MCP App StoreMCP App Store
from yonatangross
Deep pull-request code review using parallel specialized agents (quality, security, tests, architecture, performance) and synthesized review reports for approve
Performs comprehensive PR reviews by launching 6–7 specialized agents in parallel (code quality, security, test generation, frontend/backend performance, architecture). It gathers PR metadata, diffs, CI status and changed files, runs domain-aware agents, and synthesizes findings into a structured review with conventional comments (praise/issue/suggestion/nitpick) and an approve/request-changes verdict.
Use this for reviewing pull requests before merge, security audits, performance-sensitive changes, or when you need an automated, multi-perspective review that produces actionable comments and a final recommendation. Also useful for engineering teams wanting consistent, auditable review reports.
references/ and rules/ for prompts, templates, and validation commands.Designed for Claude Code-style orchestration and agent toolsets (parallel agent launches, AskUserQuestion, Bash, gh CLI). Compatible with agents that support task creation, tool calls, and structured JSON outputs.
Review PR skill for Claude Code using parallel specialized agents (quality, security, tests, architecture, performance). Extremely detailed SKILL.md with clear phase structure, progressive disclosure via references/ and rules/ directories, anti-sycophancy protocol, and domain-aware agent selection. No bundled scripts to test — purely instruction-based skill. Clean security profile: only uses gh CLI for PR interaction, no exfiltration risks, no destructive commands.
Very well-crafted skill. Progressive disclosure is exemplary — SKILL.md stays readable while references/ hold deep detail. The /ultrareview gate with user confirmation is a thoughtful touch. Anti-sycophancy rules and conventional comments system are production-quality. Only dock: not portable beyond Claude Code ecosystem, and the multi-agent orchestration relies on CC-specific features (Task tool, SendMessage).
Cross-Project Analytics
Query local, privacy-safe cross-project analytics to report on agent, skill, hook, and team performance; replay sessions and estimate token costs.
Task Dependency Patterns
Patterns and workflows for creating, sequencing, and managing task dependencies using TaskCreate/TaskUpdate/TaskGet/TaskList tools to coordinate multi-step impl
Write PRD (Product Requirements Document)
Generate an 8-section Product Requirements Document with user stories, INVEST-formatted acceptance criteria, and go/no-go criteria to turn product vision into e
Telemetry Inspect
Run a read-only health check of OrchestKit's telemetry pipeline: writer activity, file sizes, schema lock coverage, orphan files, and growth trends.
Design Ship
Turn a Claude Design handoff URL or bundle into a reviewable GitHub PR with generated Storybook stories, Playwright tests, and before/after verification.
Dream — Memory Consolidation
Automated nightly memory consolidation: prunes stale memory files, merges duplicates, resolves contradictions, and rebuilds MEMORY.md indexes with deterministic
Scope-Appropriate Architecture
Prevents over-engineering by right-sizing architectural patterns to the project's actual scope using a 6-tier classification system.
Responsive Patterns
Practical patterns for responsive UI: container queries, fluid typography, intrinsic layouts, and foldable-device support for React components.
Verify
Run comprehensive verification: parallel agents for tests, security, coverage, grading and improvement suggestions; produces evidence-backed verification report
Animation & Motion Design
Implement high-performance, accessible UI animations using the Motion library and the native View Transitions API.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
ds-fix — data-science mid-analysis fixer
Orchestrates diagnosis and targeted fixes mid-analysis: diagnose root cause, apply fixes with output-first verification, and update project learnings.
Readwise Reader Document Management
Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Junshi — Research Advisor
Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.
TradeOS
Natural-language driven CEX trading and portfolio management for agents: API key vaulting, multi-exchange orders, DCA, arbitrage scanning, alerts and security r
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
ezBookkeeping API Tools
Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi