
Nature Academic Search
A well-architected literature search tool that routes across PubMed, CrossRef, arXiv, Scopus, and ScienceDirect through a clean static/dynamic layer split. It detects which workflow you need (multi-source search, citation verification, MeSH strategy building, citation file conversion, or reference management) and loads only that fragment plus its dependencies. The T1→T2→T3 fallback chain, shared dedup engine, and format converters (nbib/ris/bib) are all on-demand references. If you're doing serious academic writing and need coordinated multi-step workflows instead of one-off API calls, this handles the orchestration. The routing protocol is disciplined: manifest, detect, load, run, with no guessing from memory.
- skills.sh installs
- 16.3K
- GitHub stars
- 52.9K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add yuan1z0825/nature-skills --skill nature-academic-search --agent claude-codeInstalls into .claude/skills of the current project.
Files
Academic Search — Router
Routing protocol
For local citation-file conversion with complete supplied records, load
references/workflows/wf4-citation-file-mgmt.md and its format reference directly.
Source lookup, API setup, and network preflight apply only when retrieval or verification is
needed; do not require them for a requested offline conversion.
For a new task, load the core and matching resources below. Reuse already loaded guidance on follow-ups; load more only when the task needs it.
1. Load the manifest and the core layer
Read manifest.yaml. It declares the workflow axis, the allowed values, and the file paths each value maps to.
Also read every file listed under always_load:
static/core/tools.md— the MCP tool inventory (core search, extended search, PubMed utilities) and the shared-module map.static/core/routing-and-ops.md— the T1→T2→T3 source routing quick guide, environment setup, error handling, and limitations.
2. Detect the workflow
Map the user's need to one or more workflow values:
Sponsors
Details
- Repository
- github.com/yuan1z0825/nature-skills
- Categories
- AI & Agent Building, Data Science & ML, Debugging, Marketing & SEO
- First seen
- Jun 3, 2026