发现 Skills

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Access NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata, for metabolomics and biomarker discovery.

DayZ Enforce Script development orchestrator. Dynamically fetches class APIs, script references, and mod documentation. Supports vanilla, Community Framework, and Expansion development for DayZ 1.28+.

Manage Proxmox VE nodes, VMs, and containers. Can list hardware stats, resources, and control power states (start, stop, reboot, shutdown).

Analyzes scenes for performance bottlenecks (draw calls, batching, textures, GameObjects). Use when optimizing scenes or investigating performance issues.

Comprehensive GitHub code review with AI-powered swarm coordination

Fetch a Trello card's metadata or create a new card on a board/list so Codex can operate on the right ticket in the conversation.

Multi-step reasoning engine for complex analysis and systematic problem solving. Use when: (1) Complex debugging scenarios with multiple layers, (2) Architectural analysis and system design, (3) Problems requiring hypothesis testing and validation, (4) Multi-component failure investigation, (5) Performance bottleneck identification. Triggers: "--think", "--think-hard", "--ultrathink", "analyze step by step", "break down this problem", "systematic analysis". IMPORTANT: Do NOT use for simple single-step tasks.

Migrate docs from bd (beads) to br (beads_rust). Use when updating AGENTS.md, converting bd commands, "bd sync" → "br sync --flush-only", or beads migration.

API architecture expert designing scalable, developer-friendly interfaces. Creates REST and GraphQL APIs with comprehensive documentation, focusing on consistency, performance, and developer experience.

Use when the user asks to write specs before code, define acceptance criteria, plan features before implementation, generate tests from specifications, or follow spec-first development practices.

Review UI from screenshots, mockups, browser captures, traces, or videos before proposing frontend code changes.

Project-level operating rules extracted from AGENTS.md, DESIGN.md, and .omk/memory/. Apply silently before implementation.

This skill generates interactive multiple-choice quizzes for each chapter of an intelligent textbook, with questions aligned to specific concepts from the learning graph and distributed across Bloom's Taxonomy cognitive levels to assess student understanding effectively. Use this skill after chapter content has been written and the learning graph exists.

Review Dojo code for best practices, common mistakes, security issues, and optimization opportunities. Use when auditing models, systems, tests, or preparing for deployment.

This skill should be used when the user asks to "escalate privileges on Linux", "find privesc vectors on Linux systems", "exploit sudo misconfigurations", "abuse SUID binaries", "exploit cron jobs for root access", "enumerate Linux systems for privilege escalation", or "gain root access from low-privilege shell". It provides comprehensive techniques for identifying and exploiting privilege escalation paths on Linux systems.

Web search, content extraction, crawling, and research capabilities using the Tavily API

Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform it to production-grade, corporate-level professional quality with optimizations

Guidance for configuring dependency injection in .NET MAUI apps — service registration in MauiProgram.cs, lifetime selection (Singleton / Transient / Scoped), constructor injection, Shell navigation auto-resolution, platform-specific registrations, and testability patterns. USE FOR: "dependency injection", "DI setup", "AddSingleton", "AddTransient", "AddScoped", "service registration", "constructor injection", "IServiceProvider", "MauiProgram DI", "register services", "BindingContext injection". DO NOT USE FOR: data binding (use maui-data-binding), Shell route configuration (use maui-shell-navigation), unit-test mocking frameworks (use standard xUnit and NSubstitute patterns).

Software Requirements Specification documentation following the IEEE 830 standard. Use when generating formal SRS documents or compiling gathered requirements into structured documentation.

Test n8n nodes using Jest as the test runner, nock for deterministic HTTP mocking, and npm link for local node validation in the n8n UI. Use this skill when writing test files in __tests__ folders, mocking HTTP requests with nock, creating mock IExecuteFunctions contexts to simulate the n8n runtime, testing helper functions, setting up golden-file style tests, running the linter as part of the pre-publish checklist, or locally testing nodes in the n8n UI. Apply these practices when organizing test files, mocking external APIs, validating node execution output, or following the pre-publish checklist.

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (scripts/text_to_speech.py) with built-in voices and require OPENAI_API_KEY for live calls. Custom voice creation is out of scope.

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles