New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Nature Paper Xray

by Yuan1z0825 in Yuan1z0825/nature-skills

Read one supplied paper closely enough to reconstruct how its authors actually got there, rather than restating what the abstract claims.

Apache-2.0Auto-check passedResearch & Science

Install Nature Paper Xray

skills CLI
$ npx skills add Yuan1z0825/nature-skills --skill nature-paper-xray -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Yuan1z0825/nature-skills nature-paper-xray --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Yuan1z0825/nature-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/nature-paper-xray .claude/skills/nature-paper-xray && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
nature-paper-xray
GitHub stars
47k
Token cost
~1.5k tokens
SKILL.md length
794 words
Files
7 (incl. references)
Skills in repo
23
Repo updated
First seen
Licence
Apache-2.0

At a glance

Read one supplied paper closely enough to reconstruct how its authors actually got there, rather than restating what the abstract claims.

  • Works in 7 steps: Read the whole source first — body,… → Reconstruct the research path. Name the… → Separate load-bearing from decoration.… → …
  • Deep single-paper comprehension before building on
  • SKILL.md covers Default stance, Workflow, Paper-type adaptation and Boundaries, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Nature Paper Xray is an agent skill from Yuan1z0825/nature-skills. Read one supplied paper closely enough to reconstruct how its authors actually got there, rather than restating what the abstract claims. Use for 精读论文, 讲透这篇论文, 把这篇读懂, 作者为什么这么设计, 这个公式怎么推出来的, paper x-ray, and deep single-paper comprehension before building on, reviewing, presenting, or citing that paper. Recovers the real starting point and the bet the authors placed, separates load-bearing design from decoration, grounds each key formula in a worked micro-example with concrete numbers, and checks how far the…

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `README.md`, `README_EN.md` and `agents/openai.yaml`).

It sits in Research & Science, covering Translation. The repository describes itself as: 符合nature论文学术表达和科研绘图的Skill. The licence is Apache-2.0.

When your agent uses it

  • Deep single-paper comprehension before building on
  • Citing that paper

Example prompts

  • “/nature-paper-xray”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Read the whole source first — body, appendix, footnotes, figure and table captions, and supplementary material if supplied. Appendices…
  2. Reconstruct the research path. Name the concrete failure the work reacts to, and the bet the authors placed on their strongest evidence…
  3. Separate load-bearing from decoration. For each distinctive design choice, judge whether removing it collapses the result or merely…
  4. Ground the mathematics. Give every symbol its shape and meaning, state what a formula is for before stating the formula, and follow each…
  5. Check the evidence boundary. Agreement between body text, tables, and figures; whether baselines share data, steps, and tuning budget…
  6. Preserve hedging strength. "May" is not "does", "suggests" is not "shows", "some settings" is not "all settings". Where the paper does not…
  7. Deliver the long-read. Lead with what the paper is actually claiming, then the reconstructed path, the load-bearing judgment, the worked…

What it can do on your machine

Read from SKILL.md and the folder at commit e605b35. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Nature Paper Xray loads about 1.5k tokens when it runs, and up to ~3.3k if it reads all its reference files. Until then it costs about 188 tokens; SKILL.md has 794 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~188
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Yuan1z0825/nature-skills at commit e605b35, republished under its Apache-2.0 licence (© Yuan1z0825). 794 words, ~1,524 tokens.

Download SKILL.mdSave it as .claude/skills/nature-paper-xray/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
nature-paper-xray
description
Read one supplied paper closely enough to reconstruct how its authors actually got there, rather than restating what the abstract claims. Use for 精读论文, 讲透这篇论文, 把这篇读懂, 作者为什么这么设计, 这个公式怎么推出来的, paper x-ray, and deep single-paper comprehension before building on, reviewing, presenting, or citing that paper. Recovers the real starting point and the bet the authors placed, separates load-bearing design from decoration, grounds each key formula in a worked micro-example with concrete numbers, and checks how far the evidence actually reaches, including where the authors are confident and where the paper does not report something. Delivers a structured Markdown long-read by default. Not a summary, not a translation, not a peer review.

Nature Paper X-Ray

Read a paper the way a researcher explains it at a whiteboard to a colleague: what the authors saw, why they believed it, where they hesitated, what they gave up, and which numbers would change the conclusion.

The delivered artifact is a Markdown long-read. A section-by-section summary of the paper is a failure mode, not a fallback.

Default stance

  • The method section is a teaching order, not the order the work happened in. The introduction's story is arranged after the fact. The contribution list is written for reviewers.
  • The judgments that decided the paper — what the authors noticed, why they trusted it, what they abandoned — are mostly not written down. Recovering them is the job.
  • Every figure was chosen. Ask what the authors want a reader to believe from this one, then look for details inside it that do not support that reading.
  • A figure contains its own counter-evidence more often than the text does: a curve that crosses later, an error bar wider than the gap between compared methods, a log axis hiding a constant-factor difference, one seed standing in for a variance claim.
  • Name a mechanism or say the paper does not name one. Do not supply a motive the authors never stated.

Workflow

  1. Read the whole source first — body, appendix, footnotes, figure and table captions, and supplementary material if supplied. Appendices carry what the body declined to print: real hyperparameter search ranges, unflattering ablations, reviewer-response material. Record disagreements between the body and the appendix as findings.
  2. Reconstruct the research path. Name the concrete failure the work reacts to, and the bet the authors placed on their strongest evidence. The first figure usually carries that bet and deserves separate treatment.
  3. Separate load-bearing from decoration. For each distinctive design choice, judge whether removing it collapses the result or merely accompanies it. Cite the ablation, appendix table, or controlled comparison that settles it. When no such control exists, write that the paper does not run it.
  4. Ground the mathematics. Give every symbol its shape and meaning, state what a formula is for before stating the formula, and follow each key formula with a micro-example using concrete numbers carried to the end. See references/deep-reading-protocol.md.
  5. Check the evidence boundary. Agreement between body text, tables, and figures; whether baselines share data, steps, and tuning budget; whether hyperparameters were selected on the test set; preprocessing leakage; cost and the conditions under which the claim stops holding. See references/evidence-boundary.md.
  6. Preserve hedging strength. "May" is not "does", "suggests" is not "shows", "some settings" is not "all settings". Where the paper does not report something the conclusion needs, write that it is not reported. Never substitute a plausible number, an assumed default, or a value remembered from a similar paper.
  7. Deliver the long-read. Lead with what the paper is actually claiming, then the reconstructed path, the load-bearing judgment, the worked examples, and the evidence boundary. Close with what a reader should carry away and what remains open. State the scope read — body, appendix, supplementary, or a stated subset — and never imply fuller coverage than was achieved.
Show full SKILL.md (275 more words)Show less

Paper-type adaptation

Reading emphasis shifts with the paper type. Load ../nature-shared/core/paper-type-taxonomy.md when the type is not obvious:

  • algorithmic — fair-comparison discipline dominates: are baselines tuned as hard as the proposal, and where does it fail?
  • methods — reproducibility dominates: would the protocol work in another lab, and what is left implicit?
  • hypothesis — the strength of the causal evidence dominates: does the evidence rule out the alternative explanation?
  • research — what was found, and how far the observation generalizes beyond the studied system.
  • review — how the field is organized, where sources disagree, and what remains open.

Boundaries

  • Reading sets no verdict. This skill reports what the paper does and how far its evidence reaches. It does not score, rank, or judge acceptance readiness, novelty, or significance — that is nature-reviewer.
  • It does not extract reusable writing patterns from a paper — that is nature-writing and its exemplar material.
  • It does not translate a paper or produce a bilingual reader — that is nature-reader.
  • It does not search the literature, verify citations, or cite sources on the paper's behalf — those are nature-academic-search, nature-citation, and nature-ref-verifier.
  • It does not draft manuscript prose. Use the reading as input to nature-writing when writing related work or positioning.

Output discipline

  • Write in the language the user is using. A Chinese request produces Chinese prose with English technical terms preserved exactly.
  • Quote the source only where an anchor requires it; do not reproduce the paper at length.
  • Formulas use $...$ inline and $$...$$ on their own line. Never place a formula in backticks or a code block.
  • A long paper is not a reason to degrade the output into a summary. If the reading is incomplete, say where it stopped.

© Yuan1z0825, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (references) in skills/nature-paper-xray of Yuan1z0825/nature-skills.

  • SKILL.md
  • README.md
  • README_EN.md
  • agents/openai.yaml
  • manifest.yaml
  • references/deep-reading-protocol.md
  • references/evidence-boundary.md

Open the folder on GitHubat commit e605b35

Compare with similar skills

Nature Paper Xray next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Nature Paper Xray compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nature Paper Xray this skillYuan1z0825/nature-skills47k—~1.5kAutomated safety check: PassApache-2.0
NSFC Abstract Writerhuangwb8/ChineseResearchLaTeX2.9k1 repos~1.3kAutomated safety check: PassMIT
Tooluniverse Gwas Drug Discoverywu-yc/LabClaw1.1k2 repos~4.7kAutomated safety check: PassNone
Alego Docsingula-ai/alego1091 repos~4.5kAutomated safety check: PassMIT
SetupZimoLiao/scholaraio577—~1.7kAutomated safety check: NotesMIT
Tone Adjusteraipoch/medical-research-skills1.9k—~2.3kAutomated safety check: PassMIT

Similar skills

  • NSFC Abstract Writer

    huangwb8/ChineseResearchLaTeX

    Writes Chinese and English abstracts for NSFC grant applications, with a recommended title and five alternatives, within set character limits.

    2.9k GitHub starsUsed in 1 repo~1.3k tokens
    Research & ScienceAuto-check passed

  • Tooluniverse Gwas Drug Discovery

    wu-yc/LabClaw

    Transform GWAS signals into actionable drug targets and repurposing opportunities.

    1.1k GitHub starsUsed in 2 repos~4.7k tokens
    Research & ScienceAuto-check passed

  • Alego Doc

    singula-ai/alego

    Create, restructure, review, audit, or migrate Alego Markdown documentation, package READMEs, and the documentation website using audience-first hierarchy, kind-mapped YAML metadata, bilingual line…

    109 GitHub starsUsed in 1 repo~4.5k tokens
    Research & ScienceAuto-check passed

  • Setup

    ZimoLiao/scholaraio

    A skill your agent uses when the user wants to install, configure, diagnose, or troubleshoot ScholarAIO, including setup check, dependency status, API keys, and bilingual setup flow.

    577 GitHub stars~1.7k tokensUpdated 16 days ago
    Research & ScienceAuto-check: notes

  • Tone Adjuster

    aipoch/medical-research-skills

    A skill your agent uses when converting medical text between academic and patient-friendly tones, translating medical jargon for patients, adapting research papers for public audiences, or rewriting…

    1.9k GitHub stars~2.3k tokensUpdated 24 days ago
    Research & ScienceAuto-check passed

  • Bio Workflows Metabolic Modeling Pipeline

    GPTomics/bioSkills

    Orchestrates genome-scale metabolic modeling from a protein FASTA to flux predictions, chaining CarveMe/gapseq reconstruction, memote QC, gap-filling, media-constrained FBA/FVA, gene essentiality…

    1.2k GitHub starsUsed in 1 repo~5.2k tokens
    Research & ScienceAuto-check passed

More from Yuan1z0825/nature-skills

All 23 skills in this repo

  • Nature Paper Card

    Yuan1z0825/nature-skills

    Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.

    47k GitHub starsUsed in 2 repos~2.1k tokens
    Auto-check passed

  • Nature-Style Scientific Figures

    Yuan1z0825/nature-skills

    Creates, revises, audits and exports manuscript-ready scientific figures in Python or R, and routes AI-generated graphical abstracts to a separate workflow.

    47k GitHub stars~3.1k tokensUpdated today
    Auto-check passed

  • Paper to Chinese Patent Drafter

    Yuan1z0825/nature-skills

    Drafts Chinese invention patent applications and technical disclosures from research papers or inventor materials, tying each claim feature to source evidence.

    47k GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed

  • Researchwrite Proposal Pipeline

    Yuan1z0825/nature-skills

    Composes, revises or audits research proposals and opening reports through an evidence-first state machine with argument maps, section contracts and dynamic expert reviewers.

    47k GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed

  • Nature Literature Downloader

    Yuan1z0825/nature-skills

    Routes literature requests to lawful full-text sources: open access, publisher APIs, CNKI and institutional browser access, with a supporting-information gate.

    47k GitHub starsUsed in 2 repos~6k tokens
    Auto-check passed

  • Image to Editable PPTX

    Yuan1z0825/nature-skills

    Rebuilds slide images, screenshots, scanned PDFs or image-only PPTX files as PowerPoint with editable objects, using a local CLI with per-page manifests and QA.

    47k GitHub stars~2.5k tokensUpdated today
    Auto-check passed

Categories

Questions about Nature Paper Xray

What does Nature Paper Xray do?

Read one supplied paper closely enough to reconstruct how its authors actually got there, rather than restating what the abstract claims. Nature Paper Xray is an agent skill from Yuan1z0825/nature-skills. Read one supplied paper closely enough to reconstruct how its authors actually got there, rather than restating what the abstract claims.

When should I use Nature Paper Xray?

Nature Paper Xray fits situations like: deep single-paper comprehension before building on; citing that paper.

How do I install Nature Paper Xray in Claude Code?

Run `npx skills add Yuan1z0825/nature-skills --skill nature-paper-xray -a claude-code`. Or copy the skill folder (skills/nature-paper-xray in Yuan1z0825/nature-skills) into .claude/skills/nature-paper-xray in your project. Claude Code loads it when a task matches its description.

How do I install Nature Paper Xray in Codex?

Run `npx skills add Yuan1z0825/nature-skills --skill nature-paper-xray -a codex`. Or copy the skill folder (skills/nature-paper-xray in Yuan1z0825/nature-skills) into .agents/skills/nature-paper-xray in your project. Codex loads it when a task matches its description.

Can I use Nature Paper Xray in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Yuan1z0825/nature-skills --skill nature-paper-xray -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nature-paper-xray, .gemini/skills/nature-paper-xray, .github/skills/nature-paper-xray and .opencode/skills/nature-paper-xray in your project.

What does Nature Paper Xray need to run?

SKILL.md names no scripts, command-line tools or credentials: Nature Paper Xray is instructions for the agent only.

Does Nature Paper Xray access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Nature Paper Xray safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Nature Paper Xray use?

Nature Paper Xray is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Nature Paper Xray use?

About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.7k tokens, read only when the agent opens those files.

What are the alternatives to Nature Paper Xray?

Skills that share tags, products or a category with Nature Paper Xray: NSFC Abstract Writer (huangwb8/ChineseResearchLaTeX, 2.9k stars), Tooluniverse Gwas Drug Discovery (wu-yc/LabClaw, 1.1k stars), Alego Doc (singula-ai/alego, 109 stars) and Setup (ZimoLiao/scholaraio, 577 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nature Paper Xray?

Yuan1z0825 (a GitHub user) maintains it in Yuan1z0825/nature-skills, which has 47,222 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 11, 2026.

Source: Yuan1z0825/nature-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.