loveNovel

UI/UX design intelligence with searchable database

Generate comprehensive implementation plans through systematic discovery, synthesis, verification, and decomposition into beads. Use when asked to plan a feature, create a roadmap, design an implementation approach, or decompose work into trackable issues. Do NOT use for simple one-step tasks, quick fixes, or when the user just wants to execute an existing plan — use the work skill instead.

Execute a plan or direct task with worker delegation and verification.

Deep investigation mode. Gather context, analyze, synthesize recommendations without making code changes.

Fetch up-to-date library documentation via Context7 MCP. Use when working with external libraries, APIs, or frameworks.

Start interview-driven planning with Prometheus. Asks clarifying questions before generating implementation plan.

Diagnose and fix Maestro installation issues

Git worktree isolation for parallel plan execution. Creates isolated working directories so multiple plans can execute simultaneously without conflicts.

Extract hard-won principles from the current session and save as reusable learned skills.

AI agent workflow with interview-driven planning and team-based execution. Use /design to start planning, /work to execute.

Manage persistent working memory. Add priority context, manual notes, or working memory that persists across sessions.

Sequential agent chains with context passing. Run agents in series where each stage receives output from prior stages.

Scaffold a blank plan with required sections in .maestro/plans/. Use /plan-template <name> to create a new plan file.

Discovers host project conventions from CLAUDE.md, package.json, linter configs, and other configuration files. Use when agents need to understand the target project's coding standards.

Project Session Manager — isolated dev environments with git worktrees and tmux

Automated release workflow with version bump, tag, publish, and GitHub release

Multi-stage research with parallel agents, verification, and synthesis. Supports AUTO mode for hands-free deep investigation.

Clean stale Maestro state — remove old drafts, orphaned teams, and stale task directories.

Code review with auto-fix — plan-vs-implementation comparison or structured git-diff review. Automatically fixes issues found during review.

Deep security analysis delegated to the security-reviewer agent. Checks auth, injection, secrets, dependencies, and reports with severity ratings.

Verify Maestro plugin prerequisites — Agent Teams flag, jq, trace MCP, PSM tools, directories, and hooks.

Scaffold persistent project context — product definition, tech stack, and guidelines. Interviews you about your project and generates context files that all Maestro agents reference.

Show current Maestro state — plans, drafts, active tasks, and wisdom files.

Detect project languages and inject code style guides into CLAUDE.md. Provides consistent coding conventions for all Claude Code interactions.

Show agent execution timeline and performance summary

Iterative fix-and-verify loop for tests, build, lint, or typecheck. Diagnoses failures, applies fixes, re-verifies — up to 5 cycles.

Execute a plan using Agent Teams, or work directly from a description. Spawns specialized teammates to implement tasks in parallel.