Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.
AI paper reviewer. Use when the user says 'review my paper', 'help me review this paper', '审稿', 'give me feedback on my paper', 'check my manuscript', 'evaluate this paper for NeurIPS/ICLR/EuroSys'. Accepts PDF files and produces structured narrative reviews with venue-specific dimensional scores and Accept/Reject recommendation.
Reviews chapter quality using 5 specialized checkers and generates comprehensive reports. Activates when user requests chapter review or /webnovel-review.
Plans detailed volume outlines with chapter-by-chapter breakdown, cool-point distribution, and Strand Weave pacing. Activates when user requests outline planning or /webnovel-plan.
Critiques ML conference papers with reviewer-style feedback. Use when users want to anticipate reviewer concerns, identify weaknesses, check claim-evidence gaps, or find missing citations.
Conduct a literature review and develop a CS research proposal. Use when asked to review a research area, find gaps in existing work, and propose a novel research contribution. The output is a research proposal identifying an assumption to challenge (the "bit flip") and how to validate it.
Paper reviewer that evaluates machine learning research projects following official ICML reviewer guidelines. Provides comprehensive reviews with actionable feedback across all key dimensions: claims/evidence, relation to prior work, originality, significance, clarity, and reproducibility. Also provides formative feedback on incomplete drafts, proposals, and research code repositories. MANDATORY TRIGGERS: review paper, ICML review, paper review, evaluate paper, research paper feedback, ML paper review, conference review, academic review, paper critique, NeurIPS review, ICLR review, project proposal, research proposal, paper draft, early feedback, incomplete paper, work in progress, WIP review, review repo, review codebase, research project review
Evaluate how well a job posting matches your background. Paste a JD or URL and get an honest A-F scored assessment with match analysis, compensation research, positioning strategy, and interview prep. Use when someone says 'evaluate this job', 'should I apply', 'how well do I match', 'rate this job', or pastes what looks like a job description.
Write or edit an academic CS paper following formal, evidence-driven, and structured writing style
Suggest the top 5 improvements for an academic paper to increase its impact
Add relevant bibliography entries to a LaTeX academic paper and reference them in the text
Synthesizes findings across multiple papers into a coherent narrative, structured comparison table, or temporal evolution story. Use when the user wants the "big picture" across a set of papers, needs a related work section that synthesizes rather than lists, wants to compare methods/models across papers in a table, or wants to understand how a field's thinking has evolved over time. Triggers on phrases like "synthesize these papers", "big picture", "how has this evolved", "compare these methods", "related work section", "what's the through line", "narrative synthesis".
Evaluates and grades the strength of evidence behind scientific claims based on study design, replication status, sample size, venue quality, and recency. Use when the user wants to know how much to trust a finding, needs to calibrate hedging language for a manuscript, wants to grade preliminary evidence for a grant, or needs to rank a set of papers by evidentiary weight. Triggers on phrases like "how strong is the evidence", "can we trust this result", "how preliminary is this", "grade this paper", "how confident should we be", "is this well-supported", "calibrate our claim".
Searches and retrieves paper metadata, citations, references, and author profiles from the Semantic Scholar Academic Graph (200M+ papers). Use when the user needs paper metadata by title or DOI, wants papers citing or referenced by a specific work, needs an author's publication list or h-index, wants to do a semantic search over a topic, or needs structured paper data for building a literature database. Triggers on phrases like "look up this paper", "find papers on", "who cites", "references of", "author profile", "h-index", "semantic scholar".
Drafts concise, strategic rebuttals for conference paper reviews under strict word limits. Use when the user has received conference reviews and needs a rebuttal for NeurIPS, ICML, ICLR, ACL, CVPR, or similar venues. This is different from journal review-response — conference rebuttals are word-limited and strategically different. Triggers on phrases like "conference rebuttal", "author response", "NeurIPS rebuttal", "ICML rebuttal", "ICLR rebuttal", "ACL rebuttal", "500 word rebuttal", "how to respond to conference reviews".
Identifies research gaps — what hasn't been studied, is underexplored, or remains unresolved — in a body of literature. Use when the user wants to find novel research directions, position their work as a new contribution, write a significance or motivation section for a grant or paper, verify that a proposed contribution is actually novel, or identify what the field is missing. Triggers on phrases like "what hasn't been done", "research gaps", "what's missing", "is this novel", "open questions", "what should we study next", "gap in the literature".
Monitors arXiv for new papers matching research interests. Use when the user wants to know what's new on arXiv, set up monitoring for a topic or author, get a weekly digest of relevant preprints, or find out if anyone has published on a specific topic recently. Triggers on phrases like "what's new on arXiv", "monitor arXiv for", "recent papers on", "arXiv digest", "any new preprints about", "has anyone published on X".
Drafts structured, evidence-backed responses to peer reviewer comments for journal revisions. Use when the user has received reviewer feedback and needs help drafting a point-by-point response, wants to triage reviewer concerns by impact, needs to find literature addressing a reviewer's concern, or needs to write the cover letter for a resubmission. Triggers on phrases like "respond to reviewers", "reviewer comments", "point-by-point response", "revise and resubmit", "address reviewer", "reviewer 2 says", "write the rebuttal letter", "revision response".
Shares, surfaces, and discusses PDF annotations across a research team. Use when the user wants to see what teammates highlighted or noted in a paper, share their own annotations with the team, search across all team annotations on a topic, start or reply to a discussion thread on a specific passage, or import annotations from Zotero or Hypothesis. Triggers on phrases like "what did X highlight", "share my annotations", "team notes on this paper", "search annotations", "what did we note about", "annotation thread", "import from Hypothesis".
Maintains a continuously updated, structured literature review for a research team. Use when the user wants to add papers to a shared review, generate or update a literature review document, summarize what the team has collectively read on a topic, prepare an introduction or related work section, or onboard a new team member with a fast overview of prior work. Triggers on phrases like "update our lit review", "add this paper to the review", "what do we know about X", "summarize the papers on", "generate a related work section".
Tracks which papers the team has collectively read, who has read what, and which important papers remain unread. Use when the user wants to know if anyone has read a specific paper, wants an overview of team reading coverage, needs to assign unread papers to team members, or wants to generate a reading queue. Triggers on phrases like "has anyone read", "who read this paper", "reading coverage", "unread papers", "reading assignments", "what haven't we read", "reading queue", "assign papers to".
Scans a body of papers for conflicting empirical claims, opposing conclusions, or methodological disagreements on the same topic. Use when the user wants to know if papers in their corpus disagree with each other, needs to address conflicting findings in a discussion section, wants to verify a claim before building on it, or is trying to understand why two papers got different results. Triggers on phrases like "do any papers disagree", "conflicting findings", "paper A contradicts paper B", "why do results differ", "conflicting claims", "contradiction in the literature".
Use when researching documentation, papers, or articles for insights. Triggers on "research external", "find sources", "literature review", "what do the docs say".
