Loading...
Loading...
Found 107 Skills
Intelligent multi-topic in-depth research tool that supports input of any materials, uses independent research Agents for parallel in-depth retrieval and generates systematic research documents. This skill should be used when users need to conduct in-depth research on multiple related topics, perform systematic information retrieval, and integrate multi-angle analysis.
Google web search with integrated image results
CCDB Carbon Emission Factor Search Tool. Based on Carbonstop's CCDB database, query carbon emission factor data via ccdb-mcp-server. Supports keyword-based carbon emission factor search, retrieval of structured JSON data, and multi-keyword comparison. **Use this Skill when**: (1) Users query carbon emission factors (e.g., "power emission factor", "cement carbon emission", "natural gas emission coefficient", etc.) (2) Users need to calculate carbon emissions (require querying factors first then multiplying by activity volume) (3) Users need to compare carbon emission factors of different energy sources/materials (4) Users mention "CCDB", "carbon emission factor", "emission coefficient", "carbon footprint", "LCA", "emission factor" (5) Need to query carbon emission factor data for specific countries/regions and specific years
Search Korean scholarship announcements across official KOSAF, university, foundation, company, and public-sector sources, extract amount and eligibility, and filter results by school, income band, student level, and organization type. Users may invoke it with the phrase 장학금 검색 및 조회.
Offer a structured but non-clinical space for a PhD student or researcher to check in on their mental and emotional state, especially around imposter syndrome, guilt about rest, chronic over-promising, and burnout signals. Use this skill when the user expresses feelings of inadequacy, constant comparison to peers, fear of disappointing their advisor, guilt about taking time off, or exhaustion that isn't just physical. Trigger on phrases like "I feel behind", "everyone is smarter than me", "I can't rest", "I'm burned out", "imposter syndrome", "I'm not good enough", "I'm afraid of disappointing", "I should be working", or whenever the tone of the user's message suggests emotional strain rather than a technical question. Also trigger gently if these signals appear incidentally in a task-focused conversation.
Extract structured fields, original text locations, missing items, and supportable judgments from papers and supplementary materials. Use when the user asks for "extract this paper", "batch extract paper information", "create paper cards", or requests the rw-paper-extractor workflow. Runs without a private local workspace or preset research-lab; use user-provided material and bundled public-source methods.
Search OpenSearch documentation, blogs, and community forums. Use when the user asks about OpenSearch features, configuration, APIs, troubleshooting, k-NN, neural search, cluster settings, index mappings, query DSL, or any OpenSearch-related questions.
Choose the right search tool for each query type
One-time onboarding - upload resume, set preferences, and do a work history interview
Use the built-in web_search function to perform web searches and return summary results. Prepare a clear and specific `query`. Run the script `python scripts/web_search.py "query"`. Organize the answer based on the returned summary list without adding or fabricating content.
DEFAULT search tool for ALL search/lookup needs. Multi-source search and deduplication layer with intent-aware scoring. Integrates Brave Search (web_search), Exa, Tavily, and Grok to provide high-coverage, high-quality results. Automatically classifies query intent and adjusts search strategy, scoring weights, and result synthesis. Use for ANY query that requires web search — factual lookups, research, news, comparisons, resource finding, "what is X", status checks, etc. Do NOT use raw web_search directly; always route through this skill.
A specialized skill for generating high-quality illustrations for academic papers, supporting two output formats: (1) LaTeX/TikZ code: Suitable for structured diagrams such as system architecture diagrams, data flow diagrams, and geometric schematic diagrams, which can be directly embedded into papers; (2) draw.io XML: Suitable for highly decorative diagrams such as technical roadmaps, scientific research display diagrams, and academic presentation illustrations, supporting gradient colors, shadows, and free layout, which can be opened and edited at app.diagrams.net. Supports the above two output formats with a unified workflow: Analyze input (copy/image/paper) → Drawing instructions → Code generation → Compilation verification → Full-score delivery. It automatically identifies the field of the paper and designs illustrations as an expert in that field. Use when the user asks to: 画论文图、画架构图、画流程图、画示意图、 LaTeX画图、TikZ画图、论文配图、生成画图指令、复刻图片、 画图代码、学术论文图、画系统架构、画协议流程、论文插图、tikz diagram、 latex figure、根据论文画图、画个图、帮我画图、生成tikz、论文tikz、 根据文案画图、照着图片画、复刻这张图、技术路线图、科研架构图、 学术汇报图、drawio、draw.io、路线图、研究框架图、技术方案图。