agentleFS
szzjayson25-hubszzjayson25-hub/nature-academic-skills/nature-writing/SKILL.md

nature-writing

Skill0 starsChanged 2 months agoMITView on GitHub

Write or complete scientific manuscript sections from attached drafts, papers, notes, or project files; infer the target journal and retrieve available evidence to produce readable prose with verification markers for unresolved claims. Use for 完成写作、根据这个文件写、根据项目内容写论文、补全引言、填补占位符, manuscript drafting, restructuring, outlines, Results evidence allocation, and initial-submission materials. Requests to explain or review a file alone do not authorize rewriting it. Supports Nature and configured journal routes.

10 other projects use a version of this, 6 of them edited.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. 0 are common, 7 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not try to apply the drafting logic from memory or from this router.

    line 20
  2. Distinctive:

    Do not infer permission to rewrite from a file attachment alone or a question about its contents.

    line 30
  3. Very specific:

    Read static/core/evidence-completion.md through always_load.

    line 34
  4. Distinctive:

    Follow these five steps every time the skill is invoked.

    line 43
  5. Very specific:

    Read manifest.yaml. It declares the axes (task, paper_type, section, language, journal), the allowed values, and the file paths each value …

    line 47
  6. Very specific:

    Use the manifest’s aliases and applicability rules.

    line 60
  7. Very specific:

    Look up journal_sections[journal] in the manifest.

    line 80
  8. Very specific:

    If applicable and the section has a mapping, read that mapped file instead of the default axes.section.values fragment and its generic deep …

    line 83
  9. Distinctive:

    If absent or inapplicable, use the original section fragment and on-demand references.

    line 87
  10. Distinctive:

    Do not require separate Related Work or Discussion headings to use their logic.

    line 92
  11. Very specific:

    Do not read every fragment in static/.

    line 110
  12. Very specific:

    When drafting or restructuring Results, or compressing a full manuscript's main text, also load …

    line 125
  13. Distinctive:

    When the target is flagship Nature, Nature Communications, Nature Machine Intelligence, or another Nature Portfolio title, load the …

    line 132
  14. Distinctive:

    Use these files for claim escalation, question-chain alignment, discovery-centred compression, and synthesis.

    line 142

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Nature-Style Scientific Writing — Router

This skill is split into two layers:

  • A static layer under static/ that holds versioned, reusable content fragments (core stance + workflow, paper-type playbooks, per-section drafting guidance, initial-submission 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 drafting logic from memory or from this router. Always load fragments from disk as described below.

Completion intent and scope

A manuscript file plus “完成写作 / 帮我写完 / 根据这个文件写”, a project plus “根据项目内容写作”, or a request to fill manuscript placeholders invokes complete-draft behavior without a special command. Infer scope from the request, active conversation and document headings; a named section stays that section. A multi-section draft may be completed within its existing scope; a project-only request for a paper supports a full manuscript where evidence permits. Do not infer permission to rewrite from a file attachment alone or a question about its contents. Explicit outline-only, routing-test, review-only, translation, language, and staged-approval requests keep their narrower scope.

Read static/core/evidence-completion.md through always_load. It defines project discovery, evidence retrieval and first-pass completion for all journals. For manuscript work it governs missing-input handling and whether clarification is needed when older section examples say “ask”, “confirm”, or “fill [X]”. Those examples are planning aids, not author fill-in forms. Preserve scientific evidence constraints; a marker never makes an invented fact acceptable.

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 (task, 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, writing workflow, and output format that apply to every drafting 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:

  • task — manuscript / submission-package. Use submission-package for first-submission materials, never for revision correspondence.
  • paper_type — research / methods / hypothesis / algorithmic / review. Default: research.
  • section — abstract / intro / related-work / method / experiments / discussion / conclusion / title. May be multiple. Infer from the supplied material first; use the completion workflow for unresolved scope.
  • language — en or zh-to-en. Detect from the user's notes themselves.
  • journal — asc / eaai / isa / kbs / neurocomputing / measurement / ieee-trel / eswa / nature / nature-family / nat-comms / nat-mach-intell / generic. Use the manifest’s aliases and applicability rules; default to generic. Match named journal targets rather than general topic words. Nature means the flagship journal; use each configured subjournal’s own key.

State the detected axis values in one short line to the user before drafting, so they can correct you cheaply.

For Expert Systems with Applications (ESWA, Expert Syst. Appl.), use journal=eswa and read static/fragments/journal/eswa.md. Its shared ESWA contract overrides incompatible Nature-specific journal defaults; retain the normal scientific workflow and evidence safeguards. For layout jobs that skip prose axes, read ../nature-shared/journal-formats/eswa.md directly when ESWA submission requirements affect the layout.

3. Load the matching fragments

For every axis except section, read the file mapped in the manifest. Skip section routing for task=submission-package or free-floating prose without a section context.

Resolve each requested section before loading its guidance:

  1. Look up journal_sections[journal] in the manifest. If present, read its profile and check the stated manuscript/domain applicability. Do not assume a journal match alone makes a narrow corpus applicable.
  2. If applicable and the section has a mapping, read that mapped file instead of the default axes.section.values fragment and its generic deep section reference (for example references/introduction.md). The mapped file contains both the section plan and detailed journal-specific writing/revision logic.
  3. If absent or inapplicable, use the original section fragment and on-demand references. Keep the recognized journal and its submission requirements; do not substitute another journal's profile.
  4. For multiple sections, resolve each separately. For a full manuscript, first identify the actual sections/functions, then read the relevant mapped guides. Do not require separate Related Work or Discussion headings to use their logic.

Paths in the manifest are relative to this skill directory; links inside a reference are relative to that reference. Journal adaptations live beside their original counterparts with a -<journal>.md suffix and a matching -<journal>-zh.md Chinese version. Writing owns the shared chapter content; polishing points to those exact files instead of maintaining a second copy. When a mapped guide requests a finer template, follow its matching journal-specific links. English is the default reference language; do not load both languages unless comparison is requested. No files are discovered merely by being placed in a folder. Apply this resolved section choice to later instructions in core workflows, task fragments, or reference tables as well. With an active override, do not additionally load the default deep section guide or Nature-only corpus/style examples; load general examples only when requested or needed and compatible with the selected guide. Preserve shared evidence/ethics constraints, terminology, paper-type guidance, language rules, and the original output format. The selected guide controls section organization where defaults differ; the current journal contract controls official requirements, never the corpus.

Do not read every fragment in static/. Load only what step 2 selected.

4. Draft using the loaded material

Apply the loaded fragments in this priority order:

  1. Core stance + evidence completion (static/core/stance.md, static/core/evidence-completion.md) — retrieve claim, evidence and boundary from the supplied materials before drafting.
  2. Paper-type playbook — argument chain, drafting order.
  3. Resolved section-specific drafting rules and structure from step 3.
  4. Task-specific submission rules when task=submission-package.
  5. Journal-specific framing and constraints.
  6. Language-specific sentence and paragraph rules (apply last).

For task=manuscript, run static/core/workflow.md end-to-end. Plan internally and deliver prose in the same task; do not turn ordinary completion requests into outline-approval rounds.

When drafting or restructuring Results, or compressing a full manuscript's main text, also load ../nature-shared/core/main-text-discipline.md before building the paragraph map. Classify every result by function, allocate it across main text, captions, Methods/source data, and SI, then draft the shortest sufficient evidence chain. Do not equate a complete analysis record with a complete main text.

When the target is flagship Nature, Nature Communications, Nature Machine Intelligence, or another Nature Portfolio title, load the matching shared Nature-style corpus guidance for the section being drafted:

  • Results or Discussion → ../nature-shared/core/nature-results-discussion.md
  • Introduction or whole-manuscript narrative → ../nature-shared/core/nature-introduction.md
  • Abstract → ../nature-shared/core/nature-abstract.md

Use these files for claim escalation, question-chain alignment, discovery-centred compression, and synthesis. They were initially distilled from published NMI papers and generalized as Nature-style defaults; do not present them as official policy, and let the target journal's current rules override them.

For any Discussion drafting, restructuring, or section audit, also load ../nature-shared/core/discussion-argument-language.md. Use it to select the opening anchor, control the reverse-funnel expansion, distinguish literature positioning from citation decoration, calibrate modal strength to evidence, and turn limitations and future work into claim-specific reasoning. This is general writing guidance rather than an official journal rule.

For task=submission-package, follow static/fragments/task/submission-package.md and references/submission-package.md instead. Build the deliverable matrix and readiness audit; do not force manuscript paragraph architecture onto administrative submission materials.

For missing manuscript evidence, follow static/core/evidence-completion.md: retrieve, narrow or omit unsupported claims, and return prose with verification notes rather than fill-in blanks. Administrative submission fields retain the submission-package workflow.

5. Reach for references only when needed

The files under references/ are deep references and the example library, not defaults. Open them on demand per the references.on_demand table in the manifest. Typical triggers:

  • The user asks for a concrete example or template → references/examples/index.md.
  • A section's draft has structural problems that the section fragment alone does not explain → the matching references/<section>.md.
  • The user needs a broad-audience Nature abstract opening or asks about a summary paragraph → references/nature-summary-paragraph.md.
  • The user asks "does this paragraph flow?" → references/paragraph-flow.md.
  • The user asks for a self-review or rejection-risk audit → references/paper-review.md.
  • The user asks what belongs in the main text, captions, or SI; wants a shorter Results section; or is adding reviewer-driven explanation → ../nature-shared/core/main-text-discipline.md.
  • The user requests a complete first-submission package, templates, or a submission-readiness audit → references/submission-package.md.
  • The target is the flagship journal Nature and exact submission or formatting requirements matter → ../nature-shared/journal-formats/nature.md.
  • The target is Nature Machine Intelligence and exact content-type, submission, data/code or production requirements matter → ../nature-shared/journal-formats/nature-machine-intelligence.md.
  • Any Nature / Nature Portfolio target needs Results claim progression, evidence-bound interpretation, robustness placement, or Discussion synthesis → ../nature-shared/core/nature-results-discussion.md.
  • Any target needs a Discussion function chain, evidence-calibrated modal language, claim-specific limitations, non-redundant literature positioning, or uncertainty-driven future work → ../nature-shared/core/discussion-argument-language.md.
  • Any Nature / Nature Portfolio target needs an Introduction funnel, exact gap, literature logic, question-first novelty, study roadmap, or alignment with Results → ../nature-shared/core/nature-introduction.md.
  • Any Nature / Nature Portfolio target needs abstract evidence-chain, main/supporting-claim, numeric-result, or final-payoff decisions → ../nature-shared/core/nature-abstract.md.
  • The work involves regulated or specialist research compliance → ../nature-shared/core/research-compliance.md.

Submission boundary

  • nature-writing owns initial submission materials prepared before peer review.
  • nature-response owns revision cover letters, rebuttals, point-by-point responses, marked manuscripts, appeals, and other post-decision correspondence.
  • Route graphical abstracts and TOC graphics to nature-figure; route simulated pre-submission peer review to nature-reviewer.

Why this split

  • The static layer is versioned and reviewable. Register journal aliases and the journal fragment in the manifest. For journal-specific chapter logic, additionally register a profile and section paths under journal_sections; no further router change is needed for the next journal.
  • The dynamic layer keeps each invocation cheap: only the fragments relevant to this draft enter context, instead of the full multi-thousand-line reference set.
  • The router itself is short on purpose. Update fragments, not this file, when adding scope.
  • This structure mirrors nature-polishing so shared content can later be lifted into a nature-shared/ layer used by both skills.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.