medsci-skills 5.9.0 → 5.9.1

package/README.md

@@ -57,7 +57,9 @@ rather than reimplementing the ecosystem. Clinical AI model research
 engineering is in scope; it is **not** a diagnostic tool, an autonomous author, or a
 general AI-scientist platform, and every output requires human-expert verification.
 New here? See the [3 workflows below](#start-here-3-workflows), the
-[FAQ](docs/faq.md), and the
+[FAQ](docs/faq.md), the
+[research connectors it calls](docs/connectors.md) (keyless public APIs — nothing to set
+up in the common case), and the
 [scope boundary](ROADMAP.md#not-planned--explicitly-out-of-scope).
 
 ---

package/metadata/distribution_files.json

@@ -1578,8 +1578,8 @@
     },
     {
       "path": "skills/fulltext-retrieval/fetch_oa.py",
-      "size": 24503,
-      "sha256": "768f95a30737e67b7f9edee72fe8815a795c9f83451b46551bbe25fc36094f4b"
+      "size": 24810,
+      "sha256": "12bfbf094d338ac461267cea133c0a63a66bc0d2dadd28727921149bc5b72855"
     },
     {
       "path": "skills/fulltext-retrieval/fetch_oa_report_challenge/expected/projection.json",
@@ -3853,8 +3853,8 @@
     },
     {
       "path": "skills/verify-refs/scripts/verify_refs.py",
-      "size": 40629,
-      "sha256": "ca762e7f294cf90aa1675129a8c152304b48ba7340982c09a64204babc53c674"
+      "size": 41415,
+      "sha256": "4377e25e6b125ace31fd35df9ffdd21a413f0f70ba1e429e5bfcf50c0a29510e"
     },
     {
       "path": "skills/verify-refs/skill.yml",

package/metadata/distribution_manifest.json

@@ -1,6 +1,6 @@
 {
   "schema_version": 1,
-  "version": "5.9.0",
+  "version": "5.9.1",
   "owned_skills": [
     "academic-aio",
     "add-journal",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "medsci-skills",
-  "version": "5.9.0",
+  "version": "5.9.1",
   "description": "MedSci Skills — a medical/scientific research skill suite for AI coding agents (Claude Code, Codex, Cursor, Copilot). The npm package is a terminal-friendly installer shortcut; the canonical distribution remains the GitHub repository and the Claude Code plugin marketplace.",
   "license": "SEE LICENSE IN LICENSE",
   "homepage": "https://github.com/Aperivue/medsci-skills#readme",

package/skills/fulltext-retrieval/fetch_oa.py

@@ -21,6 +21,7 @@ import csv
 import io
 import json
 import logging
+import os
 import re
 import shutil
 import subprocess
@@ -562,8 +563,9 @@ def main():
                              "with a DOI column (optional PMID, Title)")
     parser.add_argument("-o", "--output", type=Path, default=Path("pdfs"),
                         help="Output directory (default: pdfs/)")
-    parser.add_argument("-e", "--email", required=True,
-                        help="Contact email (required by Unpaywall TOS)")
+    parser.add_argument("-e", "--email", default=os.environ.get("MEDSCI_CONTACT_EMAIL"),
+                        help="Contact email (required by Unpaywall TOS). "
+                             "Falls back to the MEDSCI_CONTACT_EMAIL environment variable.")
     parser.add_argument("--report", type=Path, default=None,
                         help="Path for the JSON retrieval report "
                              "(default: <output>/retrieval_report.json)")
@@ -571,6 +573,10 @@ def main():
                         help="Show debug messages")
     args = parser.parse_args()
 
+    if not args.email:
+        parser.error("a contact email is required (Unpaywall TOS): pass --email you@lab.org "
+                     "or set MEDSCI_CONTACT_EMAIL")
+
     logging.basicConfig(
         level=logging.DEBUG if args.verbose else logging.WARNING,
         format="%(levelname)s: %(message)s",

package/skills/verify-refs/scripts/verify_refs.py

@@ -13,6 +13,7 @@ import argparse
 import csv
 import html
 import json
+import os
 import re
 import sys
 import time
@@ -372,8 +373,30 @@ def guess_title(raw: str) -> str:
     return ""
 
 
+def _contact_email() -> str:
+    """User-supplied contact email (courtesy for NCBI/CrossRef), never a credential."""
+    return (os.environ.get("MEDSCI_CONTACT_EMAIL")
+            or os.environ.get("NCBI_EMAIL")
+            or "medsci-skills@users.noreply.github.com")
+
+
+def _user_agent() -> str:
+    return f"medsci-skills/verify-refs (mailto:{_contact_email()})"
+
+
+def _ncbi_extras() -> dict:
+    """Optional NCBI E-utilities etiquette / rate-limit params, all from env.
+    Setting NCBI_API_KEY raises the PubMed rate limit from 3 to 10 requests/s;
+    absent it, the calls stay keyless. `tool`/`email` are NCBI-recommended courtesy."""
+    extra = {"tool": "medsci-skills", "email": _contact_email()}
+    key = os.environ.get("NCBI_API_KEY")
+    if key:
+        extra["api_key"] = key
+    return extra
+
+
 def http_json(url: str, timeout: int) -> dict | None:
-    req = urllib.request.Request(url, headers={"User-Agent": "medsci-skills/verify-refs (mailto:example@example.com)"})
+    req = urllib.request.Request(url, headers={"User-Agent": _user_agent()})
     try:
         with urllib.request.urlopen(req, timeout=timeout) as resp:
             return json.loads(resp.read().decode("utf-8", "replace"))
@@ -421,7 +444,7 @@ def verify_pubmed_pmid(pmid: str, timeout: int) -> tuple[str, str, list]:
     verify_pubmed_efetch().
     """
     url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi?" + urllib.parse.urlencode(
-        {"db": "pubmed", "id": pmid, "retmode": "json"}
+        {"db": "pubmed", "id": pmid, "retmode": "json", **_ncbi_extras()}
     )
     data = http_json(url, timeout)
     if not data:
@@ -458,11 +481,11 @@ def verify_pubmed_efetch(pmid: str, timeout: int) -> tuple[str, str, list, list]
     case: CrossRef "Vasileios" vs PubMed "Victoria" — PubMed is authoritative).
     """
     url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?" + urllib.parse.urlencode(
-        {"db": "pubmed", "id": pmid, "retmode": "xml"}
+        {"db": "pubmed", "id": pmid, "retmode": "xml", **_ncbi_extras()}
     )
     req = urllib.request.Request(
         url,
-        headers={"User-Agent": "medsci-skills/verify-refs (mailto:example@example.com)"},
+        headers={"User-Agent": _user_agent()},
     )
     try:
         with urllib.request.urlopen(req, timeout=timeout) as resp:
@@ -496,7 +519,7 @@ def verify_pubmed_title(title: str, timeout: int) -> tuple[str, str, list]:
     if not title:
         return "UNVERIFIED", "No DOI, PMID, or usable title", []
     url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?" + urllib.parse.urlencode(
-        {"db": "pubmed", "term": title, "retmode": "json", "retmax": "3"}
+        {"db": "pubmed", "term": title, "retmode": "json", "retmax": "3", **_ncbi_extras()}
     )
     data = http_json(url, timeout)
     if not data: