output/myframework_data/
python3 doc_scraper.py --config configs/myframework.json
python3 cli/doc_scraper.py --config configs/myframework.json
```
### Rate Limiting Issues
@@ -445,19 +445,19 @@ python3 doc_scraper.py --config configs/myframework.json
```
### Package Path Error
**Problem:** doc_scraper.py shows wrong package_skill.py path
**Problem:** doc_scraper.py shows wrong cli/package_skill.py path
**Expected output:**
```bash
python3 package_skill.py output/godot/
python3 cli/package_skill.py output/godot/
```
**Not:**
```bash
python3 /mnt/skills/examples/skill-creator/scripts/package_skill.py output/godot/
python3 /mnt/skills/examples/skill-creator/scripts/cli/package_skill.py output/godot/
```
The correct command uses the local `package_skill.py` in the repository root.
The correct command uses the local `cli/package_skill.py` in the repository root.
## Key Code Locations

View File

@@ -1,18 +1,30 @@
# Repository Structure
```
doc-to-skill/
Skill_Seekers/
├── README.md # Main documentation (start here!)
├── QUICKSTART.md # 3-step quick start guide
├── LICENSE # MIT License
├── .gitignore # Git ignore rules
├── 📄 Root Documentation
│ ├── README.md # Main documentation (start here!)
│ ├── CLAUDE.md # Quick reference for Claude Code
│ ├── QUICKSTART.md # 3-step quick start guide
│ ├── ROADMAP.md # Development roadmap
│ ├── TODO.md # Current sprint tasks
│ ├── STRUCTURE.md # This file
│ ├── LICENSE # MIT License
│ └── .gitignore # Git ignore rules
├── 🐍 Core Scripts
├── 🔧 CLI Tools (cli/)
│ ├── doc_scraper.py # Main scraping tool
│ ├── estimate_pages.py # Page count estimator
│ ├── enhance_skill.py # AI enhancement (API-based)
│ ├── enhance_skill_local.py # AI enhancement (LOCAL, no API)
── package_skill.py # Skill packaging tool
── package_skill.py # Skill packaging tool
│ └── run_tests.py # Test runner
├── 🌐 MCP Server (mcp/)
│ ├── server.py # Main MCP server
│ ├── requirements.txt # MCP dependencies
│ └── README.md # MCP setup guide
├── 📁 configs/ # Preset configurations
│ ├── godot.json
@@ -20,15 +32,25 @@ doc-to-skill/
│ ├── vue.json
│ ├── django.json
│ ├── fastapi.json
│ ├── steam-inventory.json
│ ├── steam-economy.json
│ ├── kubernetes.json
│ └── steam-economy-complete.json
├── 🧪 tests/ # Test suite (71 tests, 100% pass rate)
│ ├── test_config_validation.py
│ ├── test_integration.py
│ └── test_scraper_features.py
├── 📚 docs/ # Detailed documentation
│ ├── CLAUDE.md # Technical architecture
│ ├── ENHANCEMENT.md # AI enhancement guide
│ ├── UPLOAD_GUIDE.md # How to upload skills
── READY_TO_SHARE.md # Sharing checklist
│ ├── USAGE.md # Complete usage guide
── TESTING.md # Testing guide
│ └── UPLOAD_GUIDE.md # How to upload skills
├── 🔀 .github/ # GitHub configuration
│ ├── SETUP_GUIDE.md # GitHub project setup
│ ├── ISSUES_TO_CREATE.md # Issue templates
│ └── ISSUE_TEMPLATE/ # Issue templates
└── 📦 output/ # Generated skills (git-ignored)
├── {name}_data/ # Scraped raw data (cached)
@@ -42,14 +64,61 @@ doc-to-skill/
### For Users:
- **README.md** - Start here for overview and installation
- **QUICKSTART.md** - Get started in 3 steps
- **configs/** - 8 ready-to-use presets
- **configs/** - 7 ready-to-use presets
- **mcp/README.md** - MCP server setup for Claude Code
### For CLI Usage:
- **cli/doc_scraper.py** - Main scraping tool
- **cli/estimate_pages.py** - Page count estimator
- **cli/enhance_skill_local.py** - Local enhancement (no API key)
- **cli/package_skill.py** - Package skills to .zip
### For MCP Usage (Claude Code):
- **mcp/server.py** - MCP server (6 tools)
- **mcp/README.md** - Setup instructions
- **configs/** - Shared configurations
### For Developers:
- **doc_scraper.py** - Main tool (787 lines)
- **docs/CLAUDE.md** - Architecture and internals
- **docs/ENHANCEMENT.md** - How enhancement works
- **docs/USAGE.md** - Complete usage guide
- **docs/TESTING.md** - Testing guide
- **tests/** - 71 tests (100% pass rate)
### For Contributors:
- **ROADMAP.md** - Development roadmap
- **TODO.md** - Current sprint tasks
- **.github/SETUP_GUIDE.md** - GitHub setup
- **LICENSE** - MIT License
- **.gitignore** - What Git ignores
- **docs/READY_TO_SHARE.md** - Distribution guide
## Architecture
### Monorepo Structure
The repository is organized as a monorepo with two main components:
1. **CLI Tools** (`cli/`): Standalone Python scripts for direct command-line usage
2. **MCP Server** (`mcp/`): Model Context Protocol server for Claude Code integration
Both components share the same configuration files and output directory.
### Data Flow
```
Config (configs/*.json)
CLI Tools OR MCP Server
Scraper (cli/doc_scraper.py)
Output (output/{name}_data/)
Builder (cli/doc_scraper.py)
Skill (output/{name}/)
Enhancer (optional)
Packager (cli/package_skill.py)
Skill .zip (output/{name}.zip)
```

47
TODO.md
View File

@@ -6,9 +6,9 @@
- [x] Implement 6 basic tools
- [x] Update tests for new structure
## Phase 2: MCP Enhancement 🚧 IN PROGRESS
- [ ] Fix remaining 3 test failures
- [ ] Add MCP configuration examples
## Phase 2: MCP Enhancement ✅ DONE
- [x] Fix remaining 3 test failures (100% pass rate achieved!)
- [x] Add MCP configuration examples
- [ ] Test MCP server with Claude Code
- [ ] Add error handling improvements
- [ ] Add logging to MCP tools
@@ -20,8 +20,11 @@
- [ ] Batch operations (multiple configs at once)
- [ ] Config templates for popular frameworks
## Phase 4: Documentation & Polish 📋 PLANNED
- [ ] Update main README for monorepo
## Phase 4: Documentation & Polish 🚧 IN PROGRESS
- [x] Update main README for monorepo
- [x] Update STRUCTURE.md for monorepo
- [x] Update CLAUDE.md with CLI paths
- [x] Update docs/USAGE.md with CLI paths
- [ ] Create MCP setup guide with screenshots
- [ ] Add video tutorial
- [ ] Create example workflows
@@ -39,21 +42,34 @@
## Current Sprint (Week of Oct 19)
### Priority Tasks
1. [ ] Fix 3 test failures (warnings vs errors) - **STARTED**
2. [ ] Create MCP setup guide for Claude Code - **STARTED**
3. [ ] Test MCP server to ensure it works - **STARTED**
4. [ ] Update documentation for new monorepo structure - **STARTED**
### In Progress
- Setting up tasks in planning tools
- Organizing GitHub issues
- Creating visual project board
1. [x] Fix 3 test failures (warnings vs errors) - **DONE**
2. [x] Update documentation for new monorepo structure - **DONE**
3. [x] Create MCP setup guide for Claude Code - **DONE**
4. [x] Create MCP integration test template - **DONE**
5. [ ] Test MCP server with actual Claude Code - **NEXT**
6. [ ] Create GitHub Project board and issues - **NEXT**
### Completed Today
- [x] Monorepo refactor (cli/ and mcp/)
- [x] MCP server implementation (6 tools)
- [x] Planning structure (TODO.md, ROADMAP.md)
- [x] Issue templates
- [x] Fix all 3 test failures (100% pass rate!)
- [x] Update STRUCTURE.md for monorepo
- [x] Update CLAUDE.md with CLI paths
- [x] Update docs/USAGE.md with CLI paths
- [x] Add upper limit validation for config
- [x] Create comprehensive MCP setup guide (docs/MCP_SETUP.md)
- [x] Create MCP integration test template (tests/mcp_integration_test.md)
- [x] Create example MCP config (.claude/mcp_config.example.json)
### Ready for Next Sprint
- [ ] Test MCP server with Claude Code
- [ ] Create comprehensive MCP setup guide
- [ ] Create GitHub Project board
- [ ] Create GitHub issues for tracking
- [ ] Add error handling to MCP tools
- [ ] Add logging to MCP tools
### Blockers
- None
@@ -61,5 +77,6 @@
### Notes
- MCP server uses stdio protocol
- All CLI tools work via subprocess
- Tests at 95.8% (68/71 passing)
- Tests: 71/71 passing (100%) ✅
- Branch: MCP_refactor
- All documentation updated for monorepo structure

598
docs/MCP_SETUP.md Normal file
View File

@@ -0,0 +1,598 @@
# Complete MCP Setup Guide for Claude Code
Step-by-step guide to set up the Skill Seeker MCP server with Claude Code.
---
## Table of Contents
- [Prerequisites](#prerequisites)
- [Installation](#installation)
- [Configuration](#configuration)
- [Verification](#verification)
- [Usage Examples](#usage-examples)
- [Troubleshooting](#troubleshooting)
- [Advanced Configuration](#advanced-configuration)
---
## Prerequisites
### Required Software
1. **Python 3.7 or higher**
```bash
python3 --version
# Should show: Python 3.7.x or higher
```
2. **Claude Code installed**
- Download from [claude.ai/code](https://claude.ai/code)
- Requires Claude Pro or Claude Code Max subscription
3. **Skill Seeker repository cloned**
```bash
git clone https://github.com/yusufkaraaslan/Skill_Seekers.git
cd Skill_Seekers
```
### System Requirements
- **Operating System**: macOS, Linux, or Windows (WSL)
- **Disk Space**: 100 MB for dependencies + space for generated skills
- **Network**: Internet connection for documentation scraping
---
## Installation
### Step 1: Install Python Dependencies
```bash
# Navigate to repository root
cd /path/to/Skill_Seekers
# Install MCP server dependencies
pip3 install -r mcp/requirements.txt
# Install CLI tool dependencies (for scraping)
pip3 install requests beautifulsoup4
```
**Expected output:**
```
Successfully installed mcp-0.9.0 requests-2.31.0 beautifulsoup4-4.12.3
```
### Step 2: Verify Installation
```bash
# Test MCP server can start
python3 mcp/server.py
# You should see MCP protocol initialization (Ctrl+C to exit)
```
### Step 3: Note Your Repository Path
```bash
# Get absolute path
pwd
# Example output: /Users/username/Projects/Skill_Seekers
# or: /home/username/Skill_Seekers
```
**Save this path** - you'll need it for configuration!
---
## Configuration
### Step 1: Locate Claude Code MCP Configuration
Claude Code stores MCP configuration in:
- **macOS**: `~/.config/claude-code/mcp.json`
- **Linux**: `~/.config/claude-code/mcp.json`
- **Windows (WSL)**: `~/.config/claude-code/mcp.json`
### Step 2: Create/Edit Configuration File
```bash
# Create config directory if it doesn't exist
mkdir -p ~/.config/claude-code
# Edit the configuration
nano ~/.config/claude-code/mcp.json
```
### Step 3: Add Skill Seeker MCP Server
**Full Configuration Example:**
```json
{
"mcpServers": {
"skill-seeker": {
"command": "python3",
"args": [
"/Users/username/Projects/Skill_Seekers/mcp/server.py"
],
"cwd": "/Users/username/Projects/Skill_Seekers",
"env": {}
}
}
}
```
**IMPORTANT:** Replace `/Users/username/Projects/Skill_Seekers` with YOUR actual repository path!
**If you already have other MCP servers:**
```json
{
"mcpServers": {
"existing-server": {
"command": "node",
"args": ["/path/to/existing/server.js"]
},
"skill-seeker": {
"command": "python3",
"args": [
"/Users/username/Projects/Skill_Seekers/mcp/server.py"
],
"cwd": "/Users/username/Projects/Skill_Seekers"
}
}
}
```
### Step 4: Save and Restart Claude Code
1. Save the file (`Ctrl+O` in nano, then `Enter`)
2. Exit editor (`Ctrl+X` in nano)
3. **Completely restart Claude Code** (quit and reopen)
---
## Verification
### Step 1: Check MCP Server Loaded
In Claude Code, type:
```
List all available MCP tools
```
You should see 6 Skill Seeker tools:
- `generate_config`
- `estimate_pages`
- `scrape_docs`
- `package_skill`
- `list_configs`
- `validate_config`
### Step 2: Test a Simple Command
```
List all available configs
```
**Expected response:**
```
Available configurations:
1. godot - Godot Engine documentation
2. react - React framework
3. vue - Vue.js framework
4. django - Django web framework
5. fastapi - FastAPI Python framework
6. kubernetes - Kubernetes documentation
7. steam-economy-complete - Steam Economy API
```
### Step 3: Test Config Generation
```
Generate a config for Tailwind CSS at https://tailwindcss.com/docs
```
**Expected response:**
```
✅ Config created: configs/tailwind.json
```
**Verify the file exists:**
```bash
ls configs/tailwind.json
```
---
## Usage Examples
### Example 1: Generate Skill from Scratch
```
User: Generate config for Svelte docs at https://svelte.dev/docs
Claude: ✅ Config created: configs/svelte.json
User: Estimate pages for configs/svelte.json
Claude: 📊 Estimated pages: 150
Recommended max_pages: 180
User: Scrape docs using configs/svelte.json
Claude: ✅ Skill created at output/svelte/
Run: python3 cli/package_skill.py output/svelte/
User: Package skill at output/svelte/
Claude: ✅ Created: output/svelte.zip
Ready to upload to Claude!
```
### Example 2: Use Existing Config
```
User: List all available configs
Claude: [Shows 7 configs]
User: Scrape docs using configs/react.json with max 50 pages
Claude: ✅ Skill created at output/react/
User: Package skill at output/react/
Claude: ✅ Created: output/react.zip
```
### Example 3: Validate Before Scraping
```
User: Validate configs/godot.json
Claude: ✅ Config is valid
- Base URL: https://docs.godotengine.org/en/stable/
- Max pages: 500
- Rate limit: 0.5s
- Categories: 3
User: Estimate pages for configs/godot.json
Claude: 📊 Estimated pages: 450
Current max_pages (500) is sufficient
User: Scrape docs using configs/godot.json
Claude: [Scraping starts...]
```
---
## Troubleshooting
### Issue: MCP Server Not Loading
**Symptoms:**
- Skill Seeker tools don't appear in Claude Code
- No response when asking about configs
**Solutions:**
1. **Check configuration path:**
```bash
cat ~/.config/claude-code/mcp.json
```
2. **Verify Python path:**
```bash
which python3
# Should show: /usr/bin/python3 or /usr/local/bin/python3
```
3. **Test server manually:**
```bash
cd /path/to/Skill_Seekers
python3 mcp/server.py
# Should start without errors
```
4. **Check Claude Code logs:**
- macOS: `~/Library/Logs/Claude Code/`
- Linux: `~/.config/claude-code/logs/`
5. **Completely restart Claude Code:**
- Quit Claude Code (don't just close window)
- Reopen Claude Code
### Issue: "ModuleNotFoundError: No module named 'mcp'"
**Solution:**
```bash
pip3 install -r mcp/requirements.txt
```
### Issue: "Permission denied" when running server
**Solution:**
```bash
chmod +x mcp/server.py
```
### Issue: Tools appear but don't work
**Symptoms:**
- Tools listed but commands fail
- "Error executing tool" messages
**Solutions:**
1. **Check working directory in config:**
```json
{
"cwd": "/FULL/PATH/TO/Skill_Seekers"
}
```
2. **Verify CLI tools exist:**
```bash
ls cli/doc_scraper.py
ls cli/estimate_pages.py
ls cli/package_skill.py
```
3. **Test CLI tools directly:**
```bash
python3 cli/doc_scraper.py --help
```
### Issue: Slow or hanging operations
**Solutions:**
1. **Check rate limit in config:**
- Default: 0.5 seconds
- Increase if needed: 1.0 or 2.0 seconds
2. **Use smaller max_pages for testing:**
```
Generate config with max_pages=20 for testing
```
3. **Check network connection:**
```bash
curl -I https://docs.example.com
```
---
## Advanced Configuration
### Custom Environment Variables
```json
{
"mcpServers": {
"skill-seeker": {
"command": "python3",
"args": ["/path/to/Skill_Seekers/mcp/server.py"],
"cwd": "/path/to/Skill_Seekers",
"env": {
"ANTHROPIC_API_KEY": "sk-ant-...",
"PYTHONPATH": "/custom/path"
}
}
}
}
```
### Multiple Python Versions
If you have multiple Python versions:
```json
{
"mcpServers": {
"skill-seeker": {
"command": "/usr/local/bin/python3.11",
"args": ["/path/to/Skill_Seekers/mcp/server.py"],
"cwd": "/path/to/Skill_Seekers"
}
}
}
```
### Virtual Environment
To use a Python virtual environment:
```bash
# Create venv
cd /path/to/Skill_Seekers
python3 -m venv venv
source venv/bin/activate
pip install -r mcp/requirements.txt
pip install requests beautifulsoup4
which python3
# Copy this path for config
```
```json
{
"mcpServers": {
"skill-seeker": {
"command": "/path/to/Skill_Seekers/venv/bin/python3",
"args": ["/path/to/Skill_Seekers/mcp/server.py"],
"cwd": "/path/to/Skill_Seekers"
}
}
}
```
### Debug Mode
Enable verbose logging:
```json
{
"mcpServers": {
"skill-seeker": {
"command": "python3",
"args": [
"-u",
"/path/to/Skill_Seekers/mcp/server.py"
],
"cwd": "/path/to/Skill_Seekers",
"env": {
"DEBUG": "1"
}
}
}
}
```
---
## Complete Example Configuration
**Minimal (recommended for most users):**
```json
{
"mcpServers": {
"skill-seeker": {
"command": "python3",
"args": [
"/Users/username/Projects/Skill_Seekers/mcp/server.py"
],
"cwd": "/Users/username/Projects/Skill_Seekers"
}
}
}
```
**With API enhancement:**
```json
{
"mcpServers": {
"skill-seeker": {
"command": "python3",
"args": [
"/Users/username/Projects/Skill_Seekers/mcp/server.py"
],
"cwd": "/Users/username/Projects/Skill_Seekers",
"env": {
"ANTHROPIC_API_KEY": "sk-ant-your-key-here"
}
}
}
}
```
---
## End-to-End Workflow
### Complete Setup and First Skill
```bash
# 1. Install
cd ~/Projects
git clone https://github.com/yusufkaraaslan/Skill_Seekers.git
cd Skill_Seekers
pip3 install -r mcp/requirements.txt
pip3 install requests beautifulsoup4
# 2. Configure
mkdir -p ~/.config/claude-code
cat > ~/.config/claude-code/mcp.json << 'EOF'
{
"mcpServers": {
"skill-seeker": {
"command": "python3",
"args": [
"/Users/username/Projects/Skill_Seekers/mcp/server.py"
],
"cwd": "/Users/username/Projects/Skill_Seekers"
}
}
}
EOF
# (Replace paths with your actual paths!)
# 3. Restart Claude Code
# 4. Test in Claude Code:
```
**In Claude Code:**
```
User: List all available configs
User: Scrape docs using configs/react.json with max 50 pages
User: Package skill at output/react/
```
**Result:** `output/react.zip` ready to upload!
---
## Next Steps
After successful setup:
1. **Try preset configs:**
- React: `scrape docs using configs/react.json`
- Vue: `scrape docs using configs/vue.json`
- Django: `scrape docs using configs/django.json`
2. **Create custom configs:**
- `generate config for [framework] at [url]`
3. **Test with small limits first:**
- Use `max_pages` parameter: `scrape docs using configs/test.json with max 20 pages`
4. **Explore enhancement:**
- Use `--enhance-local` flag for AI-powered SKILL.md improvement
---
## Getting Help
- **Documentation**: See [mcp/README.md](../mcp/README.md)
- **Issues**: [GitHub Issues](https://github.com/yusufkaraaslan/Skill_Seekers/issues)
- **Examples**: See [.github/ISSUES_TO_CREATE.md](../.github/ISSUES_TO_CREATE.md) for test cases
---
## Quick Reference Card
```
SETUP:
1. Install dependencies: pip3 install -r mcp/requirements.txt
2. Configure: ~/.config/claude-code/mcp.json
3. Restart Claude Code
VERIFY:
- "List all available configs"
- "Validate configs/react.json"
GENERATE SKILL:
1. "Generate config for [name] at [url]"
2. "Estimate pages for configs/[name].json"
3. "Scrape docs using configs/[name].json"
4. "Package skill at output/[name]/"
TROUBLESHOOTING:
- Check: cat ~/.config/claude-code/mcp.json
- Test: python3 mcp/server.py
- Logs: ~/Library/Logs/Claude Code/
```
---
Happy skill creating! 🚀

View File

@@ -20,19 +20,19 @@ Comprehensive reference for all commands, options, and workflows.
```bash
# 1. Estimate pages (fast, 1-2 min)
python3 estimate_pages.py configs/react.json
python3 cli/estimate_pages.py configs/react.json
# 2. Scrape documentation (20-40 min)
python3 doc_scraper.py --config configs/react.json
python3 cli/doc_scraper.py --config configs/react.json
# 3. Enhance with Claude Code (60 sec)
python3 enhance_skill_local.py output/react/
python3 cli/enhance_skill_local.py output/react/
# 4. Package to .zip (instant)
python3 package_skill.py output/react/
python3 cli/package_skill.py output/react/
# 5. Test everything (1 sec)
python3 run_tests.py
python3 cli/run_tests.py
```
---
@@ -70,16 +70,16 @@ options:
**1. Use Preset Config (Recommended)**
```bash
python3 doc_scraper.py --config configs/godot.json
python3 doc_scraper.py --config configs/react.json
python3 doc_scraper.py --config configs/vue.json
python3 doc_scraper.py --config configs/django.json
python3 doc_scraper.py --config configs/fastapi.json
python3 cli/doc_scraper.py --config configs/godot.json
python3 cli/doc_scraper.py --config configs/react.json
python3 cli/doc_scraper.py --config configs/vue.json
python3 cli/doc_scraper.py --config configs/django.json
python3 cli/doc_scraper.py --config configs/fastapi.json
```
**2. Interactive Mode**
```bash
python3 doc_scraper.py --interactive
python3 cli/doc_scraper.py --interactive
# Wizard walks you through:
# - Skill name
# - Base URL
@@ -92,7 +92,7 @@ python3 doc_scraper.py --interactive
**3. Quick Mode (Minimal)**
```bash
python3 doc_scraper.py \
python3 cli/doc_scraper.py \
--name react \
--url https://react.dev/ \
--description "React framework for building UIs"
@@ -100,7 +100,7 @@ python3 doc_scraper.py \
**4. Dry-Run (Preview)**
```bash
python3 doc_scraper.py --config configs/react.json --dry-run
python3 cli/doc_scraper.py --config configs/react.json --dry-run
# Shows what will be scraped without downloading data
# No directories created
# Fast validation
@@ -108,7 +108,7 @@ python3 doc_scraper.py --config configs/react.json --dry-run
**5. Skip Scraping (Use Cached Data)**
```bash
python3 doc_scraper.py --config configs/godot.json --skip-scrape
python3 cli/doc_scraper.py --config configs/godot.json --skip-scrape
# Uses existing output/godot_data/
# Fast rebuild (1-3 minutes)
# Useful for testing changes
@@ -116,7 +116,7 @@ python3 doc_scraper.py --config configs/godot.json --skip-scrape
**6. With Local Enhancement**
```bash
python3 doc_scraper.py --config configs/react.json --enhance-local
python3 cli/doc_scraper.py --config configs/react.json --enhance-local
# Scrapes + enhances in one command
# Opens new terminal for Claude Code
# No API key needed
@@ -125,10 +125,10 @@ python3 doc_scraper.py --config configs/react.json --enhance-local
**7. With API Enhancement**
```bash
export ANTHROPIC_API_KEY=sk-ant-...
python3 doc_scraper.py --config configs/react.json --enhance
python3 cli/doc_scraper.py --config configs/react.json --enhance
# Or with inline API key:
python3 doc_scraper.py --config configs/react.json --enhance --api-key sk-ant-...
python3 cli/doc_scraper.py --config configs/react.json --enhance --api-key sk-ant-...
```
### Output Structure
@@ -182,28 +182,28 @@ options:
**1. Quick Estimate (100 pages)**
```bash
python3 estimate_pages.py configs/react.json --max-discovery 100
python3 cli/estimate_pages.py configs/react.json --max-discovery 100
# Time: ~30-60 seconds
# Good for: Quick validation
```
**2. Standard Estimate (1000 pages - default)**
```bash
python3 estimate_pages.py configs/godot.json
python3 cli/estimate_pages.py configs/godot.json
# Time: ~1-2 minutes
# Good for: Most use cases
```
**3. Deep Estimate (2000 pages)**
```bash
python3 estimate_pages.py configs/vue.json --max-discovery 2000
python3 cli/estimate_pages.py configs/vue.json --max-discovery 2000
# Time: ~3-5 minutes
# Good for: Large documentation sites
```
**4. Custom Timeout**
```bash
python3 estimate_pages.py configs/django.json --timeout 60
python3 cli/estimate_pages.py configs/django.json --timeout 60
# Useful for slow servers
```
@@ -259,8 +259,8 @@ Base URL: https://react.dev/
```bash
# Usage
python3 enhance_skill_local.py output/react/
python3 enhance_skill_local.py output/godot/
python3 cli/enhance_skill_local.py output/react/
python3 cli/enhance_skill_local.py output/godot/
# What it does:
# 1. Reads SKILL.md and references/
@@ -283,10 +283,10 @@ pip3 install anthropic
# Usage with environment variable
export ANTHROPIC_API_KEY=sk-ant-...
python3 enhance_skill.py output/react/
python3 cli/enhance_skill.py output/react/
# Usage with inline API key
python3 enhance_skill.py output/godot/ --api-key sk-ant-...
python3 cli/enhance_skill.py output/godot/ --api-key sk-ant-...
# What it does:
# 1. Reads SKILL.md and references/
@@ -307,8 +307,8 @@ python3 enhance_skill.py output/godot/ --api-key sk-ant-...
```bash
# Usage
python3 package_skill.py output/react/
python3 package_skill.py output/godot/
python3 cli/package_skill.py output/react/
python3 cli/package_skill.py output/godot/
# What it does:
# 1. Validates SKILL.md exists
@@ -330,28 +330,28 @@ python3 package_skill.py output/godot/
```bash
# Run all tests (default)
python3 run_tests.py
python3 cli/run_tests.py
# 71 tests, ~1 second
# Verbose output
python3 run_tests.py -v
python3 run_tests.py --verbose
python3 cli/run_tests.py -v
python3 cli/run_tests.py --verbose
# Quiet output
python3 run_tests.py -q
python3 run_tests.py --quiet
python3 cli/run_tests.py -q
python3 cli/run_tests.py --quiet
# Stop on first failure
python3 run_tests.py -f
python3 run_tests.py --failfast
python3 cli/run_tests.py -f
python3 cli/run_tests.py --failfast
# Run specific test suite
python3 run_tests.py --suite config
python3 run_tests.py --suite features
python3 run_tests.py --suite integration
python3 cli/run_tests.py --suite config
python3 cli/run_tests.py --suite features
python3 cli/run_tests.py --suite integration
# List all tests
python3 run_tests.py --list
python3 cli/run_tests.py --list
```
### Individual Tests
@@ -434,13 +434,13 @@ python3 -m json.tool configs/godot.json
```bash
# 1. Estimate (optional, 1-2 min)
python3 estimate_pages.py configs/react.json
python3 cli/estimate_pages.py configs/react.json
# 2. Scrape with local enhancement (25 min)
python3 doc_scraper.py --config configs/react.json --enhance-local
python3 cli/doc_scraper.py --config configs/react.json --enhance-local
# 3. Package (instant)
python3 package_skill.py output/react/
python3 cli/package_skill.py output/react/
# Result: output/react.zip
# Upload to Claude!
@@ -461,26 +461,26 @@ cat > configs/my-docs.json << 'EOF'
EOF
# 2. Estimate
python3 estimate_pages.py configs/my-docs.json
python3 cli/estimate_pages.py configs/my-docs.json
# 3. Dry-run test
python3 doc_scraper.py --config configs/my-docs.json --dry-run
python3 cli/doc_scraper.py --config configs/my-docs.json --dry-run
# 4. Full scrape
python3 doc_scraper.py --config configs/my-docs.json
python3 cli/doc_scraper.py --config configs/my-docs.json
# 5. Enhance
python3 enhance_skill_local.py output/my-docs/
python3 cli/enhance_skill_local.py output/my-docs/
# 6. Package
python3 package_skill.py output/my-docs/
python3 cli/package_skill.py output/my-docs/
```
### Workflow 3: Interactive Mode
```bash
# 1. Start interactive wizard
python3 doc_scraper.py --interactive
python3 cli/doc_scraper.py --interactive
# 2. Answer prompts:
# - Name: my-framework
@@ -491,16 +491,16 @@ python3 doc_scraper.py --interactive
# - Max pages: 100
# 3. Enhance
python3 enhance_skill_local.py output/my-framework/
python3 cli/enhance_skill_local.py output/my-framework/
# 4. Package
python3 package_skill.py output/my-framework/
python3 cli/package_skill.py output/my-framework/
```
### Workflow 4: Quick Mode
```bash
python3 doc_scraper.py \
python3 cli/doc_scraper.py \
--name vue \
--url https://vuejs.org/ \
--description "Vue.js framework" \
@@ -512,13 +512,13 @@ python3 doc_scraper.py \
```bash
# Already scraped once?
# Skip re-scraping, just rebuild
python3 doc_scraper.py --config configs/godot.json --skip-scrape
python3 cli/doc_scraper.py --config configs/godot.json --skip-scrape
# Try new enhancement
python3 enhance_skill_local.py output/godot/
python3 cli/enhance_skill_local.py output/godot/
# Re-package
python3 package_skill.py output/godot/
python3 cli/package_skill.py output/godot/
```
### Workflow 6: Testing New Config
@@ -535,13 +535,13 @@ cat > configs/test.json << 'EOF'
EOF
# 2. Estimate
python3 estimate_pages.py configs/test.json --max-discovery 50
python3 cli/estimate_pages.py configs/test.json --max-discovery 50
# 3. Dry-run
python3 doc_scraper.py --config configs/test.json --dry-run
python3 cli/doc_scraper.py --config configs/test.json --dry-run
# 4. Small scrape
python3 doc_scraper.py --config configs/test.json
python3 cli/doc_scraper.py --config configs/test.json
# 5. Validate output
ls output/test-site/
@@ -572,7 +572,7 @@ ls output/test-site/references/
```bash
# Estimate first
python3 estimate_pages.py configs/my-config.json
python3 cli/estimate_pages.py configs/my-config.json
# Set max_pages based on estimate
# Add buffer: estimated + 50
@@ -622,7 +622,7 @@ python3 -m unittest tests.test_config_validation.TestConfigValidation.test_name
echo $ANTHROPIC_API_KEY
# Or use inline:
python3 enhance_skill.py output/react/ --api-key sk-ant-...
python3 cli/enhance_skill.py output/react/ --api-key sk-ant-...
```
### Issue: "Package fails"
@@ -632,7 +632,7 @@ python3 enhance_skill.py output/react/ --api-key sk-ant-...
ls output/my-skill/SKILL.md
# If missing, build first:
python3 doc_scraper.py --config configs/my-skill.json --skip-scrape
python3 cli/doc_scraper.py --config configs/my-skill.json --skip-scrape
```
### Issue: "Can't find output"
@@ -773,9 +773,9 @@ Skill_Seekers/
```bash
# Tool-specific help
python3 doc_scraper.py --help
python3 estimate_pages.py --help
python3 run_tests.py --help
python3 cli/doc_scraper.py --help
python3 cli/estimate_pages.py --help
python3 cli/run_tests.py --help
# Documentation
cat CLAUDE.md # Quick reference for Claude Code
@@ -793,18 +793,18 @@ cat README.md # Project overview
**Essential Commands:**
```bash
python3 estimate_pages.py configs/react.json # Estimate
python3 doc_scraper.py --config configs/react.json # Scrape
python3 enhance_skill_local.py output/react/ # Enhance
python3 package_skill.py output/react/ # Package
python3 run_tests.py # Test
python3 cli/estimate_pages.py configs/react.json # Estimate
python3 cli/doc_scraper.py --config configs/react.json # Scrape
python3 cli/enhance_skill_local.py output/react/ # Enhance
python3 cli/package_skill.py output/react/ # Package
python3 cli/run_tests.py # Test
```
**Quick Start:**
```bash
pip3 install requests beautifulsoup4
python3 doc_scraper.py --config configs/react.json --enhance-local
python3 package_skill.py output/react/
python3 cli/doc_scraper.py --config configs/react.json --enhance-local
python3 cli/package_skill.py output/react/
# Upload output/react.zip to Claude!
```

View File

@@ -0,0 +1,567 @@
# MCP Integration Test Results
Test documentation for Skill Seeker MCP server with Claude Code.
---
## Test Overview
**Goal:** Verify MCP server works correctly with actual Claude Code instance
**Date:** [To be filled when tested]
**Tester:** [To be filled]
**Environment:**
- OS: [macOS / Linux / Windows WSL]
- Python Version: [e.g., 3.11.5]
- Claude Code Version: [e.g., 1.0.0]
- MCP Package Version: [e.g., 0.9.0]
---
## Setup Checklist
- [ ] Python 3.7+ installed
- [ ] Claude Code installed and running
- [ ] Repository cloned
- [ ] MCP dependencies installed (`pip3 install -r mcp/requirements.txt`)
- [ ] CLI dependencies installed (`pip3 install requests beautifulsoup4`)
- [ ] MCP server configured in `~/.config/claude-code/mcp.json`
- [ ] Claude Code restarted after configuration
---
## Test Cases
### Test 1: List Configs
**Command:**
```
List all available configs
```
**Expected Result:**
- Shows 7 preset configurations
- Lists: godot, react, vue, django, fastapi, kubernetes, steam-economy-complete
- Each with description
**Actual Result:**
```
[To be filled]
```
**Status:** [ ] Pass / [ ] Fail
**Notes:**
```
[Any observations]
```
---
### Test 2: Validate Config
**Command:**
```
Validate configs/react.json
```
**Expected Result:**
- Shows "Config is valid"
- Displays config details (base_url, max_pages, rate_limit, categories)
- No errors or warnings
**Actual Result:**
```
[To be filled]
```
**Status:** [ ] Pass / [ ] Fail
**Notes:**
```
[Any observations]
```
---
### Test 3: Generate Config
**Command:**
```
Generate config for Tailwind CSS at https://tailwindcss.com/docs
```
**Expected Result:**
- Creates `configs/tailwind.json`
- File contains valid JSON
- Has required fields: name, base_url, description
- Has default values for optional fields
**Actual Result:**
```
[To be filled]
```
**Config File Created:** [ ] Yes / [ ] No
**Config Validation:**
```bash
# Verify file exists
ls configs/tailwind.json
# Verify valid JSON
python3 -m json.tool configs/tailwind.json
# Check contents
cat configs/tailwind.json
```
**Status:** [ ] Pass / [ ] Fail
**Notes:**
```
[Any observations]
```
---
### Test 4: Estimate Pages
**Command:**
```
Estimate pages for configs/react.json with max discovery 100
```
**Expected Result:**
- Shows progress during estimation
- Completes in ~30-60 seconds
- Shows discovered pages count
- Shows estimated total
- Recommends max_pages value
- No errors or timeouts
**Actual Result:**
```
[To be filled]
```
**Performance:**
- Time taken: [X seconds]
- Pages discovered: [X]
- Estimated total: [X]
**Status:** [ ] Pass / [ ] Fail
**Notes:**
```
[Any observations]
```
---
### Test 5: Scrape Docs (Small Test)
**Command:**
```
Scrape docs using configs/kubernetes.json with max 10 pages
```
**Expected Result:**
- Creates `output/kubernetes_data/` directory
- Creates `output/kubernetes/` skill directory
- Generates `output/kubernetes/SKILL.md`
- Creates reference files in `output/kubernetes/references/`
- Completes in ~1-2 minutes (for 10 pages)
- No errors during scraping
**Actual Result:**
```
[To be filled]
```
**Files Created:**
```bash
# Check directories
ls output/kubernetes_data/
ls output/kubernetes/
ls output/kubernetes/references/
# Check SKILL.md
wc -l output/kubernetes/SKILL.md
# Count reference files
ls output/kubernetes/references/ | wc -l
```
**Performance:**
- Time taken: [X minutes]
- Pages scraped: [X]
- Reference files created: [X]
**Status:** [ ] Pass / [ ] Fail
**Notes:**
```
[Any observations]
```
---
### Test 6: Package Skill
**Command:**
```
Package skill at output/kubernetes/
```
**Expected Result:**
- Creates `output/kubernetes.zip`
- File is valid ZIP archive
- Contains SKILL.md and references/
- Size is reasonable (< 10 MB for 10 pages)
- Completes in < 5 seconds
**Actual Result:**
```
[To be filled]
```
**File Verification:**
```bash
# Check file exists
ls -lh output/kubernetes.zip
# Check ZIP contents
unzip -l output/kubernetes.zip
# Verify ZIP is valid
unzip -t output/kubernetes.zip
```
**Performance:**
- Time taken: [X seconds]
- ZIP file size: [X MB]
**Status:** [ ] Pass / [ ] Fail
**Notes:**
```
[Any observations]
```
---
## Additional Tests
### Test 7: Error Handling - Invalid Config
**Command:**
```
Validate configs/nonexistent.json
```
**Expected Result:**
- Shows clear error message
- Does not crash
- Suggests checking file path
**Actual Result:**
```
[To be filled]
```
**Status:** [ ] Pass / [ ] Fail
---
### Test 8: Error Handling - Invalid URL
**Command:**
```
Generate config for Test at not-a-valid-url
```
**Expected Result:**
- Shows error about invalid URL
- Does not create config file
- Does not crash
**Actual Result:**
```
[To be filled]
```
**Status:** [ ] Pass / [ ] Fail
---
### Test 9: Concurrent Tool Calls
**Commands (rapid succession):**
```
1. List all available configs
2. Validate configs/react.json
3. Validate configs/vue.json
```
**Expected Result:**
- All commands execute successfully
- No race conditions
- Responses are correct for each command
**Actual Result:**
```
[To be filled]
```
**Status:** [ ] Pass / [ ] Fail
---
### Test 10: Large Scrape Operation
**Command:**
```
Scrape docs using configs/react.json with max 100 pages
```
**Expected Result:**
- Handles long-running operation (10-15 minutes)
- Shows progress or remains responsive
- Completes successfully
- Creates comprehensive skill
- No memory leaks
**Actual Result:**
```
[To be filled]
```
**Performance:**
- Time taken: [X minutes]
- Pages scraped: [X]
- Memory usage: [X MB]
- Peak memory: [X MB]
**Status:** [ ] Pass / [ ] Fail
---
## Performance Metrics
| Operation | Expected Time | Actual Time | Status |
|-----------|--------------|-------------|--------|
| List configs | < 1s | [X]s | [ ] |
| Validate config | < 2s | [X]s | [ ] |
| Generate config | < 3s | [X]s | [ ] |
| Estimate pages (100) | 30-60s | [X]s | [ ] |
| Scrape 10 pages | 1-2 min | [X]min | [ ] |
| Scrape 100 pages | 10-15 min | [X]min | [ ] |
| Package skill | < 5s | [X]s | [ ] |
---
## Issues Found
### Issue 1: [Title]
**Severity:** [ ] Critical / [ ] High / [ ] Medium / [ ] Low
**Description:**
```
[Detailed description of the issue]
```
**Steps to Reproduce:**
1. [Step 1]
2. [Step 2]
3. [Step 3]
**Expected Behavior:**
```
[What should happen]
```
**Actual Behavior:**
```
[What actually happened]
```
**Error Messages:**
```
[Any error messages or logs]
```
**Workaround:**
```
[Temporary solution, if any]
```
**Fix Required:** [ ] Yes / [ ] No
---
### Issue 2: [Title]
[Same format as Issue 1]
---
## Configuration Used
```json
{
"mcpServers": {
"skill-seeker": {
"command": "python3",
"args": [
"/path/to/Skill_Seekers/mcp/server.py"
],
"cwd": "/path/to/Skill_Seekers"
}
}
}
```
---
## Summary
**Total Tests:** 10
**Tests Passed:** [X]
**Tests Failed:** [X]
**Tests Skipped:** [X]
**Overall Status:** [ ] Pass / [ ] Fail / [ ] Partial
**Recommendation:**
```
[Ready for production / Needs fixes / Requires more testing]
```
---
## Observations
### What Worked Well
- [Observation 1]
- [Observation 2]
- [Observation 3]
### What Needs Improvement
- [Observation 1]
- [Observation 2]
- [Observation 3]
### Suggestions
- [Suggestion 1]
- [Suggestion 2]
- [Suggestion 3]
---
## Next Steps
- [ ] Address critical issues
- [ ] Re-test failed cases
- [ ] Document workarounds
- [ ] Update MCP server if needed
- [ ] Update documentation based on findings
- [ ] Create GitHub issues for bugs found
---
## Appendix: Test Commands Reference
```bash
# Quick test sequence
echo "Test 1: List configs"
# User says: "List all available configs"
echo "Test 2: Validate"
# User says: "Validate configs/react.json"
echo "Test 3: Generate"
# User says: "Generate config for Tailwind CSS at https://tailwindcss.com/docs"
echo "Test 4: Estimate"
# User says: "Estimate pages for configs/tailwind.json"
echo "Test 5: Scrape"
# User says: "Scrape docs using configs/tailwind.json with max 10 pages"
echo "Test 6: Package"
# User says: "Package skill at output/tailwind/"
# Verify results
ls configs/tailwind.json
ls output/tailwind/SKILL.md
ls output/tailwind.zip
```
---
## Test Environment Setup Script
```bash
#!/bin/bash
# Test environment setup
echo "Setting up MCP integration test environment..."
# 1. Check prerequisites
echo "Checking Python version..."
python3 --version
echo "Checking Claude Code..."
# (Manual check required)
# 2. Install dependencies
echo "Installing dependencies..."
pip3 install -r mcp/requirements.txt
pip3 install requests beautifulsoup4
# 3. Verify installation
echo "Verifying MCP server..."
timeout 2 python3 mcp/server.py || echo "Server can start"
# 4. Create test output directory
echo "Creating test directories..."
mkdir -p test_output
echo "Setup complete! Ready for testing."
echo "Next: Configure Claude Code MCP settings and restart"
```
---
## Cleanup Script
```bash
#!/bin/bash
# Cleanup after tests
echo "Cleaning up test artifacts..."
# Remove test configs
rm -f configs/tailwind.json
rm -f configs/test*.json
# Remove test output
rm -rf output/tailwind*
rm -rf output/kubernetes*
rm -rf test_output
echo "Cleanup complete!"
```
---
**Testing Status:** [ ] Not Started / [ ] In Progress / [ ] Completed
**Sign-off:**
- Tester: [Name]
- Date: [YYYY-MM-DD]
- Approved: [ ] Yes / [ ] No