Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/referee-response
Structure responses to referee reports for R&R submissions
Passed 7 of 15 test cases with the skill, and 8 of 15 without it.
3 fixed8 passed either way9 still failing5 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
When generating the final rebuttal document for round 1 feedback, what directory path should contain the generated markdown file?
| Checked | Without skill | With skill |
|---|---|---|
| Saves the resulting output inside the notes directory | Missed | Passed |
The instructions your model reads when the skill loads.
Draft a structured point-by-point response to referee comments.
$ARGUMENTS — path to a file containing referee comments (e.g., notes/referee-report-R1.txt), or the word "paste" to accept inline inputRead the referee comments:
Read index.qmd to understand the current manuscript content, structure, and arguments.
Parse the referee comments into individual points. Each point typically starts with a number, letter, or dash.
For each referee point, draft a structured response:
**Point N:** [Quote or paraphrase the referee's comment]
**Response:** [Address the comment — acknowledge the concern, explain what was done
or why you disagree, provide additional evidence or reasoning]
**Changes made:** [Describe specific edits with section references, e.g.,
"We have added two paragraphs to Section 3 (@sec-data) clarifying the sample selection."]
Use appropriate response conventions:
Organize the response by referee:
# Response to Referee Comments
test cases passed, vs 8 / 15 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.