From academic-paper
Simulates peer review on LaTeX academic paper drafts: generates 5 reviewer personas with 5D scoring, devil's advocate stress tests, editorial decision, and revision roadmap.
npx claudepluginhub curryfromuestc/academic-paper --plugin academic-paperThis skill is limited to using the following tools:
Simulate peer review on an academic LaTeX paper draft. Runs the full review
Simulates peer review of computer science academic papers, producing bilingual (English-Chinese) structured reports with 1-10 scores on novelty, methodology, writing quality, presentation, significance, critical weaknesses, and actionable suggestions.
Generates structured peer review reports for academic manuscripts, evaluating novelty, methodological rigor, clarity, impact, and ethics. Use when critiquing papers or providing reviewer feedback.
Academic writing multi-agent orchestrator. TRIGGER when: user is editing .tex files, reviewing thesis/paper chapters, drafting academic content, checking writing quality, or analyzing research positioning. Coordinates specialist agents in parallel for review, research, drafting, polishing, figure work, bibliography auditing, and literature surveys.
Share bugs, ideas, or general feedback.
Simulate peer review on an academic LaTeX paper draft. Runs the full review pipeline: 5 reviewer personas -> 5-dimension scoring -> devils-advocate stress test -> editorial synthesis decision -> revision roadmap.
Same as paper-draft. If no .paper-config.yml is found, stop.
$ARGUMENTS for optional --sections=<comma-list> to limit review
to specific sections (default: review the whole paper).peer_reviewer agent. The agent:
subfieldReviewReport with
5-dimension scores (originality, rigor, evidence, coherence, writing)ReviewReport includes recommendation (accept/minor/major/reject)devils_advocate agent to run 7 stress tests on the same
draft (counter-arguments, cherry-picking detection, "So What?" test,
etc.). Output is a 6th ReviewReport with reviewer_id: DA.editorial_synthesizer agent to weight all 6 reports by
confidence and produce a final decision plus a RevisionRoadmap.build/review_report.md (using the
templates/review_report.md template format).This skill orchestrates multiple agents that produce:
ReviewReport (one per reviewer, 5+1 total)RevisionRoadmap (final, from editorial_synthesizer)See references/handoff_schemas.md for full schemas.
/paper-revise (when external reviewer comments arrive) to compare with
this simulated review/paper-draft <section> to address the highest-priority items from the
RevisionRoadmap