academic-paper
Academic paper writing skill with 12-agent pipeline. v2.5: Style Calibration (learn author's writing voice from past papers) + Writing Quality Check (writing quality checklist for natural prose). Supports IMRaD, literature review, theoretical, case study, policy brief, and conference paper structures. APA 7.0 (default), Chicago, MLA, IEEE, Vancouver citation formats. Bilingual abstracts (zh-TW + EN). Multi-format output (LaTeX, DOCX, PDF, Markdown). Triggers on: write paper, academic paper, paper outline, write abstract, revise paper, check citations, convert to LaTeX, guide my paper, parse re
npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill academic-paper --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill implements a 12-agent pipeline for academic paper writing, including a plan-mode that provides chapter-by-chapter Socratic guidance to crystallize the thesis and structure before drafting. It supports IMRaD and other structures, multiple citation formats (APA 7.0 by default, plus Chicago, MLA, IEEE, Vancouver), bilingual abstracts (zh-TW + EN), and multi-format output (LaTeX, DOCX, PDF, Markdown). It introduces two writing quality features: Style Calibration (learns writing voice from past papers) and Writing Quality Check (a draft self-review checklist). Trigger phrases include write paper, paper outline, write abstract, revise paper, check citations, convert to LaTeX, and various Chinese equivalents. The agent team includes a configuration interviewer, literature strategist, structure architect, argument builder, draft writer, citation compliance, bilingual abstract, peer reviewer, formatter, Socratic mentor, visualization, and revision coach, orchestrated across an 8-phase workflow from configuration to final output.
How it works
- Phase 0 (CONFIG): Intake_agent collects paper type, discipline, journal, citation format, output format, language, word count, and materials.
- Phase 1 (RESEARCH): literature_strategist_agent designs search strategy, screens sources, builds annotated bibliography, constructs literature matrix, maps research gaps.
- Phase 2 (ARCHITECTURE): structure_architect_agent selects structure, drafts detailed outline with word counts, maps evidence, plans transitions.
- Phase 3 (ARGUMENTATION): argument_builder_agent develops central thesis, sub-arguments, claim-evidence-reasoning per section, includes counter-arguments and rebuttals.
- Phase 4 (DRAFTING): draft_writer_agent writes section-by-section, adjusts discipline register, integrates in-text citations, tracks word counts, adds transitions.
- Phase 5a/5b (CITATIONS + ABSTRACT): citation_compliance_agent audits citations, checks DOIs, ensures formatting; abstract_bilingual_agent crafts bilingual abstract with keywords.
- Phase 6 (PEER REVIEW): peer_reviewer_agent performs simulated five-dimension review with revision suggestions; up to two revision loops allowed.
- Phase 7 (FORMAT): formatter_agent converts to LaTeX/DOCX/PDF/Markdown, applies journal formatting, adds cover letter and AI-disclosure, and produces final package.
- Plan Mode Activation and Distinctions: plan mode activates Socratic guidance when intent matches, prioritizing planning over producing a full draft.
When to use it
- Use plan mode when you want step-by-step, chapter-by-chapter guidance to plan a paper.
- Use full mode when you want a complete draft produced via the 9-agent orchestration.
- Use format-convert or citation-check when you need to convert formats or validate references.
What it can touch
- Tools explicitly include claude-code for execution and agent orchestration across phases.
Caveats
- License is NOASSERTION. All actions are constrained to the described agent roles and phases; outputs reflect the specified pipeline and do not guarantee publication success.
Summary: An integrated, multi-agent system that guides planning with Socratic mentoring and then generates a publish-ready academic paper across formats and citation styles, with bilingual abstracts and writing-quality checks.
# Academic Paper — Academic Paper Writing Agent Team A general-purpose academic paper writing tool — 12-agent pipeline covering all disciplines, with higher education domain as the default reference. **v2.5** adds two writing quality features: - **Style Calibration** (intake Step 10, optional) — Provide 3+ past papers and the pipeline learns your writing voice (sentence rhythm, vocabulary preferen
What does the academic-paper skill do?
Academic paper writing skill with 12-agent pipeline. v2.5: Style Calibration (learn author's writing voice from past papers) + Writing Quality Check (writing quality checklist for natural prose). Supports IMRaD, literature review, theoretical, case study, policy brief, and conference paper structures. APA 7.0 (default), Chicago, MLA, IEEE, Vancouver citation formats. Bilingual abstracts (zh-TW + EN). Multi-format output (LaTeX, DOCX, PDF, Markdown). Triggers on: write paper, academic paper, paper outline, write abstract, revise paper, check citations, convert to LaTeX, guide my paper, parse re
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill academic-paper --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Auto-Empirical-Research-Skills, a repository with 3,244 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.