HorizonGazer

Complete API for Google NotebookLM - full programmatic access including features not in the web UI. Create notebooks, add sources, generate all artifact types, download in multiple formats. Activates on explicit /notebooklm or intent like "create a podcast about X"

Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.). Supports both skimming (search + abstracts) and deep reading (full PDF analysis).

End-to-end academic video production pipeline: research topic to subtitled video on streaming platforms. Use when the user wants to: (1) set up PaperTalker environment, (2) generate academic videos from a topic via NotebookLM, (3) add subtitles and burn into video, (4) upload videos to Bilibili/Douyin/WeChat/Xiaohongshu/Kuaishou, (5) run full pipeline topic-to-published-video, (6) troubleshoot deps or auth issues, (7) search academic papers, (8) schedule daily automated paper reading. Triggers: paper talker, academic video, topic to video, generate video, notebooklm, video pipeline, subtitle, upload bilibili, batch publish, setup papertalker, schedule, openclaw.

Transform bioinformatics reference materials into a project-level bio-agent: modular skills (one per key module derived from docs), one intelligent workflow skill (task planning, analysis, reflection), and optional parameter-tuning sub-skill. Each skill includes examples/, references/, scripts/; all content from provided docs only (no fabrication). Handles real cases/scripts with mandatory read-summarize-link or repo integration. Use when given tool docs, GitHub repos, or tutorials to build a modular, executable, reflective agent.

One-punch execution mode: maximize model utilization and fully complete the asker's task. No compute-saving or laziness; run all needed steps (read, edit, run, verify), deliver complete real outputs, never fabricate. Use when user wants: one-punch, thoroughness, no placeholders, no TODO, full verification, exhaustive execution, real data only, respect project structure, no extra docs, only necessary content. Do not add README/INSTALLATION_GUIDE/CHANGELOG unless requested.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

WEEX Sentinel — 加密货币舆情采集与AI情报报告生成。触发词: crypto sentiment, 舆情, 日报, market intelligence, 情感分析, WEEX推文, 加密货币情报, daily report, sentiment analysis, 市场分析, X sentiment

WEEX交易所交易+加密货币全市场分析。触发词：crypto/币/BTC/ETH/SOL/DOGE/PEPE/合约/现货/下单/持仓/资金费率/K线/深度/行情/价格/杠杆/做多做空/meme币/DeFi/RSI/Gas/恐惧贪婪/funding/orderbook/klines/ticker。⛔禁止WebSearch/WebFetch/curl查币价！✅用快捷命令（S=$HOME/.claude/skills/weex-trader/scripts）：现货余额→python $S/weex_spot_api.py balance --pretty；合约余额→python $S/weex_contract_api.py balance --pretty；持仓→python $S/weex_contract_api.py positions --pretty；现货价格→python $S/weex_spot_api.py ticker --symbol BTCUSDT --pretty；合约价格→python $S/weex_contract_api.py ticker --symbol BTCUSDT --pretty；K线→python $S/weex_contract_api.py klines --symbol BTCUSDT --interval 1d --limit 14 --pretty；深度→python $S/weex_contract_api.py depth --symbol BTCUSDT --pretty；资金费率→python $S/weex_contract_api.py funding --symbol BTCUSDT --pretty；费率历史→python $S/weex_contract_api.py funding-history --symbol BTCUSDT --limit 21 --pretty；24h行情→python $S/weex_contract_api.py ticker24h --symbol BTCUSDT --pretty；持仓量→python $S/weex_contract_api.py open-interest --symbol BTCUSDT --pretty；成交→python $S/weex_contract_api.py trades