技能列表

Generate professional labels in LMP format from natural language descriptions. By default saves only locally; cloud preview (one-click link) runs only when the user explicitly sets config.apiEndpoint — no data is sent externally unless configured.

Helps merchants selling utility / problem-solution products (car storage, multi-use kitchen shears, storage boxes, cleaning tools, etc.) do assortment and product improvement via VOC-based selection (voice of customer from reviews). Trigger when users mention review analysis, negative-review pain points, user complaints, selection from reviews, basis for feature improvements, competitor negative reviews, real buyer needs, "our bad reviews keep mentioning X," "which subcategory should I pick," or

Automatically generate social media posts from articles. Supports Twitter, LinkedIn, Instagram, TikTok, and YouTube Shorts. Perfect for content repurposing.

|

Run and integrate LM Studio with local model lifecycle control, OpenAI-compatible APIs, embeddings, and MCP-aware workflows.

Generate weekly tech news briefings from 6 major English tech media sources (TechCrunch, The Verge, Wired, Ars Technica, MIT Technology Review, The Information). Aggregates news from the past 7 days, identifies hot stories covered by multiple outlets (2 or more media sources), and creates a curated report in the user's preferred language. Features automated daily RSS fetching, intelligent deduplication, low-quality content filtering, and interactive company-based navigation. Use when users reque

>

在 GPU 服务器上部署 LLM 模型服务（vLLM）。支持多服务器配置，自动检查 GPU 和端口占用，一键部署流行的开源大语言模型。

|

search and analyze llm benchmark results within a fixed benchmark universe, then produce evidence-based model strength and weakness reports or domain-leader summaries. use when comparing a model across benchmarks, ranking the best models by domain, explaining what a benchmark measures, checking predecessor-vs-current progress, or writing benchmark reports that must prioritize exact model version, evaluation date, benchmark variant, score semantics, sub-scores, and benchmark defect warnings. work

|

Parse, extract, and analyze documents using the LlamaParse API (LlamaCloud). Use when the user asks to parse PDFs, images, spreadsheets, or other documents into markdown/text/structured data, extract tables or charts from documents, do OCR on scans, batch-process a folder of files, or use LlamaParse for any document processing task. Triggers on phrases like "parse this PDF", "extract text from document", "OCR this scan", "convert PDF to markdown", "extract tables", "parse with LlamaParse", "llam