nature-paper-xray

Yuan1z0825/nature-skillsScience & research

nature-paper-xray is a skill in Yuan1z0825/nature-skills, last changed 6 Oct 2026. It is instructions only: no scripts, no named hosts and no pre-approved tools.

From the author
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.

At a glance

What it can touch

  • Instructions only

It is instructions only: no scripts, no named hosts and no pre-approved tools.

How much a skill can do, not whether it is risky.

Pattern check

Nothing flagged

That isn't proof the skill is harmless.

Commit 69817e4 · 3 Nov 2026

How the check works

Pattern check: nothing flagged

That isn't proof the skill is harmless.

Install

Each tab says whether it installs commit 69817e4, the one we checked, or the latest version.

Read SKILL.md first
Apache 2.0
Licence
52.0k
Repo stars
Publisher
Files

What it can touch

From the files and frontmatter at commit 69817e4. This is how much a skill can do, not whether it is risky.

Instructions only

It is instructions only: no scripts, no named hosts and no pre-approved tools.

Pattern check

Pattern check: nothing flagged · commit 69817e4 · 3 Nov 2026

We checked every text file in this skill, at commit 69817e4 on 3 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specPasses

    The open format from agentskills.io, held to the strictest version of each rule among the agents we check.

    • Note

      There is no license field, so readers can't tell whether they may reuse the skill. O2

      Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.

    • Note

      Reference files that SKILL.md doesn't link: README_EN.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

  • Claude CodePasses

    Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

    • Note

      Reference files that SKILL.md doesn't link: README_EN.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

  • Claude apps & API uploadPasses

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Note

      The description is 734 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

      Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

    • Note

      Reference files that SKILL.md doesn't link: README_EN.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

  • OpenAI (Codex & API)Passes
  • VS Code & CopilotPasses

SKILL.md

Files

More from Yuan1z0825/nature-skills

SkillWhat it can touchPattern checkLicenceUpdated
  • Touches credentials
  • Runs shell commands
  • +3 more
Pattern check: Nothing flaggedApache 2.01 Nov 2026
  • Runs shell commands
  • Reaches the network
  • +2 more
Pattern check: Nothing flaggedApache 2.01 Nov 2026
  • Names web addresses
Pattern check: Nothing flaggedApache 2.013 Sept 2026
  • Touches credentials
  • Runs shell commands
  • +3 more
Pattern check: Nothing flaggedMIT19 Oct 2026
  • Runs shell commands
  • Reaches the network
  • +3 more
Pattern check: 3 items to reviewApache 2.01 Nov 2026
  • Runs shell commands
  • Reaches the network
  • +2 more
Pattern check: Nothing flaggedMIT19 Oct 2026
All skills in Yuan1z0825/nature-skills

Other Science & research skills

Same category, most repo stars first.

SkillWhat it can touchPattern checkLicenceUpdated
  • Instructions only
Pattern check: Nothing flaggedMIT27 Sept 2026
  • Instructions only
Pattern check: Nothing flaggedMIT11 Aug 2026
  • Instructions only
Pattern check: Nothing flaggedApache 2.018 Aug 2026
  • Names web addresses
Pattern check: Nothing flaggedApache 2.018 Aug 2026
  • Runs shell commands
Pattern check: Nothing flaggedApache 2.03 Nov 2026
security-research

code-yeongyu/oh-my-openagent

  • Names web addresses

Pattern check: Nothing flaggedNo licenceUpdated 31 Aug 2026

  • Names web addresses
Pattern check: Nothing flaggedNo licence31 Aug 2026

Repo facts from GitHub on 3 Nov 2026. Files read at commit 69817e4.

QAI did not write these skills and is not affiliated with their authors unless a page says so. Logos and icons belong to their owners and are not a mark of approval. How we check