全部能力

定向聊天室：根据话题推荐或接受用户指定的专家，模拟多角色对话。触发方式：/定向聊天室、「定向聊天室」

Claude-Codex-Gemini tri-model orchestration via /ask codex + /ask gemini, then Claude synthesizes results

评估并改进 Claude Code 命令、技能和智能体。用于测试提示词有效性、验证上下文工程选择或衡量…

Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns,…

Writing guidelines for producing high-quality Traditional Chinese (zh-TW) content. Use when writing any kind of content. Including blog posts, notes, technical articles, technical writing, chitchat, social media posts, etc., even when you are just sending a text message. Also use when reviewing or editing existing Chinese content for tone, style, and terminology compliance.

使用阿里云模型工作室 Qwen ASR 模型（`qwen3-asr-flash`、`qwen-audio-asr`、`qwen3-asr-flash-filetrans`）进行非实时语音转写。适用于…

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security,…

Activate this skill when BenchmarkDotNet (BDN) is involved in the task — creating, running, configuring, or reviewing BDN benchmarks. Also activate when microbenchmarking .NET code would be useful and BenchmarkDotNet is the likely tool. Consider activating when answering a .NET performance question requires measurement and BenchmarkDotNet may be needed. Covers microbenchmark design, BDN configuration and project setup, how to run BDN microbenchmarks efficiently and effectively, and using BDN for side-by-side performance comparisons. Do NOT use for profiling/tracing .NET code (dotnet-trace, PerfView), production telemetry, or load/stress testing (Crank, k6).

GraphQL development guidelines with type-safe clients, schema design, and integration with React and Next.js.

SerpApi for search engine results. Use when user mentions "SERP", "search

[Document Processing] Convert PDF files to Markdown with support for native text PDFs and scanned documents (OCR). Cross-platform.

Comprehensive guide for implementing robust testing strategies in JavaScript/TypeScript applications using modern testing frameworks and best practices.

community-publish — an installable skill for AI agents, published by starchild-ai-agent/official-skills.

通过 OpenAPI/SDK 管理阿里云 DataAnalysisGBI。当用户需要执行 DataAnalysisGBI 资源生命周期操作、配置变更、状态查询等时使用。

使用阿里云 Model Studio Qwen TTS VD 模型进行语音设计工作流。适用于从文本描述创建自定义合成语音并将其用于……时。

Decompose research ideas into atomic, self-contained concepts with bidirectional math-code mapping. For each concept, extract the math formula from papers and…

Run context-mode diagnostics. Checks runtimes, hooks, FTS5, plugin registration, npm and marketplace versions. Trigger: /context-mode:ctx-doctor

Development skill from everything-claude-code

Primary Python tool for 40+ bioinformatics services. Preferred for multi-database workflows: UniProt, KEGG, ChEMBL, PubChem, Reactome, QuickGO. Unified API for…

This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs,…