Search academic literature across sources, verify references, and convert citation files. Build PubMed queries using MeSH, its subject vocabulary, or audit citations to distinguish independent citations and document who cited a paper and how.
Search literature across sources, verify or manage citations, and build MeSH strategies or citation-impact audits. Use for 文献检索、引文核对、参考文献管理、严格他引 and evidence-backed citer profiles; not for translating a paper or drafting manuscript prose.
Run score Not tested
See how to installnature-academic-search supports academic literature searches across multiple sources, citation checks, and reference-file organization. It can check citation details extracted from a document, find related papers, and convert literature identifiers. It also helps design PubMed search queries using MeSH, PubMed’s subject vocabulary, and audit citations while distinguishing independent citations from self-citations. The results can organize who cited a paper and the context in which it was cited, with supporting evidence.
Use it to search prior work across more than one source, check the references in a manuscript, or manage .nbib, .ris, and .bib files. It can also organize citation measures for individual papers and investigate the background or positions of people who cited them.
Search and verification may require MCP tools or API settings for the sources used, as well as network access. Converting supplied, complete citation records is intended to work offline. Paper translation and drafting manuscript text are outside the skill’s scope.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).
Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 24, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
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.
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.Map the user's need to one or more workflow values:
multi-source-search — find literature across sources.citation-verification — verify citations extracted from a document.mesh-strategy — build a MeSH/PubMed search strategy.citation-file-mgmt — convert/manage .nbib/.ris/.bib files.reference-mgmt — BibTeX, related-article discovery, ID conversion.strict-other-citation-impact-audit — determine strict independent other-citations, build article-level citation metric tables, identify high-profile citers (academy members, presidents/deans, talent-award holders, fellows, field leaders), and extract how they cited the target paper.A combined request (for example search then export) may need more than one. State the detected workflow(s) in one short line before proceeding.
Read the file mapped for each detected workflow (under references/workflows/). Do not read every workflow. Each workflow file links to the shared modules it needs.
Apply the loaded material in this order:
core/tools.md, core/routing-and-ops.md) — which MCP tool for which need, and the T1→T2→T3 fallback chain for source retrieval.Report specific tool failures and continue with remaining tools; broaden terms when there are no results; fall back to manual generation from MCP-fetched metadata if a script fails twice.
The files under references/ (and scripts/) are deep references, not defaults. Open them on demand per the references.on_demand table in the manifest — for example references/source-tiers.md for the full reliability classification, references/dedup-engine.md / references/citation-parser.md / references/search-strategy.md / references/ris-bibtex-format.md for the shared modules, and scripts/academic_search.py (no-MCP fallback discovery search) / scripts/format-converter.py / scripts/preflight.py for the tooling.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Find papers from Nature or a specified Cell, Nature, and Science journal group to support manuscript claims. Check abstracts or publisher pages, map sources to individual claims, and export verified reference details for reference managers.
Draft or review manuscript statements explaining where data and code can be accessed. Organize repository choices, access restrictions, identifiers, and dataset citations, and check metadata that helps others find and reuse the research data.
Retrieve academic full texts and supporting files through open access, publisher APIs, or authorized institutional access. The skill selects a route for each paper, checks downloaded files, and records sources, formats, and download outcomes.
Organize experiment photos, audio, and notes into Markdown logs with structured metadata. Assign experiment and sample batch IDs, archive original attachments, and optionally connect records to Feishu group messages or an Obsidian notebook.
Create, revise, and export scientific figures for manuscripts using Python or R. Check panel alignment and overlapping elements, or prepare editable diagrams and explicitly requested AI-generated graphical abstracts that visually summarize a paper.
Rebuild slide images, screenshots, scanned PDFs, or image-only presentations as editable PowerPoint files. Reconstruct text and simple shapes as separate objects, retain complex visuals as image assets where needed, and check rendered slides against their sources.