Skill rating

收到代码审查反馈后、实施建议之前使用，尤其当反馈不明确或技术上有疑问时——需要技术严谨性和验证，而非敷衍附和或盲目执行

支払調書の画像を読み取り構造化データを返す。 他のスキルから呼び出されるほか、直接ユーザーが呼び出すことも可能。

issue 流程阶段 2——读 report + 读代码定位根因、评估风险，给用户 2-3 个修复方案让 TA 拍板。这一步不改代码。触发：用户说"分析这个 bug"、"找根因"、"定位问题"，且已有 {slug}-report.md。

Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration

ClawHub reputation checker for clawsec-suite. Adds a standalone reputation gate before guarded skill installation.

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems.

Opinionated toolkit for building, versioning, and publishing high-quality JavaScript/TypeScript packages.

Headless utilities for building range and multi-range sliders in TS/JS, React, Vue, Solid, Svelte & Angular.

C# and .NET testing patterns with xUnit, FluentAssertions, mocking, integration tests, and test organization best practices.

Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.

Set up and run an AI marketing team with 4 specialized agents, battle-tested frameworks, and persistent memory for campaign execution

Electron desktop app that captures web traffic via Chrome DevTools Protocol and uses AI to generate protocol analysis reports

Reference guide for permanent free-tier LLM APIs with rate limits, model lists, and OpenAI-compatible integration patterns.

Turn any CLI tool into a fully typed JavaScript/TypeScript API using cli-to-js

Expert skill for building, running, and extending MinecraftConsoles (Minecraft Legacy Console Edition) — a C++ multi-platform reimplementation with dedicated server, LAN multiplayer, and modding suppo

Ultra-lightweight AI assistant in Go that runs on $10 hardware with <10MB RAM, supporting multiple LLM providers, tools, and single-binary deployment across RISC-V, ARM, MIPS, and x86.

Free open-source macOS cleaner built with SwiftUI — CleanMyMac alternative with zero telemetry, scheduled auto-cleaning, and Xcode/Homebrew/system cache cleanup.

Self-hosted ML coding practice platform with 68 problems covering Transformers, diffusion, RLHF, and more — instant browser feedback, no GPU required.

Safe patterns for evolving database schemas in production with decision trees and troubleshooting guidance.

Debug issues using systematic investigation

Test-Driven Development patterns for GSD

Describes PHP and Laravel guidelines provided by Spatie. These rules result in more maintainable, and readable code.

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research artic

Write academic conference papers and research submissions

遇到任何 bug、测试失败或异常行为时使用，在提出修复方案之前执行

Find real fares with Google Flights, scan Kayak nonstop/long-haul routes, and add FlightAware reliability/tracking only when operational context matters.

Analyze a GitHub issue and create a detailed technical specification

Completion Check: Verify Infrastructure Is Wired

Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design.

Trade perp futures, spot, and RWA on Hyperliquid DEX with up to asset max leverage. Use when placing perp or spot orders, setting TP/SL, or moving funds on Hyperliquid (e.g. long BTC 5x, sell ETH, de

Framework-agnostic debouncing, throttling, rate limiting, queuing, and batching utilities.

Framework-agnostic, immutable reactive data store with framework adapters for React, Vue, Solid, Angular, and Svelte.

Headless UI for building powerful tables & datagrids for TS/JS, React, Vue, Solid, Svelte, Qwik, Angular, and Lit.

Runtime security monitor for active OpenClaw skills. Watches file access, network calls, and shell commands. Flags anomalous behavior and enforces permission boundaries.

Use when editing photos for Xiaohongshu, comparing editing apps, or improving visual content quality

Deep security review patterns for authorization logic, data access boundaries, action isolation, rate limiting, and protecting sensitive operations

Quick security audit checklist covering authentication, function exposure, argument validation, row-level access control, and environment variable handling

探测用户的写作风格需求并加载对应指南。当用户提到口语化、生活化、真实感、文学性、严肃文学、纯文学、网文、爽文、快节奏、古风、武侠、古韵、极简、海明威、克制等关键词时自动激活。适用于讨论小说风格、写作文风、创作方向时使用。

Deciding how to test .NET code. Unit vs integration vs E2E decision tree, test doubles.

项目管理和产品需求分析。当用户需要制定项目计划、编写 PRD 文档、管理任务或进行需求分析时使用此技能。

Modern Perl 5.36+ idioms, best practices, and conventions for building robust, maintainable Perl applications.

视频脚本口语化审校，去书面腔让脚本适合说出来。当用户提到"口语化"、"太书面了"、"像说话一样"、"脚本审校"时使用。

快速生成2-3个视频大纲方案，含标题、封面建议和结构设计。当用户提到"视频大纲"、"视频结构"、"脚本大纲"、"视频选题"时使用。

Hermes Agent framework by Nous Research - self-improving AI agent with built-in learning loop, three-layer memory, and automatic skill evolution

Expert guidance for using aube, a fast Rust-based Node.js package manager compatible with pnpm, npm, yarn, and bun lockfiles.

Create accurate Japanese UI DESIGN.md files for AI agents with proper CJK typography, font stacks, line-height, kinsoku shori, and mixed typesetting rules.

Universal AI context generator that compiles codebase maps, wiki knowledge bases, and MCP tools to save thousands of tokens per AI conversation.

Build and extend Gemma Gem, an on-device AI browser assistant Chrome extension running Google's Gemma 4 model via WebGPU with no cloud dependencies.

AI coding agent skill for GPT Image Playground — a React/TypeScript web app for OpenAI image generation and editing using gpt-image-1 and related APIs.

Suggest better variable, function, and class names based on context and conventions.