Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Boom5426/Nature-Paper-Skills --skill rebuttal-responsegit clone --depth 1 https://github.com/Boom5426/Nature-Paper-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/boom5426/nature-paper-skills/rebuttal-response)<a href="https://agentmods.dev/skills/boom5426/nature-paper-skills/rebuttal-response"><img src="https://agentmods.dev/badge/skills/boom5426/nature-paper-skills/rebuttal-response/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/boom5426/nature-paper-skills/rebuttal-response"><img src="https://agentmods.dev/badge/skills/boom5426/nature-paper-skills/rebuttal-response.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00124 | $0.02400 |
| Opus 5 | $0.00062 | $0.01200 |
| Sonnet 5 | $0.00025 | $0.00480 |
| Haiku 4.5 | $0.00012 | $0.00240 |
Grade A, and why
rebuttal-response scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Revise Reviewer Responses
Build reviewer replies for a busy reader. Begin every formal response with a brief expression of thanks to the reviewer. Then make every answer immediately traceable to the reviewer's exact concern: lead with what was done and found, state what it means, and identify where the manuscript changed. Do not make the reviewer infer the mapping, search across paragraphs, or read defensive prose after the answer is already clear.
Start from the authoritative materials
- Identify the newest response letter, manuscript, Supplementary Information, figures, tables, and result files relevant to the comment.
- Treat the user's stated version hierarchy as binding. Do not revive text or conclusions from an older response when the user says the manuscript or SI is authoritative.
- Read the complete reviewer comment and the complete current response before editing either.
- Split the comment into independently answerable requests. Preserve the reviewer's own nouns and distinctions, including datasets, methods, comparison units, requested analyses, and claimed outcomes.
- Build a private alignment matrix with one row per request:
- reviewer's exact concern or phrase;
- direct answer;
- action or evidence;
- result;
- supported conclusion;
- revision location;
- essential evidence boundary, if one is genuinely required.
- Use the matrix as an acceptance test. Every row must appear explicitly in the response; no paragraph may substitute an adjacent analysis for the requested object.
- Never invent a result, statistic, experiment, citation, revision location, or placeholder value. Mark unavailable values explicitly or ask for the missing source.
If the task involves direct document editing, also use the relevant document skill and render the finished file for visual verification.
Analyze before drafting
Unless the user explicitly requests only final prose, begin with a short diagnosis:
- What is the reviewer actually asking for?
- Is the concern methodological, evidential, interpretive, presentational, or terminological?
- Does it require a new experiment, a new analysis of existing results, a clarification, or only narrower wording?
- What is the strongest conclusion the available evidence supports?
- What statement in the manuscript, SI, or response must change for the reply to be credible?
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 165 lines · 124 tokens per session scan A 2bfc215596e0
rebuttal-response is a skill published in the GitHub repository Boom5426/Nature-Paper-Skills (490 stars, last pushed 7d ago), licensed MIT. It adds 124 tokens to every session and 2,400 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…