oracle
Ask the oracle (GPT-5.2 with deep reasoning) strategic technical questions. Use for architecture decisions, complex debugging, security analysis, or when you need a second expert opinion. Supports background ex...
Discover research debugging skills, compare source repositories and read the instructions for each workflow.
Ask the oracle (GPT-5.2 with deep reasoning) strategic technical questions. Use for architecture decisions, complex debugging, security analysis, or when you need a second expert opinion. Supports background ex...
Meta-skill plugin that generates /atlas skills for any repository, providing AI-optimized codebase navigation plus spec-driven development workflows. Use when the user needs to understand a codebase structure,...
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Get an external senior game developer's critique of the project. Reviews usefulness, identifies issues, and suggests features.
Extracts architectural, business, and operational context from existing systems. Use to build mental models of unfamiliar codebases.
Enforces simplicity, efficiency, and long-term maintainability in Next.js + TypeScript code. Prevents deep nesting/long conditionals/duplication/magic values, catches common performance anti-patterns early, and...
Designs audit trails and security telemetry for fast detection and response, aligned with OWASP Logging Cheat Sheet.
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Uses Bash commands with ref-based element selection.
Reviews UI code or designs for UX issues, suggests improvements based on Laws of UX. Use when reviewing components, designing new interfaces, or improving user experience for web applications.
Documentation synchronization knowledge. Use when analyzing documentation patterns, understanding how code changes map to documentation needs, or determining documentation structure for different project types.
Monitoring and observability expert. Logging, metrics, error tracking, health checks. Use for production monitoring setup.
Break down high-level plans into specific tasks with file paths, line numbers, and verification steps. Creates execution-ready implementation plans.
Document benchmarks and capacity planning.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Full-stack debugging specialist for Faiston NEXO. Use when encountering errors, bugs, test failures, or unexpected behavior in Frontend (React, TypeScript, Vite), Backend (FastAPI, Lambda), Agents (Google ADK,...
Scans for security vulnerabilities in Next.js + TS code/plans. Invoked by prompt-classifier in IMPLEMENT/EDIT sequences via "security-overseer ". Enforces auth, input validation, secret handling, OWASP complian...
Audit de performance du code et de l'application. Analyse Lighthouse, bundle size, Core Web Vitals, et optimisations. Utiliser après l'implémentation, avant une release, ou quand l'utilisateur dit "performance"...
使用 Context7 MCP 工具查詢最新函式庫文件。確保回答基於即時、正確的官方文件,而非過時的訓練資料。適用於任何需要查詢 npm、PyPI、crates.io 等套件文件的場景。
Documents codebase structure and implementation without evaluation or recommendations.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Trigge...
Performance optimization playbook (measure → diagnose → fix → verify) for this repo (React + R3F + Three.js + Vite). Use when asked to improve FPS, reduce jank, lower draw calls, optimize loading/bundle size, o...
Capturing and tracking TODOs and technical debt
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
This skill should be used when the user asks to "review code", "code review", "check my changes", "review this PR", "review my implementation", "PR review", "look at my code", or when reviewing GUI automation c...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.