Claude Code Profiles and Local Skill Activation

Overview

This skill creates an isolated-but-shared profile system for Claude Code CLI. Each profile gets its own .claude.json state file (provider credentials and session history) while sharing skills, projects, hook scripts, agents, and installed plugin state across all profiles — and converging each profile's settings.json (hook registration, marketplaces, env feature flags, permissions, preferences) plus the behavior slice of its .claude.json (e.g. workflowSizeGuideline) from the default profile, so the only intended difference between profiles is the model/provider.

The result: you can open one terminal with Kimi, another with DeepSeek, another with Anthropic — each running as a fully independent Claude Code process, without configuration bleed.

For reducing fixed startup context from preloaded MCP tool schemas, read references/mcp-startup-context.md. It owns same-mode measurement, active-profile discovery, provider compatibility checks, reversible server suppression, and fresh-process acceptance.

How It Works