nature-shared
Yuan1z0825/nature-skills · Agent Skill
Un pacchetto di supporto per altre skill Nature, che fornisce riferimenti e formati condivisi. Non per uso autonomo.
Vai all'installazione ↓Opzioni di installazione
Il prompt con anteprima è selezionato di default. Puoi passare al comando diretto.
Copia il prompt, incollalo in Claude, Codex o un altro assistente: analizzerà la pagina dello skill e lo installerà.
I'd like to install this Claude Code skill: https://github.com/Yuan1z0825/nature-skills/tree/main/skills/nature-shared Please review the SKILL.md file, verify the skill is legitimate, then copy the skill folder into .claude/skills/ of my project.
Il comando diretto salta la revisione: prima ispeziona il sorgente.
npx skills add https://github.com/Yuan1z0825/nature-skills/tree/main/skills/nature-shared
Leggi SKILL.md e i file correlati prima di installare. Clicca un file per l'anteprima.
Contenuto di SKILL.md
Testo originale dell'autore · sola letturaNature 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 and
core/research-compliance.md only 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.