MCP App StoreMCP App Store
from slot-machine
Run N independent implementations of the same clear spec in parallel, review each, and pick or synthesize the best result to maximize quality when design choice
Slot Machine is an orchestration skill that runs multiple independent attempts (slots) at the exact same specification, collects implementation artifacts, dispatches reviewers, and runs a judge to PICK a winner or SYNTHESIZE a combined result. It formalizes a best-of-N workflow to trade compute for higher-quality outcomes where architectural choices matter.
Use this skill when a task is well-specified, non-trivial, and has meaningful design decisions — for feature implementations, complex refactors, or creative writing tasks where multiple stylistic variants are valuable. Do NOT use for trivial mechanical edits.
Best suited for agent environments that support creating isolated worktrees or file-based isolation and can call external harnesses (Codex, Claude) or shell out to runtime helpers. The skill is orchestration-focused rather than providing external APIs.
Slot-machine is a best-of-N parallel implementation orchestration skill that runs multiple independent attempts at the same spec, reviews each with dedicated reviewer agents, then judges/synthesizes the best result. Exceptionally comprehensive SKILL.md (~75KB) covering profile loading, multi-harness dispatch (Claude/Codex), git worktree isolation, streaming review, event tracing, and manual handoff paths. No bundled scripts to test. Well-structured with clear phases, error states, and output contracts.
Impressive orchestration skill. Extremely thorough documentation with proper error handling, state management (events.jsonl/state.json), and trace artifacts. The 75KB SKILL.md size is notable — likely fine for AI agent consumption but could be split into leaner SKILL.md + references. No security concerns beyond minor shell injection surface from spec text interpolation.
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Maestro Orchestrate
Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.
Run Execute
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
Overnight — Autonomous Long-Running Coding
Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges
tmux Remote Control
Control tmux sessions for interactive TTYs: send keystrokes, capture panes, orchestrate parallel coding agents, and monitor output safely.
Audit Agents/Skills/Commands
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.
Skill Retro
Analyze a session's skill invocations to surface performance issues and recommend or apply improvements using the skill-creator workflow.
Build Unplanned Feature
Orchestrates ad-hoc feature development: requirement gathering, planning, implementation and validation across task-planning, implementation, and validation loo