MCP App StoreMCP App StoreOpenClaw skill to generate personalized academic paper recommendations using AMiner + arXiv + local pipelines. Designed to be invoked explicitly via /aminer-rec5 or /skill aminer-rec5 (Feishu). The skill constructs a ResearchProfile from inputs (aminer_user_id, scholar, org, seed papers, topics, language and year filters), retrieves candidate papers, enriches metadata via AMiner, and dispatches results as Feishu cards.
Run the provided handler script: python3 "{baseDir}/scripts/handle_trigger.py" --base-dir "{baseDir}" --text "<original Feishu message>". After execution check final_response: NO_REPLY means Feishu cards dispatched (return exactly NO_REPLY), TEXT means return reply_text to user, errors should surface their details.
aminer-rec5 is a well-structured research paper recommendation pipeline that integrates AMiner, arXiv, and LLM enrichment, then dispatches results via Feishu cards. It has 20 scripts organized as a Python package with a single entrypoint (handle_trigger.py). Scripts use proper HTTP clients with retries and error handling. The subprocess calls are safe (explicit command lists, no shell=True). However, it's tightly coupled to Feishu delivery and AMiner API (requires AMINER_TOKEN), limiting its audience to users already in that ecosystem. 14/20 scripts failed to import standalone due to package path issues in isolation.
Clean codebase with no security concerns. Subprocess usage is safe (list-based commands, no shell=True). No hardcoded secrets — all credentials read from env vars or config. The skill is niche (AMiner + Feishu research recommendations) which limits broad usefulness. Architecture follows good patterns with a single entrypoint, clear contract, and well-separated concerns. The import failures during testing are expected for a package-structured Python project run in isolation.
arxiv2md
Convert arXiv papers into clean, LLM-ready Markdown via a REST API or CLI for fast reading, summarization, and downstream processing.
Scite Database (Smart Citations)
Query Scite.ai Smart Citations by DOI to report supporting, contrasting, and mentioning citation counts and help assess a paper's reliability.
Generate Multilingual Sentences with Contextual Definitions
Produce multiple example sentences using a target word in varied meanings, translate them into a target language, and show the contextual meaning of the word fo
Writing Implementation Plans
Generate detailed, engineer-ready implementation plans from design docs: file paths, step-by-step tasks, tests, and verification instructions.
Humanize AI Text
Rewrite AI-generated text into more natural, human-like prose using the HumanizerAI API, with before/after scores and credit tracking.
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c
AI News Daily
Generate a structured, bilingual daily briefing of the latest AI industry news, model updates, papers, and open-source tools with in-depth technical analysis an
ToolUniverse Gateway
Unified agent gateway to 1000+ scientific tools (bioinformatics, drug discovery, genomics) via Harvard's ToolUniverse, returning JSON for downstream workflows.
