MCP App StoreMCP App Store
from My CC Harness123
Practical performance and bundle-size guidelines for React and Next.js apps — prioritized rules and patterns to avoid common performance pitfalls.
Provides a concise, prioritized rulebook for React and Next.js performance: eliminating waterfalls, reducing bundle size, server-side and client-side performance patterns, and rendering/re-render strategies. The skill summarizes rules and points to individual rule files with examples.
Apply during code reviews, refactors, or when authoring React/Next.js components and pages where performance, bundle size, or server rendering behaviour matters. Triggers when optimizing data fetching, bundling, hydration, or re-render hotspots.
rules/ files in the repo with detailed examples (has_references=false per fetch metadata but sibling rules exists)async-parallel, bundle-dynamic-imports, rerender-memo) with guidance for application.Useful with developer-focused assistants and code-writing agents (Copilot-style, Claude/GPT code assistants) that can read rule files and apply transformations or generate code suggestions.
A reference-only skill providing React/Next.js performance optimization guidelines organized into 8 priority categories with 45 rules. No scripts included — purely a knowledge document. The SKILL.md references external rule files (rules/ directory) and AGENTS.md that aren't bundled, so an agent using this skill would lack the detailed rule content and code examples.
Pure reference/knowledge skill with no executable scripts. Well-organized priority table but incomplete without the referenced rule files. Low security risk — no code execution, no network calls, no credentials. Moderate usefulness but limited by missing rule details and niche audience.
Harness Health Audit
Assess and score the overall health of a Claude Code harness across architecture, skills coverage, hooks, rules, MCP servers, eval pipelines, and team setup.
Code Evaluation Harness
Spawns an independent evaluator agent to score code outputs on functionality, code quality, originality, and usability/security, producing a structured EVAL_REP
SPEC-driven Development Interview
Conducts a structured, in-depth interview to produce a detailed SPEC.md requirements document for a feature or project.
Plan
Create structured implementation plans for multi-step or architectural changes before coding — defines success criteria, trade-offs, and stepwise tasks.
Codex + Claude Code Review
Performs a dual-pass code review of the current branch using Codex (GPT) and Claude, producing structured findings and severity classifications.
Stitch Design System Generator
Analyzes Stitch projects to create a semantic DESIGN.md file, ensuring consistent UI generation and visual identity.
Run Execute
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
Clerk Vue Patterns
Vue 3 integration patterns for Clerk: composables, router guards, and Pinia auth store integration.
OpenTestAI
Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.
Codex Collab
Bridge Claude and Codex to run tasks, perform code reviews, and run background jobs for research or implementation workflows.
Go Data Structures
Authoritative guidance on choosing and using Go built-in and standard-library data structures, with practical best practices for slices, maps, arrays, container
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
Agent Browser — Core
Core usage guide for agent-browser: snapshot-and-ref browser automation to navigate pages, interact with elements, extract data, take screenshots, manage sessio
React Development Expert
Provides authoritative React guidance on hooks, state patterns, Server Components, performance optimization, and common architectural patterns.