MCP App StoreMCP App Store
from awesome-codex-plugins546
Compare AI agents (Claude Code, Codex, OpenCode) on real coding tasks using git worktrees and standardized checks.
Provides a rigorous framework for benchmarking multiple AI agents on a specific coding task within a repository. It automates the creation of isolated environments (git worktrees), executes baseline and post-run checks, and captures detailed performance metrics including wall-time, exit codes, and costs.
Use this skill when you need to evaluate which AI agent is superior for a specific refactoring, performance optimization, or bug fix. It's ideal for objective comparisons between different LLM-powered coding assistants.
run_trial.py for executing agent runs, monitor.py for real-time progress tracking, and parse_transcript.py for aggregating results into a comparison report.Specifically designed for agents capable of executing bash commands and reading/writing files, including Claude Code, Codex, and OpenCode.
This skill has not been reviewed by our automated audit pipeline yet.
Power Automate Monitoring (FlowStudio MCP)
Monitor Power Automate tenant health and failure trends from a fast FlowStudio MCP cached store — identify failing flows, review error trends, and inventory Pow
Autopilot — Autonomous Session Orchestration
Runs an opt-in session-orchestration loop that auto-starts routine sessions when confidence is high, enforcing post-session kill-switches and resource caps.
GoFrame v2 Development
Opinionated GoFrame v2 development conventions and best-practice patterns for building services, database operations, and code structure.
Backlink Profile Analysis
Analyze a site's backlink profile: referring domains, anchor text distribution, toxic link detection, competitor link gaps, and recommendations using Common Cra
AI Learning Boundary Mapper
Maps which parts of an assignment benefit from AI assistance versus which parts AI use would undermine, and produces component-level policy recommendations for
Project Structure Auditor
Audit and recommend file and directory organisation for codebases: colocation, anti-patterns, and feature vs layer grouping guidance.
Nullcost Recommend
Recommend low-cost or free-tier developer providers and hosting options tailored to a use-case (Node, Next.js, databases, email APIs, GPU, etc.).
Nuxt 4 Patterns
Guidance and patterns for Nuxt 4 apps: hydration safety, SSR-friendly data fetching, route rules, lazy loading, and performance best practices.
Obsidian CLI — Sync & Publish
Control Obsidian desktop Sync and (when available) Publish workflows via the official obsidian CLI with conservative probes and safety checks.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
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.
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
Feishu Voice Sender
Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.