发现 Skills

Use when building, debugging, packaging, or publishing browser userscripts for Tampermonkey or ScriptCat, including GM APIs, metadata blocks, permission issues, @match/@grant/@connect setup, ScriptCat background or scheduled scripts, UserConfig blocks, or subscription workflows.

This skill establishes a **mandatory review process** for any community or third-party skills before they are installed into the Xomware Claude agent environment. Skills can execute arbitrary code and therefore may introduce supply-chain, security, and runtime risks if not properly vetted.

To install the Playwright browser defined in config, run this when the browser is missing or not installed.

AI-powered debugging assistance - analyzes errors, suggests breakpoints, and guides you through fixing bugs step-by-step

Use this agent when the user asks questions ("Can Claude...", "Does Claude...", "How do I...") about: (1) Claude Code (the CLI tool) - features, hooks, slash commands, MCP servers, settings, IDE integrations, keyboard shortcuts; (2) Claude Agent SDK - building custom agents; (3) Claude API (formerly Anthropic API) - API usage, tool use, Anthropic SDK usage. IMPORTANT: Before spawning a new agent, check if there is already a running or recently completed claude-code-guide agent that you can resume using the "resume" parameter.

Automated competitor research across the web: collect company overview, product pricing, user reviews, and other information, and generate a structured competitor analysis report.

Calculates ROI, payback period, and financial projections for business investments including technology purchases, automation projects, hiring decisions, and equipment acquisitions. Use when evaluating whether a business investment is worth making, comparing multiple investment options, or building a business case for stakeholders.

Expert Go developer (1.25+) specializing in Clean Architecture and DDD.

Alias for $plan --consensus

Feature-based frontend architecture conventions. Automatically activates when creating new files or directories, or when organizing project structure. Defines rules for feature-based code organization, module boundaries, dependency direction, and public API design.

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.

The agent team executes the entire development cycle — PRD → design → implementation → review → commit/PR — as a Q&A loop.

Generate a web-based documentation viewer for browsing project docs. Use when a human wants to view documentation in a web browser. Triggers on requests like "create doc viewer", "documentation viewer", "browse docs in browser", "generate docs site".

Generate images using the Banana.dev inference API. Lightweight image generation with Python script and configurable prompts.

X API v2 available endpoints. Use when working with the X API v2 or when the user needs to interact with this API.

This skill should be used when the user asks to create a slash command, add a command, write a custom command, define command arguments, use command frontmatter, organize commands, create command with file references, interactive command, use AskUserQuestion in command, or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

Generate videos from text and image prompts via Together AI. 15+ models including Veo 2/3, Sora 2, Kling 2.1, Hailuo 02, Seedance, PixVerse, Vidu. Supports text-to-video, image-to-video, keyframe control, and reference images. Use when users want to generate videos, create video content, animate images, or work with any video generation task.

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

Run a final release checklist before shipping. Verifies no TODOs, no debug code, docs updated, tests passing, dependencies justified, and security reviewed.

Реализует concurrent Go паттерны с goroutines и channels, проектирует микросервисы с gRPC/REST. Используй для goroutines, channels, generics, gRPC, CLI tools, benchmarks.

This skill should be used when the user asks to "test for directory traversal", "exploit path traversal vulnerabilities", "read arbitrary files through web applications", "find LFI vulnerabilities", or "access files outside web root". It provides comprehensive file path traversal attack and testing methodologies.

This skill should be used when the user asks to "perform vulnerability scanning", "scan networks for open ports", "assess web application security", "scan wireless networks", "detect malware", "check cloud security", or "evaluate system compliance". It provides comprehensive guidance on security scanning tools and methodologies.

This skill should be used when the user asks to "perform SMTP penetration testing", "enumerate email users", "test for open mail relays", "grab SMTP banners", "brute force email credentials", or "assess mail server security". It provides comprehensive techniques for testing SMTP server security.

This skill should be used when the user asks to "escalate privileges on Windows," "find Windows privesc vectors," "enumerate Windows for privilege escalation," "exploit Windows misconfigurations," or "perform post-exploitation privilege escalation." It provides comprehensive guidance for discovering and exploiting privilege escalation vulnerabilities in Windows environments.