using-llm
LLM Calling Skill
List available models and send chat requests to any of them — no extra configuration required.
Core Capabilities
More from dtyq/magic
find-skill
Search and install skills from the platform skill library, skill market, or skillhub. Use when the agent needs to find or install a skill to expand its capabilities. Always search the platform first; fall back to skillhub only if nothing is found.
26skill-vetter
Security-first skill vetting protocol for AI agents. Use before installing any skill from the platform skill market, skillhub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns to determine whether a skill is safe to install.
23ui-data-testid
Add stable `data-testid` attributes by default for new or refactored UI components. Use when implementing React/TSX views, shadcn/antd-style components, dropdown/menu configs, or interactive UI flows that need reliable selectors for unit/E2E tests.
23wiki-generator
通过分析代码结构与依赖，自动提取系统总体架构、核心特有功能模块的实现细节，并生成互相关联的多页面 Wiki 结构文档集。作为项目的架构知识库守护者，还负责在日常开发中解答疑问，并在架构变更时自动维护文档。
22code-review-expert
Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements.
21env-manager
Manage persistent environment variables. Use when the user provides API keys or other configuration values that need to be saved and reused across sessions.
21