Menü
Proofread papers and manuscripts. Checks grammar, typos, layout, consistency, writing quality. Produces report without editing files. Use when finding surface-level errors, not substantive academic critique.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
End-to-end data analysis in R or Python — exploration through regression to publication-ready tables and figures. Use when running empirical analysis, writing analysis code, or producing output from data.
Find and assess datasets for a research question. Explorer agents search data source categories; Explorer-Critic stress-tests candidates and produces ranked list with feasibility grades. Use when identifying or evaluating data sources, not searching papers or running analysis.
Start a new research project. Structured interview formalizes the idea; generates research questions with identification strategies and a project spec. Use when developing or documenting a new research idea, not searching literature or data.
Verify every quantitative claim in the paper traces to an analysis output file, and no important output was omitted. Use when checking the paper matches the analysis before submission.
Interactive wizard that configures the social-science-research plugin for a new project. Asks about field, institution, journals, datasets, key researchers, R palette; writes answers to references/domain-profile.md and CLAUDE.md. Use first when starting fresh or configuring the plugin.
R code review on existing scripts. Checks quality, reproducibility, domain correctness, professional standards. Produces report without editing files. Use when evaluating or auditing existing R code, not writing new analysis.
| name | proofread |
| description | Proofread papers and manuscripts. Checks grammar, typos, layout, consistency, writing quality. Produces report without editing files. Use when finding surface-level errors, not substantive academic critique. |
| when_to_use | proofread, check typos, grammar check, look for errors, proofread all, polish this, check my writing, any mistakes, proofread before sending, clean-up pass |
| argument-hint | [filename, 'all', or path to manuscript] |
| allowed-tools | ["Read","Grep","Glob","Write","Task","AskUserQuestion"] |
Run the mandatory proofreading protocol on papers or manuscripts. Produces a report of all issues WITHOUT editing any source files.
Identify files to review:
$ARGUMENTS is a specific filename: review that file only$ARGUMENTS is all: review all files in manuscripts/ and Quarto/ (if it exists)$ARGUMENTS is a file in manuscripts/: treat as manuscript (not slides)$ARGUMENTS is empty or ambiguous and multiple files exist, use AskUserQuestion:
For each file, launch the proofreader agent that checks for:
GRAMMAR: Subject-verb agreement, articles (a/an/the), prepositions, tense consistency TYPOS: Misspellings, search-and-replace artifacts, duplicated words LAYOUT ISSUES: Overfull hbox (LaTeX slides/manuscripts), content exceeding slide boundaries (Quarto), table/column overflow in manuscripts CONSISTENCY: Citation format, notation, terminology, variable names matching table column names ACADEMIC QUALITY: Informal language, missing words, awkward constructions
Produce a detailed report for each file listing every finding with:
Save each report to quality_reports/:
.tex slide files: quality_reports/FILENAME_report.md.qmd slide files: quality_reports/FILENAME_qmd_report.mdquality_reports/FILENAME_proofread.mdIMPORTANT: Do NOT edit any source files.
Only produce the report. Fixes are applied separately after user review (see rules/proofreading-protocol.md).
Present summary to the user: