Stats
Actions
Tags
From miller
Use when querying another registered workspace with Miller, comparing repos, opening a workspace, or routing search/inspect/context/impact/trace through workspace_id.
How this skill is triggered — by the user, by Claude, or both
Slash command
/miller:miller-cross-workspace<workspacepath,displayid,orcross-repotask>This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Miller can read registered workspaces without changing directories. Use `workspace_id` on read tools instead of shelling into another repo.
Miller can read registered workspaces without changing directories. Use workspace_id on read tools instead of shelling into another repo.
List known workspaces:
workspace(operation="list")
Valid workspace_id selectors:
currentprimaryPrime a repo that is not registered yet:
workspace(operation="open", path="<absolute-root>")
workspace open primes the index; it does not switch the live MCP server workspace.
Pass the selector to the read tool:
search(workspace_id="<selector>", query="<query>")
inspect(workspace_id="<selector>", target="<symbol-or-file>")
context(workspace_id="<selector>", query="<task>")
impact(workspace_id="<selector>", target="<symbol-or-file>")
trace(workspace_id="<selector>", target="<symbol>")
Explicit workspace_id defaults to refresh-first. Set ensure_fresh=false only when a fast, possibly stale read is acceptable.
Mention:
Do not manually cd and repeat shell searches when a Miller read tool can route to the workspace.
npx claudepluginhub anortham/miller --plugin millerProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.