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
- 01Load specific references on demand
- 02Journal-format definitions
- 03Guidance on paper structure and argument
Use cases
- 01A Nature skill needs shared definitions
- 02Writing results, introductions, or abstracts
- 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-sharedAfter installing, type/nature-sharedin Claude Code to confirm it loaded.
Bundled files
References and scripts installed along with SKILL.md.
manifest.yamlREADME_EN.mdREADME.mdagents/openai.yamlcore/consistency-sweep.mddiscussion-argument-language.mdethics.mdmain-text-discipline.mdnature-abstract.mdnature-introduction.mdnature-results-discussion.mdpaper-type-taxonomy.mdreader-workflow.mdresearch-compliance.mdterminology-ledger.mdjournal-formats/nat-comms.mdnature-machine-intelligence.mdnature.mdscripts/check_consistency.pytests/test_check_consistency.pyDetails
From the project READMENature 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/andjournal-formats/as shared definitions, not standalone workflows. - Use
journal-formats/nature.mdonly for the flagship journal Nature andcore/research-compliance.mdonly when its specialist applicability gate is triggered. - Use
journal-formats/nature-machine-intelligence.mdfor 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.mdfor result placement, main-text compression, revision accretion, caption/SI allocation, and claim-repetition checks. - Use
core/nature-results-discussion.mdfor 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.mdfor journal-general Discussion function sequencing, reverse-funnel control, evidence-calibrated modality, claim-specific limitations, and uncertainty-driven future work. - Use
core/nature-introduction.mdfor 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.mdfor 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