← ClaudeAtlas

academic-paper-writing-skilllisted

Evidence-first academic research workflow for topic ideation, scholarly search, paper reading, literature and systematic reviews, study and experiment design, statistics and data analysis, scientific figures, manuscript drafting and polishing, citation checks, peer review, rebuttals, submission packages, theses, and paper-to-presentation work. Use when an agent must plan, execute, audit, write, revise, or package research while keeping claims traceable to verified sources, data, analysis, or official requirements.
xcl2005/academic-paper-writing-skill · ★ 26 · AI & Automation · score 77
Install: claude install-skill xcl2005/academic-paper-writing-skill
# Academic Paper Writing Skill An adaptable research workflow for papers, reviews, proposals, theses, rebuttals, and research communication. It is a capability router with evidence gates, not a fixed sequence and not a single long prompt. ## Purpose Use this skill across the research lifecycle: - topic selection, research questions, hypotheses, and proposal scoping; - paper lookup, systematic search, screening, citation verification, and literature synthesis; - novelty/SOTA checks, research ROI, scope selection, and venue intelligence; - study design, experiment planning, statistics, data analysis, and reproducibility; - scientific figures, tables, schematics, manuscripts, polishing, and translation; - pre-submission review, revision planning, reviewer response, and rebuttal; - data/code availability, submission packaging, paper reading, and research presentations; - undergraduate thesis, capstone, proposal, midterm, final report, and defense workflows. ## Negative Triggers Do not use this skill as a direct ghostwriting shortcut when the user asks only for final prose without sources, data, result evidence, or requirement context. First route to evidence discovery, source verification, analysis planning, or a bounded draft with explicit placeholders. Do not treat demo samples as verified sources. Do not turn `needs_recheck`, `missing_source`, or `unknown` rows into final prose as verified findings. Explicitly labeled limitations, proposals, and assumptions may remain u