Nature-grade scientific figures in Python or R
Create, revise, audit and export submission-ready manuscript figures — matplotlib/seaborn or ggplot2 — plus an explicit AI-schematic route
- What
- Create, revise, audit and export submission-ready manuscript figures — matplotlib/seaborn or ggplot2 — plus an explicit AI-schematic route
- Cost
- Free
- Needs
- Python (matplotlib/seaborn) or R (ggplot2/patchwork/ComplexHeatmap) installed for the plotting route; your own image-generation API key (billed) only if you want the explicit AI-schematic route; scientific figure data of your own
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @yuan1z0825's router for creating, revising, auditing and exporting manuscript scientific figures: a manifest-driven flow that resolves a single plotting backend (Python/matplotlib-seaborn or R/ggplot2-patchwork-ComplexHeatmap — saved as your default), applies a figure contract (core conclusion, evidence chain, archetype, journal/export contract) and a restrained-palette stance, then ships with a rendered QA gate (panel-alignment audit at final physical size, collision audit on every exported PDF, re-inspection after any geometry change) and flagship-Nature or Nature Machine Intelligence production contracts when targeting those journals. A separate explicit route handles AI-generated graphical abstracts and mechanism schematics via an image-generation API, with a policy gate, human scientific review and disclosure/provenance requirements. Honest caveats: figures serve the scientific logic — aesthetics are subordinate to making the core conclusion clear, defensible and reviewable; AI schematics are drafts, never quantitative data panels; the optional AI-schematic route needs an image-generation API key of your own (billed). By @yuan1z0825, listed here with credit to its creator. Apache-2.0 licensed (declared in the source repo). Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Nature Figure is a free Muse skill that creates, revises, audits and exports submission-ready manuscript figures, in Python with matplotlib and seaborn or in R with ggplot2, plus an explicit AI-schematic route. Its manifest-driven flow resolves a single plotting backend, saved as your default, and applies a figure contract covering core conclusion and evidence chain.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 2a20e4aStep 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: Python (matplotlib/seaborn) or R (ggplot2/patchwork/ComplexHeatmap) installed for the plotting route; your own image-generation API key (billed) only if you want the explicit AI-schematic route; scientific figure data of your own Install "Nature-grade scientific figures in Python or R" for me. It teaches an agent @yuan1z0825's nature-figure router: resolve one plotting backend (Python or R, saved as default), apply the figure contract and restrained-palette stance, build multi-panel figures with inferential panel roles, and run the rendered QA gate (panel-alignment and collision audits at final physical size, mandatory re-audit after any change) — plus flagship-Nature or NMI production contracts when targeting those journals, and a separate explicit route for AI-generated graphical abstracts/schematics with policy gate and human scientific review. Apache-2.0 licensed (declared in the source repo). Repository: https://raw.githubusercontent.com/yuan1z0825/nature-skills/2a20e4a0868ef9094257cb5386cfe623454ae092/skills/nature-figure/SKILL.md Pinned version: install the code at commit 2a20e4a0868ef9094257cb5386cfe623454ae092 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "nature-figure". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. answer "Python or R?" once when the agent asks, provide your figure data; the AI-schematic route needs your own image-generation API key). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
- It works with an API key or a token that you provide.
What the scan found — excerpts from the install prompt
- uses API keys or tokens — Prerequisites: Python (matplotlib/seaborn) or R (ggplot2/patchwork/ComplexHeatmap) installed for the plotting
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 2a20e4a · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : uses API keys or tokens
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.