ai-image-creator
Generate PNG images using AI (multiple models via OpenRouter including Gemini, FLUX.2, Riverflow, SeedDream, GPT-5 Image, proxied…
Configure MCP servers for the workspace — web search, filesystem, GitHub, Stripe, etc. Use when adding a new integration that needs MCP-level access.
Claude Code
$ npx -y skills add evolution-foundation/evo-nexus --skill dev-mcp-setup --agent claude-code
Codex
$ npx skills add evolution-foundation/evo-nexus --skill dev-mcp-setup -a codex -y
Cursor
$ npx skills add evolution-foundation/evo-nexus --skill dev-mcp-setup -a cursor -y
Gemini CLI
$ npx skills add evolution-foundation/evo-nexus --skill dev-mcp-setup -a gemini-cli -y
GitHub Copilot
$ npx skills add evolution-foundation/evo-nexus --skill dev-mcp-setup -a github-copilot -y
OpenCode
$ npx skills add evolution-foundation/evo-nexus --skill dev-mcp-setup -a opencode -y
Windsurf
$ npx skills add evolution-foundation/evo-nexus --skill dev-mcp-setup -a windsurf -y
name: dev-mcp-setup description: Configure MCP servers for the workspace — web search, filesystem, GitHub, Stripe, etc. Use when adding a new integration that needs MCP-level access.
Derived from oh-my-claudecode (MIT, Yeachan Heo). Adapted for the EvoNexus Engineering Layer.
Configure MCP (Model Context Protocol) servers for the workspace. When a new integration needs access at the MCP layer (rather than via skill-level API calls), this skill walks through the configuration.
These are typically configured in `~/.claude/settings.json` or `.claude/settings.json`:
| MCP | Purpose | Setup | |---|---|---| | google-calendar | Calendar events | OAuth | | gmail | Email read/send | OAuth | | linear-server | Linear issues/projects | API key | | github | GitHub PRs/issues/files | GitHub token | | canva | Design files | OAuth | | claude_ai_Notion | Notion pages | OAuth | | computer-use | Desktop control | local | | figma | Design files | OAuth | | plugin_telegram | Telegram bot | bot token |
1. **Identify** which MCP server you need to add 2. **Check current config** — read `.claude/settings.json` (project) or `~/.claude/settings.json` (user) 3. **Add the server entry** with its required env vars or auth 4. **Restart Claude Code** to load the new MCP 5. **Verify** by listing tools — the new MCP's tools should appear with `mcp__<server>__*` prefix 6. **Document** the addition in `workspace/development/research/[C]mcp-setup-{server}-{date}.md`
{
"mcpServers": {
"github": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-github"],
"env": {
"GITHUB_TOKEN": "${GITHUB_TOKEN}"
}
}
}
}If an MCP isn't working: 1. Check Claude Code logs for spawn errors 2. Verify env vars are set 3. Test the MCP server independently if possible 4. Check that the MCP package is installed
Generate PNG images using AI (multiple models via OpenRouter including Gemini, FLUX.2, Riverflow, SeedDream, GPT-5 Image, proxied…
Create a new custom agent for the workspace. Guides the user through defining agent name, domain, personality, skills, model, and…
Create a new slash command for Claude Code. Guides the user through defining the command name, what it does, and generates the…
Create a Mission, Project, or Goal (Mission → Project → Goal → Task hierarchy) in EvoNexus. Guides the user through picking a…
Create a new heartbeat (proactive agent scheduled with a decision prompt) for EvoNexus. Guides the user through picking an agent,…
Create a new custom integration (API/service wrapper) for the workspace. Guides the user through defining the integration's slug,…
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…