Nature Skills is a collection of reusable skills that help AI agents handle academic writing and scientific visualization. Researchers and AI-assisted scholars use it to turn research tasks into repeatable workflows and usable outputs. The catalogue entries are skills from this collection.
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 Yuan1z0825/nature-skills --skill nature-polishinggit clone --depth 1 https://github.com/Yuan1z0825/nature-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/yuan1z0825/nature-skills/nature-polishing)<a href="https://agentmods.dev/skills/yuan1z0825/nature-skills/nature-polishing"><img src="https://agentmods.dev/badge/skills/yuan1z0825/nature-skills/nature-polishing/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/yuan1z0825/nature-skills/nature-polishing"><img src="https://agentmods.dev/badge/skills/yuan1z0825/nature-skills/nature-polishing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Anti-Refusal · line 105 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00065 | $0.01265 |
| Opus 5.5 | $0.00026 | $0.00506 |
| Sonnet 5.5 | $0.00013 | $0.00253 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade A, and why
nature-polishing 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 1mo 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nature-Style Academic Polishing — Router
Routing protocol
For a new polishing task, follow the routing below. For follow-up edits, reuse established task choices and already loaded guidance; read additional fragments only when the requested scope changes.
1. Load the manifest and the core layer
Read manifest.yaml. It declares the axes (paper_type, section, language, journal), the allowed values, and the file paths each value maps to.
Also read every file listed under always_load. These hold the default stance, failure-mode diagnosis, ethics, and output format that apply to every polish job.
2. Detect the axis values for this request
For each axis in the manifest, decide the value using the manifest's detect: hint and the user's input:
paper_type— research / methods / hypothesis / algorithmic / review. Default: research.section— abstract / intro / results / discussion / conclusion / title / methods. May be multiple. Ask the user if it is ambiguous and matters for the polish.language— en or zh-to-en. Detect from the draft itself.journal— nature / nat-comms / nat-mach-intell / generic. Default: generic. Usenatureonly for flagship Nature,nat-commsfor Nature Communications andnat-mach-intellfor Nature Machine Intelligence (NMI). Do not route another Nature Portfolio title through flagship Nature rules.
State the detected axis values in one short line to the user before proceeding, so they can correct you cheaply. This is a progress update, not an approval gate; continue unless a necessary decision remains unresolved.
3. Load the matching fragments
For each axis value, Read the file mapped in the manifest. Skip the section axis only if the user has supplied free-floating prose with no section context.
Do not read every fragment in static/. Load only what step 2 selected.
4. Polish using the loaded material
Apply the loaded fragments in this priority order, matching the paper type -> section job -> paragraph logic -> claim/evidence/boundary -> sentence polish rule from core/failure-modes.md:
What ships with it
32 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.
- agents/openai.yaml 263 B
- manifest.yaml 6.4 KB
- README_EN.md 4.2 KB
- README.md 3.6 KB
- references/latex-layout.md 10 KB
- references/nat-comms-2025-diction.md 3.9 KB
- references/phrasebank-playbook.md 4.1 KB
- references/published-article-patterns.md 4.6 KB
- references/section-moves.md 5.9 KB
- references/style-guardrails.md 2.6 KB
- references/writing-strategy.md 4.7 KB
- static/core/failure-modes.md 1.3 KB
- static/core/output-format.md 840 B
- static/core/stance.md 1.6 KB
- static/fragments/journal/generic.md 1022 B
- static/fragments/journal/nat-comms.md 2.4 KB
- static/fragments/journal/nat-mach-intell.md 4.6 KB
- static/fragments/journal/nature.md 1.2 KB
- static/fragments/language/en.md 1.2 KB
- static/fragments/language/zh-to-en.md 1.2 KB
- static/fragments/paper_type/algorithmic.md 953 B
- static/fragments/paper_type/hypothesis.md 765 B
- static/fragments/paper_type/methods.md 806 B
- static/fragments/paper_type/research.md 785 B
- static/fragments/paper_type/review.md 994 B
- static/fragments/section/abstract.md 1.1 KB
- static/fragments/section/conclusion.md 512 B
- static/fragments/section/discussion.md 1.7 KB
- static/fragments/section/intro.md 1.3 KB
- static/fragments/section/methods.md 815 B
- static/fragments/section/results.md 2.7 KB
- static/fragments/section/title.md 645 B
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.
- 1mo ago Changed · -13 lines · -127 tokens per session 9391b2a24873
- 1mo ago Changed c8ff9503a8d3
- 1mo ago First seen · 112 lines · 192 tokens per session scan A f4c08a7b27b1
nature-polishing is a skill published in the GitHub repository Yuan1z0825/nature-skills (50,803 stars, last pushed 2d ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,265 once invoked, about $0.0003 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
literature-searcher
Search CrossRef, OpenAlex, PubMed, Semantic Scholar, and optional Scopus; deduplicate results, download open-access PDFs by DOI, classify papers, monitor new results, and analyze coverage. Use when asked to search literature, monitor a topic, download an open-access paper, classify papers, or analyze literature gaps.
matlab-orchestrator
MATLAB agentic workflow router. Use this whenever the user asks for MATLAB, Simulink, .m/.mlx/.slx work, toolbox-driven engineering, paper reproduction, simulation, code generation, data analysis, control, robotics, signal/image/AI workflows, or wants an end-to-end automated MATLAB task with validation. For Simulink…
matlab-runner
Run MATLAB tasks from Codex with reliable MCP-based execution, logs, artifacts, toolbox inventory, smoke tests, and reproducible validation. Use whenever MATLAB code, .m/.mlx scripts, MATLAB tests, local toolbox probing, or command-line automation is needed.
matlab-simulink-modeling
MATLAB and Simulink workflow for creating, inspecting, modifying, simulating, validating, and exporting .slx models. Use for Simulink, Stateflow, Simscape, model-based design, parameter sweeps, signal logging, requirements, and simulation automation. On this machine, Simulink tasks should be visual-first: open the…
manim-animator
Create code-driven explanatory animations and precise vector graphics with Manim, optionally using SandBase for generated images, narration, music, or transcription. Use for mathematical, scientific, algorithmic, or diagrammatic animation; use a video-generation workflow for photoreal footage.
matlab-robotics-autonomy
MATLAB robotics and autonomy workflow for ROS Toolbox, Robotics System Toolbox, Navigation Toolbox, UAV Toolbox, sensor fusion, trajectory planning, simulation, and reproducible robot experiments. Use for ROS/ROS 2 bags, robot models, path planning, SLAM, state estimation, and autonomy prototyping.