Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/paper-self-revise
Revise an academic paper based on internal review comments. Reads review report or annotated manuscript, then applies revisions one by one with user approval.
Passed 10 of 17 test cases with the skill, and 5 of 17 without it.
and 5 more in the full report
6 fixed7 passed either way9 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
I have an academic manuscript folder at `./project_directory/` that includes my `main.tex` file and a review report from my co-author. Please process this folder, summarize all the review items for me, and then go through them one at a time showing the relevant manuscript passage, your proposed update, and asking for my decision before saving changes to `main.tex`.
| Checked | Without skill | With skill |
|---|---|---|
| The assistant responds to the user in Chinese. | Missed | Passed |
The instructions your model reads when the skill loads.
This skill revises an academic paper (main.tex) based on internal review comments. The user provides a project folder containing the manuscript and review materials. The skill extracts review comments, then processes them one by one: displaying the comment, showing the original text, proposing a revision, and asking for user approval before applying the change.
Input: A project folder containing:
main.tex — the main manuscript (the file to be modified)review.txt, review.md, review.pdf, report.txt, report.md, report.pdf)annotated.tex, annotated.pdf) where annotations/comments serve as review commentsOutput: The revised main.tex with all approved changes applied in place.
$ARGUMENTS or ask).main.tex and all supporting materials (tables, figures) in the project folder to fully understand the paper.
b. Draft a review report in English (~3000 words), structured as:
review.pdf in the project folder using a Bash command to generate the PDF (e.g., via pandoc or a Python script with reportlab/fpdf). If pandoc is available, first write the content to review.md then convert: pandoc review.md -o review.pdf. If pandoc is not available, use Python to generate the PDF.
d. Count the words of the generated review report (count words in the source text — the review.md content or the raw English text used to build review.pdf, excluding markdown/PDF formatting markup). Use a Bash command such as wc -w review.md or a Python word-count snippet on the text.
e. Inform the user, displaying the actual word count: "审稿报告已生成并保存为 review.pdf（共 X 词），现在开始逐条修改。" — substitute X with the measured count.
f. Proceed to Phase 1 using the newly created review.pdf as the review material.main.tex (the target file to revise).test cases passed, vs 5 / 17 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.