rebuttal-writing
Skill20 starsChanged 9 days agoMITView on GitHub
Prepare point-by-point responses to academic reviews using the supplied manuscript and completed evidence, tracking unanswered questions and proposed experiments separately.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- willlee1995/skillstheir own version, first seen Oct 13, 2026
- Alexyskoutnev/research-skillstheir own version, first seen Aug 7, 2026
- black-yt/skillstheir own version, first seen Aug 4, 2026
- dongzhigang13305312738-art/paper-skillstheir own version, first seen Jul 21, 2026
- sergeeey/Claude-cod-top-2026their own version, first seen May 13, 2026
- xjtulyc/awesome-rosetta-skillstheir own version, first seen Mar 17, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- lingzhi227/agent-research-skills★ 350same name
- xjtulyc/awesome-rosetta-skills★ 34same name
- black-yt/skills★ 16same name
- sergeeey/Claude-cod-top-2026★ 9same name
- Alexyskoutnev/research-skills★ 2same name
- dongzhigang13305312738-art/paper-skills★ 1same name
- willlee1995/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository2 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
If dependencies are missing, create a Python 3.10+ virtual environment and install scripts/requirements.txt from this skill.
- Very specific: line 22
Use paper-agent instead of python3 src/main.py after installation.
- Distinctive: line 31
When new results are supplied, use the academic revision workflow to check result consistency.
- Distinctive: line 34
Keep replies specific and professional.
- Distinctive: line 36
Check the current venue/year response rules before choosing length or format.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Evidence-based rebuttal
For a standalone skill installation, use
python3 <installed-skill-directory>/scripts/paper_agent.py instead of
python3 src/main.py. Its readable runtime is bundled in scripts/runtime/.
If dependencies are missing, create a Python 3.10+ virtual environment and install
scripts/requirements.txt from this skill. No model key is needed by the tools.
Export the complete paper and review text for the host agent:
python3 src/main.py rebuttal --paper paper.md --reviews reviews.txt --out runs/rebuttal-01Use paper-agent instead of python3 src/main.py after installation. Read all
inputs and write rebuttal.md plus actions.json in the exported directory.
The command prepares a task; it does not automatically generate or submit a reply.
- Split reviews into individual points. Assess misunderstanding, valid flaw, missing evidence, experiment request and presentation issue on their merits.
- Link factual responses to manuscript lines and actual supplied evidence.
- Track actions as proposed, not_run, completed or verified. Never describe an experiment as performed or a manuscript change as applied until it exists.
- When new results are supplied, use the academic revision workflow to check result consistency. A rebuttal example is not experimental evidence.
- Acknowledge genuine limitations and state what the evidence cannot resolve.
- Keep replies specific and professional. Do not invent reviewer score changes or promise that a response will reverse a decision.
- Check the current venue/year response rules before choosing length or format.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.