skills/15-Felpix-Studios-social-science-research/skills/write-paper/SKILL.md
Draft a full academic paper manuscript from analysis outputs, project spec, and lit review. Make sure to use this skill whenever the user wants to turn completed analysis into a written paper — not to run analysis or review existing writing. Triggers include: "write the paper", "draft the manuscript", "write up the results", "start the paper", "turn my results into a paper", "write the introduction", "draft the empirics section", "I have my results, now write the paper", "help me write this up", "write the abstract", or any request to produce academic prose from existing research outputs.
npx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research write-paperInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Draft an academic manuscript from existing analysis outputs. Follows propose-first — the outline is always shown for approval before writing begins.
Input: $ARGUMENTS — a paper title, research question, or from spec to read from quality_reports/specs/.
Read project context:
CLAUDE.md — project name, author, institutionquality_reports/specs/ — research question and identification strategyquality_reports/lit_review_*.md — related literature (if it exists)quality_reports/research_ideation_*.md — hypotheses (if it exists)If no spec exists, ask the user for the core research question before proceeding.
Glob for available outputs:
output/tables/**/*.tex — regression tablesoutput/tables/**/*.html — HTML table versionsoutput/figures/**/*.pdf, output/figures/**/*.png — figuresoutput/**/*.rds, output/**/*.pkl, output/**/*.parquet — saved objectsList what exists. Note any gaps (e.g., "no summary statistics table found").
Draft a paper outline using standard social science structure:
1. Abstract
2. Introduction
3. Related Literature
4. Data and Institutional Background
5. Empirical Strategy
6. Results
7. Robustness and Extensions
8. Conclusion
References
Present the outline with a one-sentence description of each section's content, linking specific output files to each section (e.g., "Table 2 → Section 6, Results"). Do NOT start writing until the user approves the outline or requests changes.
Write in this order (minimizes backtracking):
output/tables/summary_stats.tex if it exists.\input{} or \includegraphics{} — do NOT copy table content inline.Save to manuscripts/[project-name]-draft.tex (or .qmd if the user prefers Quarto).
Create manuscripts/ directory if it does not exist.
Use \input{} for tables and \includegraphics{} for figures — reference the actual files in output/, do not embed content directly.
After saving the draft, launch the domain-reviewer agent via Task:
Task prompt: "Review the draft at manuscripts/[filename] for argument structure, identification assumptions, and citation fidelity. Check that the identification strategy is clearly stated, assumptions are explicit, and all cited tables/figures exist in output/." Task agent: domain-reviewer
Wait for the review to complete, then present the findings to the user.
Inform the user:
/review-paper — for a full top-journal-style review of the manuscript/validate-bib — to check all citations are in the bibliography/quality-gate — to verify every claim in the paper is backed by an output fileoutput/; the paper references them by path.output/, flag it rather than guessing.tools
Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review — searching, reading, extracting, synthesizing, screening, citation-checking, and paper writing. Use when the user asks "what tool should I use to..." OR "install/run/use <tool> to ..." for research/lit-review work: automating a survey or related-work section, PDF→Markdown extraction for LLMs (MinerU/marker/docling), PRISMA / systematic review (ASReview), citation-backed Q&A over PDFs (PaperQA2), wiring papers into Claude/Cursor via MCP (arxiv/paper-search/zotero servers), or chatting with a Zotero library. Ships a launcher (scripts/litrun.py) that installs each tool in an isolated venv and runs it. Curated catalog of 70+ vetted projects. 支持中英文(用于「文献综述工具选型」与「一键安装/运行」)。
development
Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acquisition, manuscript writing, peer review and referee responses, citation checking, de-AIGC editing, or full empirical-paper workflows without reading the entire repository at once.
documentation
Use when the project collects primary data or runs a field, lab, or survey experiment, before the intervention begins — write the pre-analysis plan, size the sample from a power calculation, and register with the AEA RCT Registry. Apply after the design is chosen in aer-identification and before any outcome data are seen.
tools
Guide economists to authoritative data sources with explicit, confirmed data specifications before retrieval; interfaces with Playwright MCP to navigate portals and extract real data, not articles about data.