mirror of
https://github.com/duthaho/claudekit.git
synced 2026-07-15 20:25:19 +03:00
feat: Integrate MCP servers for enhanced capabilities
This commit is contained in:
duthaho
+3
-2
@@ -285,8 +285,9 @@ Optional MCP servers for extended capabilities.
|
||||
|--------|---------|--------|
|
||||
| Context7 | Library documentation lookup | Optional |
|
||||
| Sequential | Multi-step reasoning tools | Optional |
|
||||
| Puppeteer | Browser automation | Optional |
|
||||
| Magic | UI component generation | Optional |
|
||||
| Playwright | Browser automation (Microsoft) | Optional |
|
||||
| Memory | Persistent knowledge graph | Optional |
|
||||
| Filesystem | Secure file operations | Optional |
|
||||
|
||||
Setup: See `.claude/mcp/README.md`
|
||||
|
||||
|
||||
@@ -180,6 +180,36 @@ After design is complete:
|
||||
| 4 | 8-10 | Comprehensive |
|
||||
| 5 | 10+ | Exhaustive, all angles |
|
||||
|
||||
## MCP Integration
|
||||
|
||||
This command leverages MCP servers for enhanced brainstorming:
|
||||
|
||||
### Sequential Thinking - Structured Exploration (Primary)
|
||||
```
|
||||
ALWAYS use Sequential Thinking for brainstorming:
|
||||
- Explore design options systematically
|
||||
- Track pros/cons for each approach
|
||||
- Revise conclusions based on user feedback
|
||||
- Build confidence in final design incrementally
|
||||
```
|
||||
|
||||
### Memory - Design Persistence
|
||||
```
|
||||
Store design decisions for continuity:
|
||||
- Create entities for design concepts
|
||||
- Store user preferences and constraints
|
||||
- Recall previous design patterns
|
||||
- Build knowledge graph of architecture decisions
|
||||
```
|
||||
|
||||
### Context7 - Technology Options
|
||||
```
|
||||
When exploring technology choices:
|
||||
- Fetch current documentation for options
|
||||
- Compare library capabilities accurately
|
||||
- Understand trade-offs with real data
|
||||
```
|
||||
|
||||
## When NOT to Use
|
||||
|
||||
- Clear "mechanical" processes with known implementation
|
||||
|
||||
@@ -200,6 +200,47 @@ git diff --staged
|
||||
/feature --format=concise "add logging utility"
|
||||
```
|
||||
|
||||
## MCP Integration
|
||||
|
||||
This command leverages MCP servers for enhanced capabilities:
|
||||
|
||||
### Context7 - Library Documentation
|
||||
When researching unfamiliar libraries or frameworks:
|
||||
```
|
||||
Use Context7's resolve-library-id and get-library-docs tools to fetch
|
||||
current documentation for any libraries involved in the feature.
|
||||
```
|
||||
|
||||
### Sequential Thinking - Structured Planning
|
||||
For complex feature breakdowns:
|
||||
```
|
||||
Use Sequential Thinking's sequentialthinking tool for step-by-step
|
||||
analysis when decomposing requirements or designing architecture.
|
||||
```
|
||||
|
||||
### Memory - Context Persistence
|
||||
Store and recall project context:
|
||||
```
|
||||
- Store architectural decisions made during planning
|
||||
- Recall user preferences from previous sessions
|
||||
- Remember patterns used in similar features
|
||||
```
|
||||
|
||||
### Filesystem - File Operations
|
||||
For creating and modifying files:
|
||||
```
|
||||
- Use directory_tree to understand project structure
|
||||
- Use search_files to find related implementations
|
||||
- Use read_file and write_file for file operations
|
||||
```
|
||||
|
||||
### Playwright - E2E Testing
|
||||
For features with UI components:
|
||||
```
|
||||
Use Playwright for browser-based E2E testing of the implemented feature.
|
||||
Validate user flows and interactions in real browser environment.
|
||||
```
|
||||
|
||||
<!-- CUSTOMIZATION POINT -->
|
||||
## Variations
|
||||
|
||||
|
||||
@@ -262,6 +262,53 @@ for item in items:
|
||||
| `performance` | Speed, memory, efficiency |
|
||||
| `reliability` | Error handling, edge cases |
|
||||
|
||||
## MCP Integration
|
||||
|
||||
This command leverages MCP servers for enhanced debugging:
|
||||
|
||||
### Sequential Thinking - Root Cause Analysis (Primary)
|
||||
```
|
||||
ALWAYS use Sequential Thinking for debugging:
|
||||
- Trace execution path step-by-step
|
||||
- Form and test hypotheses systematically
|
||||
- Track confidence in each potential cause
|
||||
- Revise understanding as evidence emerges
|
||||
```
|
||||
|
||||
### Memory - Bug Context
|
||||
```
|
||||
Store and recall debugging context:
|
||||
- Remember similar bugs from previous sessions
|
||||
- Recall fix patterns that worked before
|
||||
- Store root cause analysis for future reference
|
||||
- Create relations between bugs and affected components
|
||||
```
|
||||
|
||||
### Playwright - Browser Testing
|
||||
```
|
||||
For UI/frontend bugs:
|
||||
- Reproduce the bug in browser environment
|
||||
- Test fix across different browsers
|
||||
- Verify visual regressions are resolved
|
||||
- Automate regression test for the fix
|
||||
```
|
||||
|
||||
### Context7 - Library Issues
|
||||
```
|
||||
When debugging library-related issues:
|
||||
- Fetch current documentation for correct usage
|
||||
- Check for known issues or breaking changes
|
||||
- Find correct patterns and examples
|
||||
```
|
||||
|
||||
### Filesystem - Code Search
|
||||
```
|
||||
For tracing bug across codebase:
|
||||
- Use search_files to find related code
|
||||
- Use read_file to examine suspicious areas
|
||||
- Track changes with file history
|
||||
```
|
||||
|
||||
<!-- CUSTOMIZATION POINT -->
|
||||
## Variations
|
||||
|
||||
|
||||
@@ -120,3 +120,25 @@ After generating the index, inform the user:
|
||||
2. Number of files indexed
|
||||
3. Key components discovered
|
||||
4. Suggest using `/load` to load specific components into context
|
||||
|
||||
## MCP Integration
|
||||
|
||||
This command leverages MCP servers for enhanced indexing:
|
||||
|
||||
### Filesystem - Project Scanning (Primary)
|
||||
```
|
||||
ALWAYS use Filesystem for project scanning:
|
||||
- Use directory_tree for full structure view
|
||||
- Use list_directory for targeted exploration
|
||||
- Use search_files to find specific patterns
|
||||
- Use get_file_info for file metadata
|
||||
```
|
||||
|
||||
### Memory - Project Knowledge
|
||||
```
|
||||
Store project structure in knowledge graph:
|
||||
- Create entities for key modules
|
||||
- Store component relationships
|
||||
- Recall structure in future sessions
|
||||
- Build project understanding over time
|
||||
```
|
||||
|
||||
@@ -285,6 +285,44 @@ Use `/execute-plan [plan-file]` for subagent-driven execution with code review g
|
||||
| `deep-research` | Complex features needing investigation |
|
||||
| `implementation` | Quick plans for clear tasks |
|
||||
|
||||
## MCP Integration
|
||||
|
||||
This command leverages MCP servers for enhanced planning:
|
||||
|
||||
### Sequential Thinking - Structured Planning (Primary)
|
||||
```
|
||||
ALWAYS use Sequential Thinking for task decomposition:
|
||||
- Break complex tasks into logical thought sequences
|
||||
- Track dependencies between steps
|
||||
- Revise plan as understanding deepens
|
||||
- Use for risk identification and mitigation planning
|
||||
```
|
||||
|
||||
### Memory - Decision Persistence
|
||||
```
|
||||
Store and recall planning context:
|
||||
- Remember decisions from previous planning sessions
|
||||
- Recall user preferences for task sizing
|
||||
- Store architectural patterns for reuse
|
||||
- Create entities for major features/components
|
||||
```
|
||||
|
||||
### Context7 - Technology Research
|
||||
```
|
||||
When planning involves unfamiliar technologies:
|
||||
- Fetch current documentation for accurate estimates
|
||||
- Understand API patterns before estimating complexity
|
||||
- Identify potential integration challenges
|
||||
```
|
||||
|
||||
### Filesystem - Codebase Analysis
|
||||
```
|
||||
For accurate file identification:
|
||||
- Use directory_tree to understand project structure
|
||||
- Use search_files to find existing patterns
|
||||
- Identify files to create vs modify
|
||||
```
|
||||
|
||||
<!-- CUSTOMIZATION POINT -->
|
||||
## Variations
|
||||
|
||||
|
||||
@@ -61,6 +61,34 @@ Research: **$ARGUMENTS**
|
||||
| 4 | Comprehensive with trade-offs |
|
||||
| 5 | Exhaustive with citations |
|
||||
|
||||
## MCP Integration
|
||||
|
||||
This command leverages MCP servers for enhanced research:
|
||||
|
||||
### Context7 - Library Documentation (Primary)
|
||||
```
|
||||
ALWAYS use Context7 for library/framework research:
|
||||
1. Use resolve-library-id to find the library ID
|
||||
2. Use get-library-docs with topic parameter for focused docs
|
||||
3. Use mode='code' for API references, mode='info' for concepts
|
||||
```
|
||||
|
||||
### Sequential Thinking - Structured Analysis
|
||||
```
|
||||
For complex research requiring step-by-step reasoning:
|
||||
- Use sequentialthinking tool to break down analysis
|
||||
- Track confidence scores for each finding
|
||||
- Revise conclusions as new information emerges
|
||||
```
|
||||
|
||||
### Memory - Persistent Research
|
||||
```
|
||||
Store research findings for future reference:
|
||||
- Create entities for researched technologies
|
||||
- Add observations with pros/cons/recommendations
|
||||
- Link related technologies with relations
|
||||
```
|
||||
|
||||
## Output
|
||||
|
||||
```markdown
|
||||
|
||||
@@ -291,6 +291,45 @@ Found **1 critical issue** (security), **2 recommendations**, and **2 suggestion
|
||||
| `quality` | Readability, maintainability |
|
||||
| `testing` | Coverage, test patterns |
|
||||
|
||||
## MCP Integration
|
||||
|
||||
This command leverages MCP servers for enhanced code review:
|
||||
|
||||
### Playwright - Visual/UI Review
|
||||
```
|
||||
For reviewing UI changes:
|
||||
- Render and screenshot components
|
||||
- Compare visual changes across browsers
|
||||
- Verify responsive behavior
|
||||
- Check accessibility in real browser
|
||||
```
|
||||
|
||||
### Memory - Review Context
|
||||
```
|
||||
Store and recall review context:
|
||||
- Remember past review decisions
|
||||
- Recall user's coding standards
|
||||
- Store patterns approved/rejected previously
|
||||
- Track recurring issues across reviews
|
||||
```
|
||||
|
||||
### Sequential Thinking - Systematic Analysis
|
||||
```
|
||||
For thorough code analysis:
|
||||
- Step through complex logic systematically
|
||||
- Track multiple concerns in parallel
|
||||
- Build comprehensive issue list
|
||||
- Revise severity as context emerges
|
||||
```
|
||||
|
||||
### Filesystem - Code Access
|
||||
```
|
||||
For reviewing file changes:
|
||||
- Use read_file to examine code
|
||||
- Use search_files to find related patterns
|
||||
- Check for similar issues across codebase
|
||||
```
|
||||
|
||||
<!-- CUSTOMIZATION POINT -->
|
||||
## Variations
|
||||
|
||||
|
||||
@@ -288,6 +288,44 @@ pytest tests/services/auth.test.ts -v
|
||||
| `jest` | JavaScript |
|
||||
| `playwright` | E2E (any) |
|
||||
|
||||
## MCP Integration
|
||||
|
||||
This command leverages MCP servers for enhanced testing:
|
||||
|
||||
### Playwright - E2E Testing (Primary for UI)
|
||||
```
|
||||
For E2E and browser tests:
|
||||
- Use Playwright for cross-browser testing
|
||||
- Automate user flow verification
|
||||
- Capture screenshots for visual testing
|
||||
- Test on different device emulations
|
||||
```
|
||||
|
||||
### Filesystem - Test File Management
|
||||
```
|
||||
For test file operations:
|
||||
- Use directory_tree to find test directories
|
||||
- Use search_files to find existing tests
|
||||
- Use read_file to check test patterns
|
||||
- Use write_file to create new test files
|
||||
```
|
||||
|
||||
### Context7 - Testing Best Practices
|
||||
```
|
||||
For framework-specific testing:
|
||||
- Fetch current testing library docs
|
||||
- Get latest assertions and matchers
|
||||
- Find recommended testing patterns
|
||||
```
|
||||
|
||||
### Memory - Test Patterns
|
||||
```
|
||||
Recall testing context:
|
||||
- Remember project testing conventions
|
||||
- Recall mock patterns used previously
|
||||
- Store common test fixtures
|
||||
```
|
||||
|
||||
<!-- CUSTOMIZATION POINT -->
|
||||
## Variations
|
||||
|
||||
|
||||
+168
-19
@@ -8,8 +8,9 @@ Model Context Protocol (MCP) servers extend Claude Code capabilities with specia
|
||||
|--------|---------|--------|
|
||||
| Context7 | Up-to-date library documentation | Optional |
|
||||
| Sequential | Multi-step reasoning tools | Optional |
|
||||
| Puppeteer | Browser automation | Optional |
|
||||
| Magic | UI component generation | Optional |
|
||||
| Playwright | Browser automation (Microsoft) | Optional |
|
||||
| Memory | Persistent knowledge graph | Optional |
|
||||
| Filesystem | Secure file operations | Optional |
|
||||
|
||||
## Installation
|
||||
|
||||
@@ -21,14 +22,48 @@ Model Context Protocol (MCP) servers extend Claude Code capabilities with specia
|
||||
|
||||
MCP servers are configured in your Claude Code settings:
|
||||
|
||||
**Location**: `~/.claude/settings.json` (user) or `.claude/settings.json` (project)
|
||||
**Location**: `~/.claude/settings.json` (user) or `.mcp.json` (project)
|
||||
|
||||
### Quick Setup
|
||||
|
||||
1. Copy the desired configuration from the server-specific JSON files
|
||||
2. Add to your `settings.json` under `mcpServers`
|
||||
1. Copy the configuration for your platform (see below)
|
||||
2. Add to your `.mcp.json` or `settings.json` under `mcpServers`
|
||||
3. Restart Claude Code
|
||||
|
||||
## Platform-Specific Configuration
|
||||
|
||||
MCP server configuration differs between platforms:
|
||||
|
||||
### Linux / macOS
|
||||
|
||||
```json
|
||||
{
|
||||
"mcpServers": {
|
||||
"context7": {
|
||||
"command": "npx",
|
||||
"args": ["-y", "@upstash/context7-mcp"]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Windows
|
||||
|
||||
Windows requires the `cmd /c` wrapper to execute npx:
|
||||
|
||||
```json
|
||||
{
|
||||
"mcpServers": {
|
||||
"context7": {
|
||||
"command": "cmd",
|
||||
"args": ["/c", "npx", "-y", "@upstash/context7-mcp"]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
> **Note**: The `.mcp.json` included in this repository uses Windows syntax. Linux/macOS users should use the configurations in this README.
|
||||
|
||||
## Server Configurations
|
||||
|
||||
### Context7 (Documentation Lookup)
|
||||
@@ -40,7 +75,7 @@ Provides up-to-date documentation for libraries and frameworks.
|
||||
"mcpServers": {
|
||||
"context7": {
|
||||
"command": "npx",
|
||||
"args": ["-y", "@context7/mcp-server"]
|
||||
"args": ["-y", "@upstash/context7-mcp"]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -48,6 +83,10 @@ Provides up-to-date documentation for libraries and frameworks.
|
||||
|
||||
**Usage**: Ask about any library and get current documentation.
|
||||
|
||||
**Tools**:
|
||||
- `resolve-library-id` - Find library IDs for documentation lookup
|
||||
- `get-library-docs` - Fetch documentation for a specific library
|
||||
|
||||
### Sequential Thinking
|
||||
|
||||
Provides structured reasoning tools for complex problem-solving.
|
||||
@@ -65,16 +104,19 @@ Provides structured reasoning tools for complex problem-solving.
|
||||
|
||||
**Usage**: Complex analysis with step-by-step reasoning.
|
||||
|
||||
### Puppeteer (Browser Automation)
|
||||
**Tools**:
|
||||
- `sequentialthinking` - Dynamic problem-solving through thought sequences
|
||||
|
||||
Enables browser automation for testing and web interaction.
|
||||
### Playwright (Browser Automation)
|
||||
|
||||
Microsoft's browser automation using accessibility tree for fast, LLM-friendly interaction.
|
||||
|
||||
```json
|
||||
{
|
||||
"mcpServers": {
|
||||
"puppeteer": {
|
||||
"playwright": {
|
||||
"command": "npx",
|
||||
"args": ["-y", "@modelcontextprotocol/server-puppeteer"]
|
||||
"args": ["-y", "@playwright/mcp"]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -82,44 +124,149 @@ Enables browser automation for testing and web interaction.
|
||||
|
||||
**Usage**: Web testing, screenshots, form automation.
|
||||
|
||||
### Magic (UI Generation)
|
||||
**Key Features**:
|
||||
- Fast and lightweight - uses accessibility tree, not pixels
|
||||
- LLM-friendly - no vision models needed
|
||||
- Supports Chrome, Firefox, WebKit, Edge
|
||||
- Device emulation and profile management
|
||||
|
||||
Generates UI components from descriptions.
|
||||
**Command-Line Options**:
|
||||
- `--browser <browser>` - Browser to use (chrome, firefox, webkit, msedge)
|
||||
- `--headless` - Run browser in headless mode
|
||||
- `--viewport-size <size>` - Viewport size (e.g., "1280x720")
|
||||
- `--device <device>` - Device to emulate (e.g., "iPhone 15")
|
||||
|
||||
### Memory (Persistent Knowledge Graph)
|
||||
|
||||
Maintains persistent memory across sessions using a local knowledge graph.
|
||||
|
||||
```json
|
||||
{
|
||||
"mcpServers": {
|
||||
"magic": {
|
||||
"memory": {
|
||||
"command": "npx",
|
||||
"args": ["-y", "@anthropic/magic-mcp-server"]
|
||||
"args": ["-y", "@modelcontextprotocol/server-memory"]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Usage**: Generate React/Vue components from descriptions.
|
||||
**Usage**: Remember information across conversations and sessions.
|
||||
|
||||
**Tools**:
|
||||
- `create_entities` - Create new entities in the knowledge graph
|
||||
- `create_relations` - Create relationships between entities
|
||||
- `add_observations` - Add observations to entities
|
||||
- `delete_entities` - Remove entities from the graph
|
||||
- `delete_observations` - Remove observations
|
||||
- `delete_relations` - Remove relationships
|
||||
- `read_graph` - Read the entire knowledge graph
|
||||
- `search_nodes` - Search for entities
|
||||
- `open_nodes` - Open specific entities by name
|
||||
|
||||
### Filesystem (Secure File Operations)
|
||||
|
||||
Enables secure file operations with configurable access controls.
|
||||
|
||||
```json
|
||||
{
|
||||
"mcpServers": {
|
||||
"filesystem": {
|
||||
"command": "npx",
|
||||
"args": ["-y", "@modelcontextprotocol/server-filesystem", "."]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Usage**: Read, write, and manage files with access controls.
|
||||
|
||||
**Tools**:
|
||||
- `read_file` - Read file contents
|
||||
- `read_multiple_files` - Read multiple files at once
|
||||
- `write_file` - Write content to a file
|
||||
- `edit_file` - Make edits to a file
|
||||
- `create_directory` - Create a new directory
|
||||
- `list_directory` - List directory contents
|
||||
- `directory_tree` - Get directory tree structure
|
||||
- `move_file` - Move or rename files
|
||||
- `search_files` - Search for files by pattern
|
||||
- `get_file_info` - Get file metadata
|
||||
|
||||
**Note**: The last argument specifies the allowed directory (`.` for current directory).
|
||||
|
||||
## Full Configuration Example
|
||||
|
||||
### Linux / macOS
|
||||
|
||||
```json
|
||||
{
|
||||
"mcpServers": {
|
||||
"context7": {
|
||||
"command": "npx",
|
||||
"args": ["-y", "@context7/mcp-server"]
|
||||
"args": ["-y", "@upstash/context7-mcp"]
|
||||
},
|
||||
"sequential": {
|
||||
"command": "npx",
|
||||
"args": ["-y", "@modelcontextprotocol/server-sequential-thinking"]
|
||||
},
|
||||
"puppeteer": {
|
||||
"playwright": {
|
||||
"command": "npx",
|
||||
"args": ["-y", "@modelcontextprotocol/server-puppeteer"]
|
||||
"args": ["-y", "@playwright/mcp"]
|
||||
},
|
||||
"memory": {
|
||||
"command": "npx",
|
||||
"args": ["-y", "@modelcontextprotocol/server-memory"]
|
||||
},
|
||||
"filesystem": {
|
||||
"command": "npx",
|
||||
"args": ["-y", "@modelcontextprotocol/server-filesystem", "."]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Windows
|
||||
|
||||
```json
|
||||
{
|
||||
"mcpServers": {
|
||||
"context7": {
|
||||
"command": "cmd",
|
||||
"args": ["/c", "npx", "-y", "@upstash/context7-mcp"]
|
||||
},
|
||||
"sequential": {
|
||||
"command": "cmd",
|
||||
"args": ["/c", "npx", "-y", "@modelcontextprotocol/server-sequential-thinking"]
|
||||
},
|
||||
"playwright": {
|
||||
"command": "cmd",
|
||||
"args": ["/c", "npx", "-y", "@playwright/mcp"]
|
||||
},
|
||||
"memory": {
|
||||
"command": "cmd",
|
||||
"args": ["/c", "npx", "-y", "@modelcontextprotocol/server-memory"]
|
||||
},
|
||||
"filesystem": {
|
||||
"command": "cmd",
|
||||
"args": ["/c", "npx", "-y", "@modelcontextprotocol/server-filesystem", "."]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Optional Additional Servers
|
||||
|
||||
These servers can be added for extended functionality:
|
||||
|
||||
| Server | Package | Purpose |
|
||||
|--------|---------|---------|
|
||||
| Fetch | `mcp-server-fetch` (uvx) | Web content fetching |
|
||||
| Brave Search | `@modelcontextprotocol/server-brave-search` | Web search (requires API key) |
|
||||
| PostgreSQL | `@modelcontextprotocol/server-postgres` | Database access |
|
||||
| Sentry | `@sentry/mcp-server` | Error tracking |
|
||||
| GitHub | `@github/mcp-server` | GitHub API operations |
|
||||
|
||||
## Verification
|
||||
|
||||
After configuration, verify servers are loaded:
|
||||
@@ -150,11 +297,13 @@ After configuration, verify servers are loaded:
|
||||
|
||||
- MCP servers run with your user permissions
|
||||
- Review server source before installing
|
||||
- Puppeteer has browser access - use carefully
|
||||
- Playwright has browser access - use carefully
|
||||
- Context7 makes network requests to documentation sources
|
||||
- Filesystem server restricts access to specified directories
|
||||
|
||||
## Resources
|
||||
|
||||
- [MCP Protocol Documentation](https://modelcontextprotocol.io/)
|
||||
- [Available MCP Servers](https://github.com/modelcontextprotocol/servers)
|
||||
- [Microsoft Playwright MCP](https://github.com/microsoft/playwright-mcp)
|
||||
- [Claude Code MCP Guide](https://docs.anthropic.com/claude-code/mcp)
|
||||
|
||||
@@ -80,6 +80,34 @@ Once I understand these, I can provide better recommendations.
|
||||
|
||||
---
|
||||
|
||||
## MCP Integration
|
||||
|
||||
This mode leverages MCP servers for enhanced brainstorming:
|
||||
|
||||
### Sequential Thinking (Primary)
|
||||
```
|
||||
ALWAYS use Sequential Thinking in brainstorm mode:
|
||||
- Explore design options systematically
|
||||
- Track trade-offs for each approach
|
||||
- Build confidence in recommendations incrementally
|
||||
- Allow for revisions and backtracking
|
||||
```
|
||||
|
||||
### Memory
|
||||
```
|
||||
Persist design decisions:
|
||||
- Store design concepts and rationale
|
||||
- Remember user preferences from previous sessions
|
||||
- Build project design knowledge over time
|
||||
```
|
||||
|
||||
### Context7
|
||||
```
|
||||
For informed technology choices:
|
||||
- Fetch docs to compare library options
|
||||
- Ground recommendations in real capabilities
|
||||
```
|
||||
|
||||
## Combines Well With
|
||||
|
||||
- `/brainstorm` command
|
||||
|
||||
@@ -124,6 +124,35 @@ Or use command flag:
|
||||
|
||||
---
|
||||
|
||||
## MCP Integration
|
||||
|
||||
This mode leverages MCP servers for comprehensive research:
|
||||
|
||||
### Sequential Thinking (Primary)
|
||||
```
|
||||
ALWAYS use Sequential Thinking in deep-research mode:
|
||||
- Structure analysis into logical thought sequences
|
||||
- Track confidence scores for each finding
|
||||
- Revise conclusions as evidence emerges
|
||||
- Document reasoning chain for transparency
|
||||
```
|
||||
|
||||
### Context7
|
||||
```
|
||||
For library/technology research:
|
||||
- Fetch current documentation with get-library-docs
|
||||
- Use mode='info' for conceptual understanding
|
||||
- Verify findings against authoritative sources
|
||||
```
|
||||
|
||||
### Memory
|
||||
```
|
||||
Build persistent research knowledge:
|
||||
- Store research findings as entities
|
||||
- Create relations between discovered concepts
|
||||
- Recall previous research in future sessions
|
||||
```
|
||||
|
||||
## Combines Well With
|
||||
|
||||
- `/research` command
|
||||
|
||||
@@ -112,6 +112,35 @@ Continuing with [choice]. Let me know if you'd prefer different.
|
||||
|
||||
---
|
||||
|
||||
## MCP Integration
|
||||
|
||||
This mode leverages MCP servers for efficient implementation:
|
||||
|
||||
### Filesystem (Primary)
|
||||
```
|
||||
ALWAYS use Filesystem in implementation mode:
|
||||
- Use read_file to check existing code
|
||||
- Use write_file to create new files
|
||||
- Use edit_file for modifications
|
||||
- Use search_files to find patterns to follow
|
||||
```
|
||||
|
||||
### Context7
|
||||
```
|
||||
For accurate library usage:
|
||||
- Fetch current API documentation
|
||||
- Use mode='code' for API references
|
||||
- Get correct patterns and examples
|
||||
```
|
||||
|
||||
### Memory
|
||||
```
|
||||
Recall implementation context:
|
||||
- Remember established patterns
|
||||
- Recall user preferences
|
||||
- Store decisions for consistency
|
||||
```
|
||||
|
||||
## Combines Well With
|
||||
|
||||
- `/execute-plan` command
|
||||
|
||||
@@ -137,6 +137,43 @@ Or use command flag:
|
||||
|
||||
---
|
||||
|
||||
## MCP Integration
|
||||
|
||||
This mode leverages MCP servers for thorough review:
|
||||
|
||||
### Playwright
|
||||
```
|
||||
For UI/frontend reviews:
|
||||
- Render and verify visual changes
|
||||
- Test responsive behavior
|
||||
- Check accessibility
|
||||
- Capture screenshots for comparison
|
||||
```
|
||||
|
||||
### Sequential Thinking
|
||||
```
|
||||
For systematic code analysis:
|
||||
- Step through logic methodically
|
||||
- Track multiple concerns
|
||||
- Build comprehensive issue list
|
||||
```
|
||||
|
||||
### Memory
|
||||
```
|
||||
Apply consistent review standards:
|
||||
- Recall past review decisions
|
||||
- Remember approved patterns
|
||||
- Track recurring issues
|
||||
```
|
||||
|
||||
### Filesystem
|
||||
```
|
||||
For thorough code examination:
|
||||
- Use read_file to examine code
|
||||
- Use search_files to find related patterns
|
||||
- Check consistency across codebase
|
||||
```
|
||||
|
||||
## Combines Well With
|
||||
|
||||
- `/review` command
|
||||
|
||||
+2
-36
@@ -23,48 +23,14 @@
|
||||
],
|
||||
"deny": []
|
||||
},
|
||||
"mcpServers": {
|
||||
"_comment": "Uncomment servers to enable. See .claude/mcp/README.md for setup.",
|
||||
"_context7": {
|
||||
"command": "npx",
|
||||
"args": ["-y", "@context7/mcp-server"]
|
||||
},
|
||||
"_sequential": {
|
||||
"command": "npx",
|
||||
"args": ["-y", "@modelcontextprotocol/server-sequential-thinking"]
|
||||
},
|
||||
"_puppeteer": {
|
||||
"command": "npx",
|
||||
"args": ["-y", "@modelcontextprotocol/server-puppeteer"]
|
||||
},
|
||||
"_magic": {
|
||||
"command": "npx",
|
||||
"args": ["-y", "@anthropic/magic-mcp-server"]
|
||||
}
|
||||
},
|
||||
"hooks": {
|
||||
"PostToolUse": [
|
||||
{
|
||||
"matcher": {
|
||||
"tool": "Write",
|
||||
"files": ["*.py"]
|
||||
},
|
||||
"matcher": "Write",
|
||||
"hooks": [
|
||||
{
|
||||
"type": "command",
|
||||
"command": "ruff check --fix $FILE 2>/dev/null || true"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"tool": "Write",
|
||||
"files": ["*.ts", "*.tsx"]
|
||||
},
|
||||
"hooks": [
|
||||
{
|
||||
"type": "command",
|
||||
"command": "npx eslint --fix $FILE 2>/dev/null || true"
|
||||
"command": "if [[ \"$FILE\" == *.py ]]; then ruff check --fix \"$FILE\" 2>/dev/null || true; elif [[ \"$FILE\" == *.ts || \"$FILE\" == *.tsx ]]; then npx eslint --fix \"$FILE\" 2>/dev/null || true; fi"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -156,3 +156,35 @@ After design is validated:
|
||||
4. Use `executing-plans` skill for implementation
|
||||
|
||||
---
|
||||
|
||||
## MCP Integration
|
||||
|
||||
This skill leverages MCP servers for enhanced brainstorming:
|
||||
|
||||
### Sequential Thinking (Primary)
|
||||
```
|
||||
Use Sequential Thinking for structured exploration:
|
||||
- Track design options as thought sequences
|
||||
- Build confidence in recommendations incrementally
|
||||
- Allow for revisions as user provides feedback
|
||||
- Document reasoning chain for design decisions
|
||||
```
|
||||
|
||||
### Memory
|
||||
```
|
||||
Persist design decisions across sessions:
|
||||
- Store design concepts as entities
|
||||
- Create relations between components
|
||||
- Recall user preferences from previous sessions
|
||||
- Build project design knowledge over time
|
||||
```
|
||||
|
||||
### Context7
|
||||
```
|
||||
For informed technology choices:
|
||||
- Fetch current library documentation
|
||||
- Compare capabilities accurately
|
||||
- Ground recommendations in real data
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
@@ -201,6 +201,39 @@ Use skill: sequential-thinking
|
||||
|
||||
---
|
||||
|
||||
## MCP Integration
|
||||
|
||||
This skill is powered by the Sequential Thinking MCP server:
|
||||
|
||||
### Using the MCP Tool
|
||||
```
|
||||
The Sequential Thinking MCP server provides the `sequentialthinking` tool.
|
||||
Use it for:
|
||||
- Breaking complex problems into thought sequences
|
||||
- Tracking confidence and revising conclusions
|
||||
- Building evidence chains with explicit reasoning
|
||||
- Maintaining state across multiple reasoning steps
|
||||
```
|
||||
|
||||
### Tool Parameters
|
||||
```
|
||||
thought: Your current thinking step
|
||||
thoughtNumber: Current step number
|
||||
totalThoughts: Estimated total steps needed
|
||||
nextThoughtNeeded: Whether more steps are needed
|
||||
isRevision: If revising previous thinking
|
||||
needsMoreThoughts: If more analysis needed
|
||||
```
|
||||
|
||||
### Integration Pattern
|
||||
```
|
||||
1. Start with initial thought defining the question
|
||||
2. Gather evidence in subsequent thoughts
|
||||
3. Form hypotheses with probability estimates
|
||||
4. Test and verify in later thoughts
|
||||
5. Conclude with confidence score
|
||||
```
|
||||
|
||||
## Combines Well With
|
||||
|
||||
- Deep research mode
|
||||
|
||||
Reference in New Issue
Block a user