paper-polish
Proofread and verify academic papers in LaTeX. Runs 19 sequential checks covering titles, consistency, citations, formatting, theoretical tension in motivation, concise results reporting, cross-section repetition, em-dash usage, and auxiliary-text-to-footnote conversion. Trigger when user says "check paper" / "proofread" / "paper-checker" / "校对" / "核查论文".
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill paper-polish --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 conducts a comprehensive, multi-step proofreading process for LaTeX papers, running 19 checks in sequence. For each issue found, it presents the user with an original vs. proposed change, then asks for approval to apply the change. Changes are applied only after user approval via the Edit tool. It requires an initial paper directory path, scans for main files (main.tex, ref.bib, and figure/table tex files), reads all files into context, and then proceeds check-by-check with per-issue interactivity. It supports interacting through a defined CRITICAL INTERACTION RULE set, ensuring user control over every modification before execution.
How it works
- Initialization asks for or determines the paper directory path.
- Scans the directory to identify Main LaTeX file, Bibliography file(s), results directory with table/figure .tex, and any original PDFs.
- Reads all relevant files into context (including table .tex files and ref.bib).
- Presents inventory to the user for confirmation before proceeding.
- Executes 19 checks in order. For each check, it surfaces all issues one by one in a stated output format. For each issue:
- It shows the original vs. proposed change (or description of finding).
- It prompts: Accept this change? (yes/no/edit).
- It waits for the user response. If yes, it uses the Edit tool to apply the change; if no, it skips; if edit or custom text is provided, it applies the user’s version.
- After completing all issues within a check, it announces completion and moves to the next check.
When to use it
Trigger phrases include: "check paper", "proofread", "paper-checker", "校对", "核查论文". Use this skill to perform a structured, user-guided proofreading pass on LaTeX papers.
What it can touch
- The skill may touch LaTeX source files via the provided Edit tool for applying approved changes. It reads files with supported tools and can modify content based on user approvals.
Caveats
- All output and interactions are in English.
- The process is strictly interactive: no changes are applied without user approval per issue.
- The license is NOASSERTION for this skill.
- The set of allowed tools includes Read, Bash, Edit, Write, Glob, Grep, AskUserQuestion, WebSearch, WebFetch, but actual modification uses Edit as per approvals.
# Paper Checker ## Overview This skill performs a comprehensive 19-step proofreading and verification of academic papers in LaTeX. Each step is run sequentially. Within each step, every individual issue found is presented to the user one at a time for approval before applying the change. **CRITICAL INTERACTION RULE**: For every issue found in every check, you MUST: 1. Present the issue clearly (or
What does the paper-polish skill do?
Proofread and verify academic papers in LaTeX. Runs 19 sequential checks covering titles, consistency, citations, formatting, theoretical tension in motivation, concise results reporting, cross-section repetition, em-dash usage, and auxiliary-text-to-footnote conversion. Trigger when user says "check paper" / "proofread" / "paper-checker" / "校对" / "核查论文".
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill paper-polish --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.