ovohao

@ovohao source repo

4 skills
0 followers
3 days ago last updated

▌
Auto Paper Collecter · ovohao bundle
Personal research-paper radar. Fetches the latest papers and code repos for the user's keyword subscriptions across arXiv, Crossref (IEEE/ACM), Semantic Scholar, GitHub, HuggingFace, Papers with Code and RSS; deduplicates against history; then YOU (the assistant) expand the queries, filter for computer-science relevance, write Chinese summaries, detect hot sub-fields, and emit a Markdown + HTML digest (optionally emailed). Use when the user asks to "run my paper radar / 文献雷达", "check for new papers", "what's new in my topics", "今天有什么新论文 / 最新文献", "today's research digest", or to configure their keyword subscriptions / sources / schedule.

0 installs
▌
Companion Pet · ovohao bundle
Control the companion-pet desktop companion (桌面陪伴小精灵) for Claude Code/Codex. Use when the user wants to start/show/hide/stop the desktop pet, switch or add a character image, list characters, change what it says (台词/通知文案), check status, or install it. Triggers include "桌宠", "陪伴小精灵", "启动/关闭桌宠", "换个角色", "把这张图加进桌宠/加个角色", "我的桌宠有哪些角色", "改一下桌宠说的话", "companion pet", "show/hide my pet", "desktop pet".

0 installs
▌
Worldcup Prediction · ovohao bundle
World Cup football match prediction pipeline producing calibrated probability distributions (1X2, totals, top scorelines), edge analysis vs de-vigged market odds, fractional-Kelly sizing with a strict no-bet rule, and qualification scenario simulation. Use this skill whenever the user asks to predict, analyse, or preview a World Cup (or other football) match, asks about win/draw/loss chances, expected goals or scorelines, odds value, line movement, betting edge, Kelly staking, group standings or qualification scenarios, or asks to run the agent pipeline / generate a match prediction report — even if they just say "分析这场比赛" or "这场怎么看".

0 installs
▌
Paper Explainer · ovohao
Deep-read an uploaded academic paper and explain it thoroughly in Chinese — background and positioning, the limitation it targets, how the method solves it, experimental setup and results, critical analysis, and future work — then stay in an anchored Q&A mode for follow-up questions. Every claim is grounded in a paper-specific knowledge graph whose nodes carry location anchors (section / table / figure / equation / page), so answers never drift from the source. Use this skill whenever the user uploads a paper and asks to deeply understand, explain, walk through, or teach it — phrases like "讲一下这篇论文", "帮我精读", "这篇文章讲了什么", "给我讲懂这个方法", "explain this paper to me", "walk me through this paper", or when the user asks follow-up questions about a paper already read in this conversation (e.g. "4.2节那个loss怎么算的"). Do NOT use for peer review, venue-calibrated reviewing, proofreading, or error-checking — that is academic-paper-reader's job. This skill is for comprehension and explanation, not assessment.

0 installs

4 published skills