pal-mcp-expert
Expert guidance for using the Pal MCP Server (zen-pal-nas). This skill should be used when working with multi-model AI orchestration, tool workflows (chat, thinkdeep, planner, consensus, debug, codereview, precommit, clink), configuration troubleshooting, or optimizing model selection strategies. Activates automatically when user mentions Pal MCP, zen-pal-nas, or specific tool names.
npx skills add majiayu000/claude-skill-registry --skill pal-mcp-expert --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Pal MCP Server Expert Guide Master guide for the Pal MCP Server - a Provider Abstraction Layer that orchestrates multiple AI models (Gemini, OpenAI, Grok, Azure, Ollama, custom) through a unified MCP interface. Formerly known as "Zen MCP". ## Core Concept **PAL = Provider Abstraction Layer** Think of it as "Claude Code for Claude Code" - super-glue that connects your AI CLI (Claude Code, Codex CLI, Gemini CLI, Cursor) to multiple AI models for enhanced collaboration. Claude stays in full control, but gains perspectives from the best AI model for each subtask. **Key Principle:** You craft the prompts. PAL enables Claude to engage other models only when needed, maintaining context across all interactions. ## When to Use This Skill Activate this skill when: - Orchestrating multiple AI models in workflows - Using specific PAL tools (chat, thinkdeep, planner, consensus, codereview, precommit, debug, clink) - Troubleshooting zen-pal-nas configuration issues - Optimizing model selection for complex tasks - Implementing context revival after Claude resets - Setting up CLI subagents for isolated workloads - Configuring environment variables or API keys - Managing tool timeouts or performa
- Core Concept
- When to Use This Skill
- Revolutionary Features
- 1. Context Revival After Claude Resets
- 2. CLI Subagents (clink tool)
- 3. MCP 25K Token Limit Bypass
- 4. Vision Support
- Tool Ecosystem
- Core Tools (Always Enabled)
- Advanced Workflow Tools
- Specialized Tools (Disabled by Default)
- Utility Tools
- Critical Parameters
- continuationid (MOST IMPORTANT)
Model Provider (at least one required) Model Selection Tool Management Conversation Settings Model Restrictions (optional) Multi-Client Conflicts Logging
What does the pal-mcp-expert skill do?
Expert guidance for using the Pal MCP Server (zen-pal-nas). This skill should be used when working with multi-model AI orchestration, tool workflows (chat, thinkdeep, planner, consensus, debug, codereview, precommit, clink), configuration troubleshooting, or optimizing model selection strategies. Activates automatically when user mentions Pal MCP, zen-pal-nas, or specific tool names.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill pal-mcp-expert --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.