From mir
Use when a Make It Real project needs optional feature flags changed, especially enabling or disabling live wiki sync.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mir:configThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read or update project-local Make It Real options. The normal user-facing action is `/mir:config`; keep internal config file paths and engine subcommands out of ordinary workflow narration unless the user asks.
Read or update project-local Make It Real options. The normal user-facing action is /mir:config; keep internal config file paths and engine subcommands out of ordinary workflow narration unless the user asks.
makeitreal-engine config get "$CLAUDE_PROJECT_DIR" to inspect current settings.makeitreal-engine config set "$CLAUDE_PROJECT_DIR" --live-wiki enabled
makeitreal-engine config set "$CLAUDE_PROJECT_DIR" --live-wiki disabled
makeitreal-engine config set "$CLAUDE_PROJECT_DIR" --dashboard-auto-open enabled
makeitreal-engine config set "$CLAUDE_PROJECT_DIR" --dashboard-refresh-on-status enabled
makeitreal-engine config set "$CLAUDE_PROJECT_DIR" --dashboard-refresh-on-launch enabled
makeitreal-engine config set "$CLAUDE_PROJECT_DIR" --dashboard-refresh-on-verify enabled
features.liveWiki.enabled, features.dashboard.* values, and the config path.preview/index.html remains mandatory because Ready gating depends on it.dashboardRefresh.skipped result; it must not weaken gates or evidence.wiki sync as the normal toggle mechanism.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.