MCP App StoreMCP App Store
from crouton-kit24
Analyze technical designs for requirements coverage, flow correctness, and architectural feasibility to surface implementation risks.
Review Design provides a structured multi-phase review workflow that checks a technical design against stated requirements, simulates runtime flows to find seam issues, and assesses architectural feasibility. The skill runs automated task subagents for requirement coverage and feasibility checks, then performs an in-agent flow simulation to find gaps between components and handoffs. Its output is a concise list of PASS/FAIL findings and grouped implementation risks.
Use this after drafting or updating a design document (design.md). Invoke it when you need to verify that the design actually satisfies acceptance criteria, to find integration or handoff mismatches before implementation, or to check whether the proposed architecture is buildable with existing project patterns. It is intended for design reviews, engineering spec validation, and pre-implementation audits.
Best suited for agents that support Task, Read and code-aware tools (Claude Code / sonnet-style Task subagents). It assumes the host environment can spawn Task subagents and read repository files.
Review Design is an agent skill for validating technical designs against requirements through a four-phase process: requirements coverage check, flow simulation, feasibility review, and aggregation. It has no bundled scripts — it's purely instructional, delegating to Task subagents for coverage and feasibility checks while the main agent handles flow simulation directly. Well-structured with clear output contracts and anti-patterns to avoid.
Clean skill with no security concerns. Well-written instructions with specific checks for flow simulation (preconditions, state consistency, failure handling, handoffs). Includes guardrails against false positives in feasibility review. No scripts to test.
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
Codex Collab
Bridge Claude and Codex to run tasks, perform code reviews, and run background jobs for research or implementation workflows.
BK-CI Design Patterns Guide
Practical guide to design patterns used in the BK-CI project (Kotlin/Spring). Covers factory, strategy, singleton, decorator, observer, template method, chain-o
Node.js Best Practices
Guidelines and decision-making for Node.js architecture, runtime, async patterns, security, validation, and testing to inform framework and system choices.
AI Pair Collaboration
Orchestrates a small heterogeneous team of AI agents (author/developer + Codex reviewer + Gemini reviewer) to produce and review content or code in a coordinate
React Development Expert
Provides authoritative React guidance on hooks, state patterns, Server Components, performance optimization, and common architectural patterns.
Crucible: Build
Orchestrates an end-to-end development pipeline: interactive design, planning, autonomous execution, and quality gates with TDD and iterative reviews.