← all publishers

mathieu0905

@mathieu0905 source repo

Report this profile Claim this profile

• 6 skills
• 0 followers
• 10 hours ago last updated

1. ▌
   Idea Check · mathieu0905 bundle

   Map a CS or research-paper idea, abstract, proposal, or draft against recent top-venue prior work to judge where the idea sits in the field. Use when Codex is asked for CSPaper-style Idea Check, research idea validation, novelty/gap analysis, closest related papers, field landscape synthesis, "has this been done", "idea是否新", "这个idea有没有价值", or whether a planned paper idea has defensible positioning before implementation or submission.
   0 installs
2. ▌
   Correctness Check · mathieu0905 bundle

   Audit a CS or research paper for CSPaper-style correctness, claim verification, technical soundness, and error discovery. Use when Codex is asked to check whether a paper's claims are supported, identify objective mistakes, verify experiments, equations, proofs, metrics, baselines, conclusions, limitations, or run a "Correctness Check", "claim verification", "技术正确性检查", "实验是否支撑结论", or "这篇文章有没有硬伤" review.
   0 installs
3. ▌
   Su Paper Revision · mathieu0905 bundle

   Structural academic paper revision workflow distilled from SU-style supervisor comments. Use when Codex needs to revise, critique, mine, or rewrite research-paper sections after comments about weak story, unclear motivation, unnatural or AI-like writing, repeated RQs, poor section organization, insufficient methodological detail, vague benchmark positioning, unconvincing contributions, table/figure readability, excessive claim strength, or reviewer/supervisor comments marked as su/SU/Zhensu. Especially relevant for LaTeX manuscripts, CS/SE empirical papers, benchmark papers, results sections, RQs, introductions, related work, methodology, threats, response letters, and paper-wide narrative repair before prose polishing.
   0 installs
4. ▌
   Article Logic Editor · mathieu0905 bundle

   Edit, review, or rewrite articles, essays, papers, manuscripts, reports, proposals, and long-form prose with a global logic audit. Use when the user asks to improve coherence, argument flow, section order, paragraph transitions, concept introduction order, consistency across sections, claim-evidence alignment, method-limitation correspondence, or when prose sounds locally plausible but globally scattered or self-contradictory. Also use for Chinese requests about 改文章, 文章逻辑, 不连贯, 前后不一致, 概念突然出现, 顺序问题, or 方法和 limitation 不对应.
   0 installs
5. ▌
   Paper Review Evaluator · mathieu0905 bundle

   Evaluate, compare, calibrate, and rank research papers or LLM/foundation-model technical reports from PDFs, extracted text, or paper titles/topics. Use when Codex is asked to score papers on innovation/value/rigor, find related comparison papers, compare model technical reports, use public reviews for calibration, analyze historical score drift, create tier lists, or write image-generation prompts summarizing rankings.
   0 installs
6. ▌
   Reference Authenticity Auditor · mathieu0905 bundle

   Audit academic references and citations for authenticity, metadata accuracy, and claim support. Use when Codex is asked to verify whether references are real, detect fabricated or hallucinated citations, check BibTeX or bibliography entries, validate DOI/title/author/year/venue consistency, inspect citation contexts, confirm that cited papers support manuscript claims, or prepare a reference-integrity report for LaTeX, Markdown, Word, PDF, BibTeX, RIS, CSL JSON, or plain-text manuscripts.
   0 installs