Agent Skills by rlcao
Showing 40 vetted skills indexed across 1 GitHub repositories.
Extract text and structured data from PDF documents using pypdf and pdfplumber.
nano-pdf
Edit PDF text, formats, and content via natural language commands.
himalaya
Manage emails via IMAP and SMTP using Himalaya CLI commands.
tencent-cloud
Translate text between languages using the Tencent Cloud Python SDK.
tencent-translation
Translate text between languages using the Tencent Machine Translation API.
scrapling-official
Fetch and parse web pages with dynamic content and anti-bot bypass.
context7
Retrieve real-time library documentation, code examples, and API references.
MCP 阿里云
Search Chinese web content and parse webpage text via Aliyun DashScope.
self-improving-agent
Log command failures, corrections, and workarounds into categorized Markdown files.
MCP Fetch
Retrieve and extract text or raw HTML from URLs with robots.txt compliance.
agentscope-skill
Develop, evaluate, and deploy multi-agent LLM applications with tool integration and memory management.
MCP 12306 火车票
Query real-time train schedules, seat availability, and pricing via MCP.
MCP DeepWiki
Retrieve structured Wikipedia article content, summaries, and infoboxes via MediaWiki API.
feishu
Manage Feishu messages, tasks, documents, calendars, wikis, and Bitable data.
openai-whisper
Transcribe local audio files to text using the OpenAI Whisper model.
MCP 秘塔AI搜索
Search webpages, documents, academic papers, images, videos, and podcasts via the Metaso AI Search API.
deep-research
Integrate multi-source web and academic searches with structured summarization.
xlsx
Create, edit, and analyze Excel files with pandas and openpyxl.
summarize
Generate summaries for web pages, local files, and YouTube links.
MCP arXiv 论文
Search arXiv papers, download PDFs, and retrieve metadata.
video-frames
Extract frames, generate thumbnails, and create clips from video files using ffmpeg.
ontology
Manage structured agent memory through a typed knowledge graph.
personal-os
Manage personal productivity with OKR, GTD, PARA, and PDCA methodologies.
Image Recognition
Extracts text, tables, and visual data from images using PaddleOCR-VL.