medsci-skills 5.0.0 → 5.2.0

package/metadata/distribution_files.json

@@ -1488,23 +1488,58 @@
     },
     {
       "path": "skills/fulltext-retrieval/SKILL.md",
-      "size": 5830,
-      "sha256": "0bdf94398af3d9f144b0b58fbce643d05f5486329472681a39090f135d3ec63f"
+      "size": 8248,
+      "sha256": "d97c19a64d92f66e3c8a1445d893c0f55364f21dc99404fb6f012a3566556e73"
     },
     {
       "path": "skills/fulltext-retrieval/fetch_oa.py",
-      "size": 15882,
-      "sha256": "b33feb91c7258d1986fbb6168a044b2abe21f3ba1cacadd3a52a38689477f86c"
+      "size": 24503,
+      "sha256": "768f95a30737e67b7f9edee72fe8815a795c9f83451b46551bbe25fc36094f4b"
+    },
+    {
+      "path": "skills/fulltext-retrieval/fetch_oa_report_challenge/expected/projection.json",
+      "size": 522,
+      "sha256": "f24bdb507f66932c0429acefc171abf5221bd644cacdeba5cd7b5c07670b04aa"
+    },
+    {
+      "path": "skills/fulltext-retrieval/fetch_oa_report_challenge/extracted_text.json",
+      "size": 351,
+      "sha256": "9b512bbea3780727e79355dd4b3689be182f086d4afb4184737524449fc44e4d"
+    },
+    {
+      "path": "skills/fulltext-retrieval/fetch_oa_report_challenge/results.json",
+      "size": 175,
+      "sha256": "e46d52e6a9c038ebd5cb8ce89a5961f32c8365e80d189d3ee80bed021a60296a"
+    },
+    {
+      "path": "skills/fulltext-retrieval/fetch_oa_report_challenge/run_challenge.py",
+      "size": 3138,
+      "sha256": "a3c194bb31f319bdd011d4436e5de22cfcc79b7979fbcba4883ed370e4acbeb4"
+    },
+    {
+      "path": "skills/fulltext-retrieval/fetch_oa_report_challenge/verify.sh",
+      "size": 286,
+      "sha256": "f96687fa9d1b213734810dcdfa8126a2efd1af106f5d1cdeb43d58b431ab915b"
+    },
+    {
+      "path": "skills/fulltext-retrieval/fetch_oa_report_challenge/worklist.tsv",
+      "size": 326,
+      "sha256": "d1c4c906052be198275155ee3e9ecf29b04ec8bdfeef97816ca15aa8cefa61fa"
     },
     {
       "path": "skills/fulltext-retrieval/pdf_to_md.py",
       "size": 5398,
       "sha256": "16ba8c61db254b4b356d85686946351daa5ea650d70dca2fd0d5677851c6df4d"
     },
+    {
+      "path": "skills/fulltext-retrieval/references/find_available_pdf.js",
+      "size": 3057,
+      "sha256": "04dc6d13d0bb7c43679e5386f1788edee6b187b2503cd9e250ae4ea63e11cec0"
+    },
     {
       "path": "skills/fulltext-retrieval/skill.yml",
-      "size": 1712,
-      "sha256": "43f84eeeeedb4676fb80fdca2ac0a84f6a90901b1d4e1d88359a532bb4ead835"
+      "size": 2420,
+      "sha256": "7a457e5f5fde09f57a8ef9d2207dbaab241e56a9bca59ba577d26351bf225346"
     },
     {
       "path": "skills/generate-codebook/SKILL.md",
@@ -1563,8 +1598,8 @@
     },
     {
       "path": "skills/lit-sync/SKILL.md",
-      "size": 16378,
-      "sha256": "e59b10d8dfdb52318a212e42d403a4372435697880e45643d3864f1374c7e82a"
+      "size": 21126,
+      "sha256": "4ba2d2b6dd4704803c0922993401b837d4135ac1d655d6064229315537a8e818"
     },
     {
       "path": "skills/lit-sync/references/locale/ko/note_templates.md",
@@ -1573,8 +1608,8 @@
     },
     {
       "path": "skills/lit-sync/skill.yml",
-      "size": 2522,
-      "sha256": "5f656fae91ba46d54f9d619785607bfb57773abc6a872207435ecf7a7315816b"
+      "size": 2780,
+      "sha256": "a04d160e9fc6382c783940b737c9d9348db45e34ea80c69ef905be0a3c357e34"
     },
     {
       "path": "skills/ma-scout/SKILL.md",
@@ -2498,8 +2533,13 @@
     },
     {
       "path": "skills/mllm-eval/SKILL.md",
-      "size": 6288,
-      "sha256": "ccf3da2f70b356d432b3d33500f667f9d7858500a9ff325631a9a16f5f300a8b"
+      "size": 6720,
+      "sha256": "afdc167bfccb6bad8a4019e0af5bd7c955129220d360511a89962ecd321bc44d"
+    },
+    {
+      "path": "skills/mllm-eval/references/evaluation_axes.md",
+      "size": 10857,
+      "sha256": "49d77ab63feae5dba5cdae7e47d9de6ea97ee3b9eea4b9cba39ec8b0e185be72"
     },
     {
       "path": "skills/mllm-eval/scripts/check_mllm_eval_completeness.py",
@@ -2588,18 +2628,23 @@
     },
     {
       "path": "skills/model-evaluation/SKILL.md",
-      "size": 5031,
-      "sha256": "17ffde905359e4cffdf747422b7d41c214d2abfcc71e50e1b1e4a689d87fa695"
+      "size": 5780,
+      "sha256": "334b4ca87a2f672446563f3fb6d78c0585386fac12aee29e10dc09465e892193"
     },
     {
       "path": "skills/model-evaluation/references/metric_guide.md",
       "size": 2454,
       "sha256": "8d09ca7ce9fb9f66ee4942689294d9b12ae1d892ac67769cd68fdc38a4e220ee"
     },
+    {
+      "path": "skills/model-evaluation/references/metric_selection_grounding.md",
+      "size": 9588,
+      "sha256": "56723e73b2b74299140d353921d1dba471bedf9aea0b8e769fc69995c4733995"
+    },
     {
       "path": "skills/model-evaluation/scripts/check_metric_reporting.py",
-      "size": 9564,
-      "sha256": "c33f52ee62ae93417027d0bb0b6cf2a95f5747d52403ab99c075bc64a5e2c593"
+      "size": 9562,
+      "sha256": "fd6c0205f652651a5a43910cb415ed8442100fc553ce04aa5d5905d97743a0bf"
     },
     {
       "path": "skills/model-evaluation/scripts/metric_reporting_challenge/fixture/clf_bad.md",
@@ -2611,6 +2656,16 @@
       "size": 186,
       "sha256": "ba44a3b38b4128fa713555c8b332f211e9087e6bc016d80af4c3074c3ca6ef8e"
     },
+    {
+      "path": "skills/model-evaluation/scripts/metric_reporting_challenge/fixture/det_good_wrapped.md",
+      "size": 285,
+      "sha256": "0c1f5ed5167969870602106e7a7c9a2ae53e3a3ddea5fa280c3beb6bf470c454"
+    },
+    {
+      "path": "skills/model-evaluation/scripts/metric_reporting_challenge/fixture/det_no_iou.md",
+      "size": 224,
+      "sha256": "08227fbe46829b8eecdfe15680e1bb32087f1e6c5a353b3df6055c67d8300fc0"
+    },
     {
       "path": "skills/model-evaluation/scripts/metric_reporting_challenge/fixture/seg_bad.md",
       "size": 119,
@@ -2628,8 +2683,8 @@
     },
     {
       "path": "skills/model-evaluation/scripts/metric_reporting_challenge/verify.sh",
-      "size": 1235,
-      "sha256": "f819d1333a7206db6383ccbd41c6eadae015004e61ae335e67a3334936c58cc8"
+      "size": 1663,
+      "sha256": "4aa6db49d3552f01a54ddb70484df5d214806d805b836b24beda81d9aca32bd6"
     },
     {
       "path": "skills/model-evaluation/skill.yml",
@@ -2683,8 +2738,13 @@
     },
     {
       "path": "skills/model-validation/SKILL.md",
-      "size": 9347,
-      "sha256": "ecd48672a03923bf1ace63528fd2dbcf138cd880103cc8c40345b3857d66ad1c"
+      "size": 9810,
+      "sha256": "1a75a5a1f21f5a8778d0b77db2e99574bf37edda2a291d8dde6aafea4a207ff0"
+    },
+    {
+      "path": "skills/model-validation/references/validation_design.md",
+      "size": 11427,
+      "sha256": "16d43b688ea63745174c7ca8fafd78a7342b26c34ad1e10e1fdbc117cceafb2e"
     },
     {
       "path": "skills/model-validation/scripts/check_split_leakage.py",
@@ -3238,8 +3298,8 @@
     },
     {
       "path": "skills/search-lit/SKILL.md",
-      "size": 21637,
-      "sha256": "35809486f31f1a26288a27ee0b1383760cf97e0287916ace2e9097eef88182e4"
+      "size": 20281,
+      "sha256": "608644e83ffc357f3b43b65cf7c439c9381f5948c51798672929f7a38aea5024"
     },
     {
       "path": "skills/search-lit/references/parse_pubmed.py",

package/metadata/distribution_manifest.json

@@ -1,6 +1,6 @@
 {
   "schema_version": 1,
-  "version": "5.0.0",
+  "version": "5.2.0",
   "owned_skills": [
     "academic-aio",
     "add-journal",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "medsci-skills",
-  "version": "5.0.0",
+  "version": "5.2.0",
   "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/SKILL.md

@@ -13,10 +13,10 @@ Batch download open-access full-text PDFs from a DOI list using legitimate OA AP
 ## Pipeline
 
 ```
-DOI list → Unpaywall → PMC (Europe PMC / OA FTP / web) → OpenAlex → Crossref → landing page
+DOI → arXiv (10.48550/arXiv.* DOIs) → Unpaywall → PMC (Europe PMC / OA FTP / web) → OpenAlex → Crossref → landing page
 ```
 
-Each DOI goes through these sources in order until a valid PDF (≥10 KB, `%PDF-` header) is found.
+Each DOI goes through these sources in order until a valid PDF (≥10 KB, `%PDF-` header) is found. arXiv DOIs (`10.48550/arXiv.2401.01234`, version suffixes, old-style `hep-th/9901001`, or a bare `arXiv:` id) resolve directly to the arXiv PDF first.
 
 ## Quick Start
 
@@ -43,13 +43,20 @@ python fetch_oa.py dois.txt -o pdfs/ -e your@email.com --verbose
 10.1002/mp.12524
 ```
 
-**TSV with header** — must contain a `DOI` column, optional `PMID` column:
+**TSV / CSV with header** — must contain a `DOI` column; optional `PMID` and `Title` columns:
 ```tsv
 ID	Title	DOI	PMID	Year
 1	Some paper	10.1007/s00330-010-1783-x	20628747	2010
 ```
 
-When a PMID is available, the PMC lookup is more reliable (PMID → PMCID conversion).
+**Markdown table** — a pipe table with a `DOI` column also works:
+```markdown
+| DOI | PMID | Title |
+|-----|------|-------|
+| 10.1007/s00330-010-1783-x | 20628747 | Some paper |
+```
+
+When a PMID is available, the PMC lookup is more reliable (PMID → PMCID conversion). When a `Title` column is present, downloaded PDFs get a best-effort title cross-check (see *Retrieval report* below).
 
 ## PMC Download (JS-Challenge Resistant)
 
@@ -82,8 +89,48 @@ curl -s "https://www.ncbi.nlm.nih.gov/pmc/utils/idconv/v1.0/?ids=${DOI}&format=j
 ## Output
 
 - PDFs saved as `{DOI_safe}.pdf` (slashes replaced with underscores)
+- `pdfs/retrieval_report.json` — structured per-DOI report (see below)
 - `manual_needed.txt` — DOIs that could not be retrieved via OA
-- Summary with OA/PMC/fail/skip counts
+- Summary with arXiv/OA/PMC/fail/skip counts
+
+## Retrieval report (`--report`)
+
+Every run writes a structured report (default `<output>/retrieval_report.json`,
+override with `--report PATH`):
+
+```json
+{
+  "schema_version": 1,
+  "generated_by": "fetch_oa.py",
+  "counts": {"total": 10, "retrieved": 6, "not_retrieved": 4, "title_mismatch": 1},
+  "items": [
+    {"doi": "10.1007/...", "pmid": "20628747", "title": "...",
+     "status": "oa", "source": "unpaywall", "file": "10.1007_....pdf",
+     "size_bytes": 482113, "title_match": "match"}
+  ]
+}
+```
+
+- `status` ∈ `arxiv | oa | pmc | skip | fail`; `source` names the resolver that succeeded.
+- `title_match` ∈ `match | mismatch | unavailable` (tri-state). It is **best-effort**:
+  it needs a `Title` column **and** `pdftotext` (poppler). When either is missing it is
+  `unavailable`; a `mismatch` is **flagged** for review and **never** auto-rejects a PDF
+  (guards against a publisher serving a wrong/redirect PDF that still passes the `%PDF-` check).
+
+## Attach PDFs into Zotero ("Find Available PDF")
+
+OA-only resolvers miss paywalled-but-licensed papers. To attach full text **inside
+Zotero** at a much higher yield, use `references/find_available_pdf.js` — a user-run
+snippet for Zotero's *Tools → Developer → Run JavaScript*. It triggers Zotero's own
+`addAvailablePDF` / `addAvailablePDFs` and therefore reuses **your** OpenURL resolver /
+institutional proxy config; **no credentials, proxy hosts, or institutional identifiers
+are hard-coded or leave your Zotero client**. The no-code equivalent is right-click →
+"Find Available PDF".
+
+This path is **user-initiated** and depends on your live Zotero session, so its results
+are recorded manually (not reproducible CI evidence). `/lit-sync` Phase 2.7 orchestrates
+both routes (disk OA via this script + in-library via the snippet) and reconciles them in
+a report.
 
 ## Requirements