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 paper-reviewergit 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/paper-reviewer)<a href="https://agentmods.dev/skills/boom5426/nature-paper-skills/paper-reviewer"><img src="https://agentmods.dev/badge/skills/boom5426/nature-paper-skills/paper-reviewer/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/paper-reviewer"><img src="https://agentmods.dev/badge/skills/boom5426/nature-paper-skills/paper-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 217 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 218 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00190 | $0.03274 |
| Opus 5.5 | $0.00076 | $0.01310 |
| Sonnet 5.5 | $0.00038 | $0.00655 |
| Haiku 4.5 | $0.00019 | $0.00327 |
Grade A, and why
paper-reviewer 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 22d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Referee Reports and the Replies That Answer Them
Two jobs, one standpoint. Writing a referee report and answering one are the same competence seen from two sides: you can only prove you answered a question if you can reconstruct the question that was asked.
Pick the mode before starting.
| Mode | Input | Output |
|---|---|---|
report |
a manuscript | a referee report, or a prediction of what referees will attack |
inventory |
a referee report | every ask and sub-ask, in the referee's own words and order |
reply |
a report plus a manuscript | one reply per ask, plus the coverage audit |
grade |
a drafted reply | what an impatient referee would send back |
The contract
A referee report is a list of questions. A reply is a list of answers. The job is to make the two lists line up so exactly that a referee can verify it by scrolling their own report alongside your letter.
Same count. Same identifiers. Same order. Same words. Depth matched to weight.
The alignment has to be visible on the page, not asserted in a summary. Three consequences, and every rule in this skill follows from them:
- The referee's comment is reproduced verbatim, immediately above its reply. Not paraphrased, not summarised, not trimmed. Nature Methods names rephrasing a referee's comment as a manipulative tactic, and Nature Chemistry asks authors to list the referees' individual points.
- The reply uses the referee's own words. If they wrote
data leak, the reply saysdata leak. Never coin a replacement term, a framework name, or a category label that the referee would have to learn in order to read your answer. Plain language comes from glossing their term, never from inventing a better one. - The referee is impatient. Nature Neuroscience puts it as
keeping in mind that referees are busy. The first sentence carries the answer. Reply length is the minimum that settles the point. Over-answering a light comment is as much a defect as under-answering a heavy one, and Nature Chemistry warns specifically that a long-winded essay style makes a revision harder to follow.
What ships with it
6 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.
- 22d ago Changed · -13 lines · -100 tokens per session f6b68028400d
- 26d ago Changed 9624d3b6793a
- 28d ago Changed · +1 lines 564482be9604
- 1mo ago First seen · 259 lines · 290 tokens per session scan A 709506c328a8
paper-reviewer is a skill published in the GitHub repository Boom5426/Nature-Paper-Skills (637 stars, last pushed 15d ago), licensed MIT. It adds 190 tokens to every session and 3,274 once invoked, about $0.0008 per session on Opus 5.5. 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
anti-defensive-writing-en
Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive…
anti-defensive-writing
A Chinese-language writing guide for presenting a research paper around its strongest supported contribution. It treats the paper as a focused academic presentation rather than a project diary or complete lab record.
paper2poster-poster
Use when the user wants to turn an academic paper into a conference poster, poster outline, poster copy deck, poster layout brief, poster.yaml style draft, or Paper2Poster-ready generation package. Trigger for paper-to-poster requests involving PDF papers, arXiv links, manuscripts, PPTX posters, conference…
nature-paper2ppt
Build a complete but efficient Nature-style Chinese PPTX presentation from a scientific paper, preprint, PDF, article text, abstract, figure legends, or reading notes. Use this skill whenever the user asks to make slides/PPT/PPTX for journal club, group meeting, paper sharing, thesis seminar, lab meeting, department…
fin-submit-check
A pre-submission checklist for an academic paper and its LaTeX files. It checks journal requirements such as anonymous authorship, length, spacing, margins, citations, figures, data availability, and other submission details.
nature-citation
Add strict Nature/CNS citations to manuscript text by splitting long passages into citable segments, searching only accepted flagship and subjournal titles from Nature Portfolio, the AAAS Science family, and Cell Press, filtering by publication time range, and exporting one reference-manager-ready output by default.…