Skill rating

Project scaffolding CLI with 30+ integrations, custom templates, and MCP server for AI agents.

Code review guidelines covering code quality, security, and best practices.

Complete file handling including upload flows, serving files via URL, storing generated files from actions, deletion, and accessing file metadata from system tables

External API integration and webhook handling including HTTP endpoint routing, request/response handling, authentication, CORS configuration, and webhook signature validation

Use this skill when conducting or improving code reviews. Provides structured review processes, conventional comments patterns, language-specific checklists, and feedback templates. Use when reviewing

Test-driven development for Quarkus 3.x LTS using JUnit 5, Mockito, REST Assured, Camel testing, and JaCoCo. Use when adding features, fixing bugs, or refactoring event-driven services.

Create or update .groove/index.md config interactively. Run before groove install.

PyTorch implementation of TurboQuant for LLM KV cache compression using two-stage vector quantization (random rotation + Lloyd-Max + QJL residual correction).

Advanced TypeScript patterns and best practices for 2025

深度调研的多Agent编排工作流：把一个调研目标拆成可并行子目标，用 Claude Code 非交互模式（`claude -p`）运行子进程；联网与采集优先使用已安装的 skills，其次使用 MCP 工具；用脚本聚合子结果并分章精修，最终交付"成品报告文件路径 + 关键结论/建议摘要"。用于：系统性网页/资料调研、竞品/行业分析、批量链接/数据集分片检索、长文写作与证据整合，或用户提及"深度调研

Deploy and debug Eve-compatible apps via the CLI, with a focus on staging environments.

Comprehensive UX audit using IxDF's 7 factors, 5 usability characteristics, and 5 interaction dimensions. Holistic evaluation with redesign proposals based on user-centered design principles.

QVeris is a capability discovery and tool calling engine. Use discover to find specialized API tools — real-time data, historical sequences, structured reports, web extraction, PDF workflows, media ge

Generate a personal "Now Reading" webpage from your Reader library

Agent skill for spec-mobile-react-native - invoke with $agent-spec-mobile-react-native

Agent skill for v3-integration-architect - invoke with $agent-v3-integration-architect

Provider-agnostic, type-safe AI SDK for streaming, tool calling, structured output, and multimodal content.

Reactive client-first store for your API with collections, live queries, and optimistic mutations.

Create a new CMS collection in Webflow with specified fields and relationships. Use when setting up blog posts, products, team members, portfolios, or other content types with custom fields.

Read research outline, launch independent agent for each item for deep research. Disable task output.

Core trading insights learned from Agent Arena competition. Use when making any trading decision to apply institutional knowledge.

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

Technical SEO - robots.txt, sitemap, meta tags, Core Web Vitals

Cross-platform SEO/GEO toolkit built with Tauri and Rust for crawling, analyzing websites, and parsing server logs without crawl limits

Automated perpetual futures trading bot for AsterDEX with dual strategies, risk management, and TypeScript/Node.js stack

Better Harness Tools for Claude Code — a Python (and in-progress Rust) rewrite of the Claude Code agent harness, with CLI tooling for manifest inspection, parity auditing, and tool/command inventory.

GPT Image 2 prompt gallery, agentic skill, and CLI for OpenAI image generation and editing with curated prompts and reference workflows

WildWorld large-scale action-conditioned world modeling dataset with 108M+ frames from a photorealistic ARPG game, featuring per-frame annotations, 450+ actions, and explicit state information for gen

Evaluate and improve user experience of interfaces (CLI, web, mobile)

App dashboard with purple-themed aesthetic, top-bar navigation, card-based layouts, and developer-first workflows.

Print-inspired visual language for books, magazines, and reports with editorial grids and expressive typography.

>

Extract highlights, best moments, and key clips from long videos using each::sense AI. Perfect for gaming highlights, sports clips, podcast moments, webinar summaries, meeting recaps, and auto-trailer

对spec.md、plan.md和tasks.md三个核心文档进行非破坏性跨工件一致性和质量分析。在任务生成后识别不一致、重复、模糊和规范不足的项目。触发词包括："speckit-analyze"、"speckit分析"、"文档一致性分析"、"规范分析"、"质量检查"、"工件分析"、"spec分析"、"plan分析"、"task分析"。

GoHighLevel integration. Manage Organizations. Use when the user wants to interact with GoHighLevel data.

PostgreSQL development best practices for schema design, query optimization, and database administration

Klaviyo from the shell, with local customer-behavior analytics layered on top. Trigger phrases: `inspect a Klaviyo profile`, `deploy a Klaviyo campaign`, `check Klaviyo flow decay`, `reconcile Klaviyo

Google 連絡先操作（検索・作成・更新・削除）を gog CLI (v0.10.0) で行う。 「連絡先検索」「〇〇さんの電話番号」「連絡先追加」「連絡先一覧」 「アドレス帳から探して」「連絡先を更新」などで発火。

Reconcile the project's FPF state with recent repository changes

Systematically fix all failing tests after business logic changes or refactoring

Identify market expansion and geographic growth plans discussed in earnings calls, including new market launches, international expansion, and product diversification strategies.

Research TikTok metadata, creators, comments, trends, and benchmark data for organic platform analysis.

Visualize your highlights and their connections in an interactive 2D graph

Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder

Agent skill for sona-learning-optimizer - invoke with $agent-sona-learning-optimizer

Modern Angular (v20+) expert with deep knowledge of Signals, Standalone Components, Zoneless applications, SSR/Hydration, and reactive patterns.

Corrects outdated LLM knowledge about the Vercel platform and introduces new products. Injected at session start.

Schema migration strategies for evolving applications including adding new fields, backfilling data, removing deprecated fields, index migrations, and zero-downtime migration patterns

快速生成3-4个选题方向，含标题、大纲和优劣分析。当用户提到"选题"、"写什么"、"文章方向"、"题目建议"时使用。

为小红书笔记生成高质量配图。默认AI生成（Gemini），仅精确数据表格用HTML兜底。当用户提到"小红书配图"、"小红书封面"、"小红书图片"、"做张小红书图"、"笔记配图"时使用此技能。