Life Sciences Literature

View saved version →

---
name: biorxiv-skill
description: Submit compact bioRxiv and medRxiv API requests for details, publication-linkage, and DOI lookups. Use when a user wants concise preprint metadata summaries
---

## Source presentation
<!-- source-presentation-contract:v2 -->
- Add claim-adjacent links only for substantive claims supported by returned `sources`; never cite empty, metadata-only, or failed lookups.
- Preserve `checked_sources`, use only supported `canonical_url` mappings, and leave requested raw or machine-readable output unchanged.
- Use the `biorxiv-skill` entry in `../../references/source-links.json` and follow `../../references/source-presentation.md`.

## Operating rules
- Use `scripts/rest_request.py` for all bioRxiv and medRxiv API calls.
- Use `base_url=https://api.biorxiv.org`.
- The script accepts `max_items`; for `details` and `pubs` pages, start around `max_items=10`.
- Prefer one cursor page at a time instead of increasing page size or pasting long collections into chat.
- Re-run requests in long conversations instead of relying on older tool output.
- Treat displayed `...` in tool previews as UI truncation, not part of the true request.

## Execution behavior
- Return concise markdown summaries from the script JSON by default.
- Return the raw script JSON only if the user explicitly asks for machine-readable output.
- Prefer these paths: `details/<server>/<start>/<end>/<cursor>/json`, `details/<server>/<doi>/na/json`, `pubs/<server>/<start>/<end>/<cursor>`, and `pubs/<server>/<doi>/na/json`.
- If the user needs full page contents, set `save_raw=true` and report the saved file path rather than pasting large collections into chat.

## Input
- Read one JSON object from stdin.
- Required fields: `base_url`, `path`
- Optional fields: `method`, `params`, `headers`, `json_body`, `form_body`, `record_path`, `response_format`, `max_items`, `max_depth`, `timeout_sec`, `save_raw`, `raw_output_path`
- Common biorxiv patterns:
  - `{"base_url":"https://api.biorxiv.org","path":"details/biorxiv/2025-03-21/2025-03-28/0/json","record_path":"collection","max_items":10}`
  - `{"base_url":"https://api.biorxiv.org","path":"details/medrxiv/10.1101/2020.09.09.20191205/na/json","record_path":"collection","max_items":10}`
  - `{"base_url":"https://api.biorxiv.org","path":"pubs/medrxiv/2020-03-01/2020-03-30/0","record_path":"collection","max_items":10}`

## Output
- Success returns `ok`, `source`, `path`, `method`, `status_code`, `warnings`, and either compact `records` or a compact `summary`.
- Use `raw_output_path` when `save_raw=true`.
- Failure returns `ok=false` with `error.code` and `error.message`.

## Execution
```bash
echo '{"base_url":"https://api.biorxiv.org","path":"details/biorxiv/2025-03-21/2025-03-28/0/json","record_path":"collection","max_items":10}' | python scripts/rest_request.py
```

Referenced files: 1

View saved version →

---
name: ncbi-entrez-skill
description: Submit compact NCBI Entrez E-Utilities requests for PubMed publication search, summaries, fetches, and links; save raw JSON or XML only on request.
---

## Source presentation
<!-- source-presentation-contract:v2 -->
- Add claim-adjacent links only for substantive claims supported by returned `sources`; never cite empty, metadata-only, or failed lookups.
- Preserve `checked_sources`, use only supported `canonical_url` mappings, and leave requested raw or machine-readable output unchanged.
- Use the `ncbi-entrez-skill` entry in `../../references/source-links.json` and follow `../../references/source-presentation.md`.

## Operating rules
- Use `scripts/ncbi_entrez.py` for all Entrez calls in this package.
- Set `params.db=pubmed` on every request; if `params.dbfrom` is provided, it must also be `pubmed`.
- If `params.linkname` is provided, use only `pubmed_pubmed` or a `pubmed_pubmed_*` link.
- Use explicit `endpoint` values such as `esearch`, `esummary`, `efetch`, `elink`, or `einfo`.
- Search-style Entrez calls are better with `retmax=10` and `max_items=10`.
- Route PubMed Central Open Access and full-text requests to `ncbi-pmc-skill`.
- Re-run requests in long conversations instead of relying on older tool output.
- Treat displayed `...` in tool previews as UI truncation, not literal request content.

## Execution behavior
- Return concise markdown summaries from the script output by default.
- Return raw JSON or XML only if the user explicitly asks for machine-readable output.
- Prefer targeted endpoint calls instead of broad unfiltered dumps.
- If the user needs the full raw response, set `save_raw=true` and report the saved file path.

## Input
- Read one JSON object from stdin.
- Required fields: `endpoint` and `params.db=pubmed`.
- Optional fields: `record_path`, `response_format`, `max_items`, `max_depth`, `timeout_sec`, `save_raw`, `raw_output_path`.
- Common PubMed patterns:
  - `{"endpoint":"esearch","params":{"db":"pubmed","term":"KRAS AND colorectal cancer","retmode":"json","retmax":10},"max_items":10}`
  - `{"endpoint":"esummary","params":{"db":"pubmed","id":"22966082","retmode":"json"},"max_items":10}`
  - `{"endpoint":"efetch","params":{"db":"pubmed","id":"22966082","retmode":"xml"},"response_format":"xml","max_items":10}`
  - `{"endpoint":"elink","params":{"dbfrom":"pubmed","db":"pubmed","id":"22966082","retmode":"json"},"max_items":10}`

## Output
- Success returns `ok`, `source`, endpoint metadata, and either compact `records`, a compact `summary`, or `text_head`.
- Use `raw_output_path` when `save_raw=true`.
- Failure returns `ok=false` with `error.code` and `error.message`.

## Execution
```bash
echo '{"endpoint":"esearch","params":{"db":"pubmed","term":"TP53 AND cancer","retmode":"json","retmax":10},"max_items":10}' | python scripts/ncbi_entrez.py
```

Referenced files: 2

View saved version →

---
name: ncbi-pmc-skill
description: Retrieve compact PMC Article Dataset metadata for PMCID, PMID, or DOI lookups. Use when a user wants open-access status, license, retraction status, or current article file URLs; save raw JSON only on request.
---

## Source presentation
<!-- source-presentation-contract:v2 -->
- Add claim-adjacent links only for substantive claims supported by returned `sources`; never cite empty, metadata-only, or failed lookups.
- Preserve `checked_sources`, use only supported `canonical_url` mappings, and leave requested raw or machine-readable output unchanged.
- Use the `ncbi-pmc-skill` entry in `../../references/source-links.json` and follow `../../references/source-presentation.md`.

## Operating rules
- Use `scripts/ncbi_pmc.py` for all PMC Article Dataset metadata calls in this package.
- This skill is intentionally narrow: it resolves one PMCID, PMID, DOI, or text identifier through PMC ESearch when needed and reads versioned metadata from the current public PMC Cloud dataset.
- Pass the identifier under `params.id`; use `params.retmax` only when a non-PMCID lookup may resolve to multiple PMC records.
- Re-run requests in long conversations instead of relying on older tool output.
- Treat displayed `...` in tool previews as UI truncation, not literal request content.

## Execution behavior
- Return concise markdown summaries from the script output by default.
- Report the returned open-access, manuscript, retraction, license, and HTTPS file URL fields directly rather than inferring availability.
- Return raw JSON metadata only if the user explicitly asks for machine-readable output.
- Prefer targeted endpoint calls instead of broad unfiltered dumps.
- If the user needs the full raw response, set `save_raw=true` and report the saved file path.

## Input
- Read one JSON object from stdin.
- Required field: `params.id`
- Optional fields: `params.retmax`, `max_items`, `timeout_sec`, `save_raw`, `raw_output_path`
- Common PMC Article Dataset patterns:
  - `{"params":{"id":"PMC3257301"},"max_items":10}`
  - `{"params":{"id":"22966082"},"max_items":10}`
  - `{"params":{"id":"10.1093/nar/gkr1184"},"max_items":10}`

## Output
- Success returns `ok`, `source`, resolved `pmcids`, record counts, `truncated`, and compact versioned `records` containing license, retraction, and file URL metadata.
- Use `raw_output_path` when `save_raw=true`.
- Failure returns `ok=false` with `error.code` and `error.message`.

## Execution
```bash
echo '{"params":{"id":"PMC3257301"},"max_items":10}' | python scripts/ncbi_pmc.py
```

Referenced files: 2