mcp-project-config
Configures MCP servers for projects. Use when setting up Linear, GitHub, Chrome DevTools, Render, or other MCP servers for a project. Handles token selection and configuration.
What this skill does
# MCP Project Configuration
Guide for configuring MCP (Model Context Protocol) servers in projects.
## Standard MCP Servers
Every project should include these MCP servers:
| Server | Type | Purpose |
|--------|------|---------|
| Linear | HTTP | Project/issue tracking |
| GitHub | HTTP | Code management |
| Chrome DevTools | stdio | Browser debugging |
| Render | HTTP | Deployment management |
## Configuration Files
### .mcp.json (Project Root)
MCP server definitions with environment variable substitution:
```json
{
"mcpServers": {
"linear": {
"type": "http",
"url": "https://mcp.linear.app/mcp",
"headers": {
"Authorization": "Bearer ${LINEAR_TOKEN_VAR}"
}
},
"github": {
"type": "http",
"url": "https://api.githubcopilot.com/mcp",
"headers": {
"Authorization": "Bearer ${GITHUB_PERSONAL_ACCESS_TOKEN}"
}
},
"chrome-devtools": {
"command": "npx",
"args": ["-y", "chrome-devtools-mcp@latest"]
},
"render": {
"type": "http",
"url": "https://mcp.render.com/mcp",
"headers": {
"Authorization": "Bearer ${RENDER_TOKEN}"
}
}
}
}
```
### .claude/settings.json
Enable MCP servers for Claude Code:
```json
{
"enableAllProjectMcpServers": true,
"enabledMcpjsonServers": ["linear", "github", "chrome-devtools", "render"]
}
```
## Linear Account Selection
When setting up Linear, ask which account to use:
### Known Accounts
| Account | Token Variable |
|---------|---------------|
| Laser Focused | `LASER_FOCUSED_LINEAR_TOKEN` |
| What If | `WHAT_IF_LINEAR_TOKEN` |
### New Workspace
If neither account applies:
1. Ask user for the token environment variable name
2. User creates the token at https://linear.app/settings/api
3. User adds to their shell profile (~/.zshrc or ~/.bashrc)
### Configuration
Replace `LINEAR_TOKEN_VAR` in .mcp.json with the chosen variable:
```json
"linear": {
"type": "http",
"url": "https://mcp.linear.app/mcp",
"headers": {
"Authorization": "Bearer ${LASER_FOCUSED_LINEAR_TOKEN}"
}
}
```
## Token Environment Setup
Tokens should be stored in the user's shell profile, NOT in project files.
### Where to Store Tokens
Add to `~/.zshrc` or `~/.bashrc`:
```bash
# Linear API Tokens
export LASER_FOCUSED_LINEAR_TOKEN="lin_api_..."
export WHAT_IF_LINEAR_TOKEN="lin_api_..."
# GitHub Personal Access Token
export GITHUB_PERSONAL_ACCESS_TOKEN="ghp_..."
# Render API Token
export RENDER_TOKEN="rnd_..."
```
### Reload After Adding
```bash
source ~/.zshrc # or ~/.bashrc
```
## MCP Server Types
### HTTP Servers
Use for hosted APIs with authentication:
```json
{
"type": "http",
"url": "https://api.service.com/mcp",
"headers": {
"Authorization": "Bearer ${TOKEN_VAR}"
}
}
```
### stdio Servers (npx)
Use for local tools that run as processes:
```json
{
"command": "npx",
"args": ["-y", "package-name@latest"]
}
```
### stdio Servers (Local Binary)
Use for installed binaries:
```json
{
"command": "/path/to/binary",
"args": ["--flag", "value"]
}
```
## Setup Workflow
### Step 1: Create .mcp.json
```bash
# In project root
touch .mcp.json
```
### Step 2: Ask About Linear Account
"Which Linear workspace is this project for?"
- Laser Focused (LASER_FOCUSED_LINEAR_TOKEN)
- What If (WHAT_IF_LINEAR_TOKEN)
- New workspace (provide token name)
### Step 3: Configure All Servers
See [mcp-templates.md](mcp-templates.md) for full templates.
### Step 4: Create .claude/settings.json
```bash
mkdir -p .claude
```
Add settings to enable MCP servers.
### Step 5: Verify
Start a new Claude Code session and verify MCP tools are available.
## Adding Custom MCP Servers
To add a new MCP server:
1. Determine the server type (HTTP or stdio)
2. Get the URL or command
3. Identify required authentication
4. Add to .mcp.json
5. Add server name to enabledMcpjsonServers in settings.json
## Troubleshooting
### MCP Server Not Available
1. Check token is exported: `echo $TOKEN_NAME`
2. Verify .mcp.json syntax (valid JSON)
3. Check server is listed in settings.json
4. Restart Claude Code session
### Authentication Failed
1. Verify token is valid (not expired)
2. Check token has required permissions
3. Ensure environment variable is set
### HTTP Server Connection Failed
1. Check URL is correct
2. Verify network connectivity
3. Check if service is operational
For templates, see [mcp-templates.md](mcp-templates.md).
Related in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.