deep-research
Conduct comprehensive multi-source research on any topic with synthesis and quality assessment
Conduct comprehensive multi-source research on any topic with synthesis and quality assessment
Generate properly formatted citations and references from research
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
选题审核工具。检查选题是否符合发布标准,给出通过/不通过判断及修改建议。当用户说"审核选题"、"这个选题行不行"、"帮我看看这个能不能写"时触发。
Prepare article for publication by running all pre-publication checks (internal links + fact-check) in parallel. Use when user asks to finalize, prepare for publication, or do final checks on an article.
Perform thorough fact-checking of an article against authoritative official sources. Use when user asks to verify facts, check article accuracy, or validate claims before publication.
Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields.
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.
X(Twitter) 검색 도구. 키워드 검색과 지정 계정 트윗 조회를 수행한다. Use when: X에서 주제 검색, 특정 계정 타임라인, 트렌드·게시물 파악이 필요할 때.
Daily wisdom review applying Charlie Munger's mental models to your work and thinking. Use when asked to review decisions, analyze thinking patterns, detect biases, apply mental models, do a "Munger review", or run the Munger Observer. Triggers on scheduled daily reviews or manual requests like "run munger observer", "review my thinking", "check for blind spots", or "apply mental models".
Three-Layer Memory System — automatic fact extraction, entity-based knowledge graph, and weekly synthesis. Manages life/areas/ entities with atomic facts and living summaries.
X (Twitter) search tool for keyword search and fetching tweets from a specified account. Use when: searching X for topics, reading a user timeline, or tracking trends and posts.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Sibyl Rebuttal 辩护者 agent - 穷尽角度为论文辩护
Sibyl Rebuttal 文献搜索 agent - 引经据典,搜集支持论据
Sibyl 模拟 Reviewer agent - 从真实 reviewer 视角重新评估 rebuttal
Sibyl 新颖性检查 agent - 搜索文献验证 idea 是否与已有论文撞车
Sibyl 文献调研 agent - 使用 arXiv + Web 双源搜索进行系统性文献调研
Adversarial code review using the opposite model. Spawns 1–3 reviewers on the opposing model (Claude spawns Codex, Codex spawns Claude) to challenge work from distinct critical lenses. Triggers: "adversarial review".