nature-polishing
Skill14 starsChanged 5 months agoApache-2.0View on GitHub
Polish, restructure, or translate academic prose into Nature-leaning English using writing-strategy principles, curated Nature/Nature Communications article patterns, and phrase-level support from Academic Phrasebank. Use whenever the user asks to polish a manuscript paragraph, abstract, introduction, results, discussion, conclusion, title, methods section, or Chinese academic draft for publication-quality English. Also covers LaTeX layout/typesetting (排版) fixes — loose or sparse pages, stranded section headings, figures that don't fill the page or split across pages, "Float too large", multi-panel figure arrangement, and Supplementary Information that looks empty — via references/latex-layout.md. Also trigger on general academic/scientific writing requests even without the word "Nature", including academic writing, scientific writing, SCI/paper writing, English manuscript polishing, language editing, proofreading, and Chinese phrasings such as 学术写作、科研写作、论文润色、写paper、SCI写作、英文论文润色、语言润色、润色、改写、学术英语、英文写作.
13 other projects use a version of this, 4 of them edited.
Adopted by
Most recently taken up by
- denghuipan/nature-portfolio-skillsword for word, first seen Nov 15, 2026
- dragonadam/nature-skillsedited, first seen Oct 25, 2026
- Luooops/skillsedited, first seen Oct 13, 2026
- zhaoy2020/Skillsword for word, first seen Sep 16, 2026
- szzjayson25-hub/nature-academic-skillsedited, first seen Sep 12, 2026
- Yuan1z0825/nature-skillsedited, first seen Aug 31, 2026
Used with
Projects with it also use nature-experiment-log, nature-downloader and 3 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Delagong950Skillnature-experiment-log
Standardized lab notebook with structured YAML-frontmatter experiment logs. Supports Obsidian vault integration, image/voice/text input, and batch/tracking systems.
Also in 5 projects that use this
vcis-wangchenxuSkillnature-downloader
Help legally obtain, organize, and archive academic papers, PDFs, BibTeX, supplementary files, code links, and benchmark documents for RL, MARL, LLM, and LLM Agent research. Do not bypass paywalls or access controls.
Also in 5 projects that use this
vcis-wangchenxuSkillnature-literature-pipeline
Build a repeatable literature discovery, scoring, reading, and archiving pipeline for RL, MARL, LLM, and LLM Agent research. Use for daily/weekly paper tracking, topic watchlists, benchmark monitoring, and research-note automation.
Also in 4 projects that use this
Delagong950Skillnature-ref-verifier
Multi-source cross-validation of academic references. Verify authors, title, year, volume, issue, and pages against PubMed, CrossRef, and publisher pages. Detect fabricated citations.
Also in 4 projects that use this
Yuan1z0825Skillnature-shared
Internal shared-reference support package for installed Nature Skills, including nature-writing, nature-polishing, nature-response, nature-reader, and nature-paper2ppt. Do not invoke it as a standalone user workflow. Load only the specific core or journal-format file requested by another Nature skill.
Also in 3 projects that use this
Other versions13 projects use a version of this.
Word for word · 4
- denghuipan/nature-portfolio-skills★ 2100% same
- zh123012/claude-skills★ 1100% same
- zhaoy2020/Skills★ 1100% same
- yid83136-design/skill-collection★ 0100% same
Edited · 4
- Yuan1z0825/nature-skills★ 54k48% same
- dragonadam/nature-skills★ 499% same
- Luooops/skills★ 148% same
- szzjayson25-hub/nature-academic-skills★ 031% same
Wrote their own version · 5
- Galaxy-Dawn/claude-scholar★ 5.9ksame name
- Chanw-research/claude-code-paper-writing★ 42same name
- Delagong950/nature-skills★ 4same name
- vcis-wangchenxu/agent_nature-skills★ 4same name
- Lling0000/nature-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- nature-academic-searchSkill
- nature-citationSkill
- nature-dataSkill
- nature-figureSkill
- nature-paper2pptSkill
- nature-paper-to-patentSkill
- nature-readerSkill
- nature-responseSkill
- nature-reviewerSkill
- nature-writingSkill
- openclaw-medical-skillsSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Do not try to apply the polishing logic from memory or from this router.
- Distinctive: line 19
Follow these five steps every time the skill is invoked.
- Very specific: line 23
Read manifest.yaml. It declares the axes (paper_type, section, language, journal), the allowed values, and the file paths each value maps …
- Very specific: line 42
Do not read every fragment in static/.
- Distinctive: line 54
If a paragraph's structural problem cannot be fixed without inventing content, flag it instead of papering over it.
- Distinctive: line 60
Layout/typesetting (排版) requests are different: If the user asks to fix *placement* rather than wording — loose/sparse pages, stranded …
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Nature-Style Academic Polishing — Router
This skill is split into two layers:
- A static layer under
static/that holds versioned, reusable content fragments (core principles, paper-type playbooks, per-section guidance, language-specific rules, per-journal style). - A dynamic layer (this file plus
manifest.yaml) that detects the request's axes and loads only the fragments needed for the current job.
Do not try to apply the polishing logic from memory or from this router. Always load fragments from disk as described below.
Routing protocol
Follow these five steps every time the skill is invoked.
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 / generic. Default: generic. If the user names a Nature subjournal, treat it asnature.
State the detected axis values in one short line to the user before proceeding, so they can correct you cheaply.
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:
- Paper-type playbook (architecture, writing order).
- Section-specific job and failure modes.
- Journal-specific framing and constraints.
- Language-specific sentence and paragraph rules (apply last).
- Core stance and ethics throughout.
If a paragraph's structural problem cannot be fixed without inventing content, flag it instead of papering over it.
5. Reach for references only when needed
The files under references/ are deep references, not defaults. Open them on demand per the references.on_demand table in the manifest, for example when the user explicitly asks for phrasebank-style alternatives or a stricter style audit.
Layout/typesetting (排版) requests are different. If the user asks to fix
placement rather than wording — loose/sparse pages, stranded headings, figures
that don't fill the page or split across pages, "Float too large", multi-panel
arrangement, sparse Supplementary Information — skip the prose axes (paper_type,
section, language, journal) and load references/latex-layout.md directly. That
file is self-contained: it carries the diagnosis workflow (render → contact-sheet →
read the log), the float-glue and [H]/\clearpage/placeins patterns, and the
"regenerate wide figures taller at the source" rule. Always compile and visually
inspect rendered pages before and after — never judge layout from the .tex alone.
Why this split
- The static layer is versioned and reviewable. Adding a new journal style or paper type is one new file plus one manifest line.
- The dynamic layer keeps each invocation cheap: only the fragments relevant to this draft enter context, instead of the full 1000-line monolith.
- The router itself is short on purpose. Update fragments, not this file, when adding scope.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

