Skip to content
UsecaseBoard
Saved0
← All use cases
docsMeta-Muse

Muse Code /migrate: import Claude Code and Codex skills into Muse

At a glance

Muse Code can load skills from built-in, user, project, and plugin sources, and discovers `~/.claude/skills` and Codex skill roots by default. The bundled `/migrate` skill imports Claude Code or Codex memory notes and MCP servers; `muse skills import --from claude|codex` brings skills across. Built-ins include `/plan`, `/grill` (stress-test a plan into a written scope contract), `/taste`, and `/threejs`. This workflow is listed under Meta-Muse, Muse-Code, skills, migration, MCP.

Agents / tools
Muse Code, Meta Muse, Claude Code, Codex

Building a tool for these workflows? Sponsor / inquire.

Save ideas in this browser. Upvotes count across the board.

Prompt excerpt

In Muse Code: /migrate from Claude Code, then muse skills import --from claude, and list skills with muse skills list.

Related workflows

Explore all →
blogMeta-Muse

Muse Code’s five migration skills beat a single importer

Beyond /migrate, Muse Code bundles resume-claude, resume-codex, migrate, import, and muse skills import so unfinished Claude/Codex sessions, memory notes, MCP servers, rules, and skills each have a dedicated entry point—the migrate skill routes you to the right one. Coverage is the story vs Claude’s single claude import.

Muse CodeMeta MuseClaude Code+1
Source ↗
blogGrok-Bot

Ledger Agent Intent: Grok Bot and Muse propose, you approve on hardware

Ledger’s Agent Intent queue lets background agents (Grok Bot, Muse, Hermes, OpenClaw, Dots) prepare actions—e.g. Grok Bot watches an inbox and drafts an invoice payment—while you review asynchronously and physically confirm on a Ledger signer Secure Screen. Agents never hold signing keys; coding agents can use Agent Stack CLI/skills too.

Ledger Agent IntentGrok BotMeta Muse+3
Source ↗
blogMeta-Muse

Muse Code: fan out parallel subagents into isolated git worktrees

Meta’s Muse Code co-trained agent (with Muse Spark) fans work out automatically: parent spawns write-capable children, each in its own git worktree so parallel edits never collide; background observer agents stay live for memory/skill/goal/verification. Fully auditable event log; workers + reviewers by default. Install: curl -fsSL https://dev.meta.ai/install.sh | bash.

Muse CodeMeta MuseMuse Spark+1
Source ↗
docsMeta-Muse

muse exec: headless Muse Code runs for scripts and CI

Muse Code is Meta’s terminal/CI coding agent: run `muse` interactively or `muse exec "…"` headless for scripts and pipelines—plans, edits, and validates with approvals and an OS sandbox from the first run. Pair with Muse Spark/Wonder via Meta Model API when you build your own harness; use Muse Code when you want the ready-made agent loop.

Muse CodeMeta Musemuse exec+1
Source ↗