全部能力

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on…

Plan and optimize resource allocation. Trigger with "resource planning", "capacity", "utilization", "staffing plan", "who should work on what", "we're…

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and…

Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and…

Generate an energy-optimized, time-blocked daily plan based on circadian rhythm research and GTD principles

Use this skill when performing keyword research, search intent analysis, keyword clustering, SERP analysis, competitor keyword gaps, long-tail keyword discovery, or evaluating keywords for snippet opportunity, AI Overview presence, and tri-surface keyword reports. Covers organic (SEO), answer engine (AEO snippets/PAA), and AI citation (GEO AI Overviews/ChatGPT Search/Perplexity) surfaces.

Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader…

Generate an energy-optimized, time-blocked daily plan based on circadian rhythm research and GTD principles

Comprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based…

Converts documents into clean, chunked datasets suitable for embeddings and vector search. Produces chunked JSONL files with metadata, deduplication logic, and…

Analyze market conditions, geographic opportunities, pricing, consumer behavior, and product validation across Google Maps, Facebook, Instagram, Booking.com,…

You must use this when synthesizing existing knowledge, identifying research gaps, or tracing the evolution of scientific ideas.

Compile a LaTeX project and run basic QA (missing refs, bib errors, broken citations), producing `latex/main.pdf` and a build report. **Trigger**: latex compile, build PDF, LaTeX errors, missing refs, 编译PDF, 引用错误. **Use when**: 已有 `latex/main.tex`（通常来自 `latex-scaffold`），需要确认可编译并输出失败原因报告。 **Skip if**: 还没有 LaTeX scaffold（先跑 `latex-scaffold`）。 **Network**: none. **Guardrail**: 编译失败也要落盘 `output/LATEX_BUILD_REPORT.md`；不做“内容改写”，只做编译/QA。

Expert knowledge for Azure Monitor development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas,…

Use when analyzing Xiaohongshu account performance, tracking content metrics, researching competitors, or making data-driven decisions to optimize content…

Use when text embeddings are needed from Alibaba Cloud Model Studio models for semantic search, retrieval-augmented generation, clustering, or offline…

USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.

Find papers that cite a given Google Scholar paper. Tracks citation chains using data-cid (cluster ID). Use when user wants to see who cited a specific paper.

Export Google Scholar paper(s) to Zotero via BibTeX. Gets citation data from Google Scholar's cite dialog, then pushes to Zotero desktop. Supports single or…

Real-time Korean law lookup skill using Beopmang API v4 (api.beopmang.org). Searches statutes, articles, court cases, and revision history. Converts everyday Korean to legal keywords via keyword-map, verifies legal claims, and falls back to web search for the latest or unsupported data. No API key required. Triggers on Korean law names (민법, 근로기준법, 형법, etc.), legal questions (합법이야, 해도 돼, 처벌, 권리), and statute citations.