01
It starts by itself
before manuscript submission. Runs in Claude Code routine.
- ↻ before manuscript submission
manual run per manuscript revision
yuan1z0825 · 15K installsNature Data skill
Runs by itself, before manuscript submission.
Every dataset has an access route.
Install the Nature Data skill and make it a habit: follow https://gethabit.dev/skills/yuan1z0825/nature-data.md
- 1Copy
- 2Paste into Claude Code, Codex or Cursor
- 3It runs by itself
15K installs50K starsApache-2.0 licenceSource on GitHub ↗
Nature Data
by yuan1z0825 · 15K installs
The skill
The nature data skill drafts and audits Data and Code Availability statements, dataset access routes, repository plans and FAIR metadata, for researchers preparing a manuscript for journal submission.
Only when you ask.
The habit
Every dataset has an access route.
↻ Runs by itselfbefore manuscript submission
How the habit works.
You don't have to.
When does it start? How does it check its work? What does it remember?
One run, step by step.
Then it stops.
Stops after one manuscript per run, with no more than 2 redraft rounds.
- 01
Load the core
The agent reads manifest.yaml, then static/core/stance.md and static/core/workflow.md.
- 02
Identify the journal
It names the journal and article type, and journal rules win where they differ.
- 03
List datasets
It makes an inventory of every dataset that supports the paper.
- 04
Classify routes
Each dataset gets one route, such as public repository, controlled access or within paper.
- 05
Plan repositories
It picks the repository and identifier strategy before any drafting.
- 06
Draft and cite
It writes the statement with a dataset-to-location map and formal dataset citations.
- 07
Run the FAIR audit
It checks metadata with references/fair-metadata-checklist.md and returns paste-ready text plus open fields.
What it may do.
Nothing more.
It writes only in its own folder and asks you before anything goes out.
- Writes only inloops/data-availability-audit-loop/**
- Talks tono outside service
- Sendsnothing
- Your OKNothing goes out, so it needs no OK.
Is it for you?
Use it when it fits.
Read both lists. If the left one sounds like you, the Nature Data skill helps.
Use it when
- ✓ Drafting a Data Availability statement
- ✓ Choosing a repository and identifiers
- ✓ Auditing a statement before submission
Skip it when
- – General data cleaning
- – Statistical analysis
Nature Data skill, answered.
Will it make up identifiers?
No. Missing DOIs, accession numbers or embargo dates stay as open fields for the author.
Does it work for Chinese authors?
Yes. When the author writes Chinese, it reads static/core/chinese-mode.md and adds the 中文核对 block.
What changes for Nature Machine Intelligence?
It also checks a separate Code availability section, reviewer access and the Software Submission Checklist for new central code.
How do I install the Nature Data skill?
Copy the prompt at the top into your agent. It installs the skill from yuan1z0825/nature-skills and sets up the habit. Or run npx skills add yuan1z0825/nature-skills --skill nature-data.
Is the Nature Data skill free?
Yes. It is published under Apache-2.0. Habit is free too.
Nature Data. Now as a habit.
Install the Nature Data skill and make it a habit: follow https://gethabit.dev/skills/yuan1z0825/nature-data.md
All yuan1z0825 skills →More docs skills →
Works in
- Claude Code
- Codex
- Cursor
- ChatGPT
- Claude app
Made by yuan1z0825, published under Apache-2.0. Habit links to the original and never changes it. Is this your skill?