From mir
Use when a Make It Real installation, slash command, hook, dashboard, current-run, or Claude Code runner environment needs read-only diagnostics.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mir:doctorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Diagnose the local harness without changing implementation state.
Diagnose the local harness without changing implementation state.
The browser dashboard is read-only observability. Doctor may report dashboard paths and missing preview files, but it must not add browser actions or mutate board, Blueprint, approval, evidence, or config state.
makeitreal-engine doctor "$CLAUDE_PROJECT_DIR" through the plugin binary.checks.config, checks.plugin, checks.currentRun, checks.hooks, checks.dashboard, and checks.claudeBinary.healthy:false as a diagnostic result, not a command failure.supportMatrix to separate environment problems from harness state problems.nextAction exactly when it is a public command or an install/PATH repair instruction.Keep the report short: healthy state, failing checks, evidence paths, support matrix highlights, and the next safe action.
npx claudepluginhub mir-makeitreal/makeitreal --plugin mirGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.
2plugins reuse this skill
First indexed May 8, 2026