mcpField
N
nature-shared

nature-shared

github.com/yuan1z0825Documents51.2k13.5k installsUpdated 1d ago
Repository

About nature-shared

nature-shared is a reference package loaded by other installed Nature skills. It provides journal-format definitions and writing guidance, while the requesting skill supplies the workflow and output requirements.

Key features

  1. 01Load specific references on demand
  2. 02Journal-format definitions
  3. 03Guidance on paper structure and argument

Use cases

  1. 01A Nature skill needs shared definitions
  2. 02Writing results, introductions, or abstracts
  3. 03Organizing discussion and main-text content

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/yuan1z0825/nature-skills --skill nature-shared

After installing, type/nature-sharedin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

manifest.yaml
README_EN.md
README.md
agents/
openai.yaml
core/
consistency-sweep.md
discussion-argument-language.md
ethics.md
main-text-discipline.md
nature-abstract.md
nature-introduction.md
nature-results-discussion.md
paper-type-taxonomy.md
reader-workflow.md
research-compliance.md
terminology-ledger.md
journal-formats/
nat-comms.md
nature-machine-intelligence.md
nature.md
scripts/
check_consistency.py
tests/
test_check_consistency.py

Details

From the project README

Nature Shared References

Use this package only as a dependency of another installed Nature skill.

  • Load the exact referenced file; do not preload the whole package.
  • Treat core/ and journal-formats/ as shared definitions, not standalone workflows.
  • Use journal-formats/nature.md only for the flagship journal Nature and core/research-compliance.md only when its specialist applicability gate is triggered.
  • Use journal-formats/nature-machine-intelligence.md for exact NMI article types, limits, initial-submission files, data/code duties and production requirements; do not import flagship Nature or Nature Communications limits.
  • Use core/main-text-discipline.md for result placement, main-text compression, revision accretion, caption/SI allocation, and claim-repetition checks.
  • Use core/nature-results-discussion.md for corpus-derived Nature-style Results claim escalation, evidence-bound local interpretation, and Discussion synthesis; do not present it as official journal policy.
  • Use core/discussion-argument-language.md for journal-general Discussion function sequencing, reverse-funnel control, evidence-calibrated modality, claim-specific limitations, and uncertainty-driven future work.
  • Use core/nature-introduction.md for corpus-derived Nature-style problem funnels, exact knowledge gaps, literature tension, question-first novelty, and Introduction–Results alignment; do not present it as official journal policy.
  • Use core/nature-abstract.md for corpus-derived Nature-style discovery-centred abstract compression, claim hierarchy, selective numeric support, and field-level payoff; do not present it as official journal policy.
  • Return to the requesting skill for task logic, output format, and final QA.

Comments

Markdown supported