medsci-skills 5.26.0 → 5.26.2

package/metadata/distribution_files.json

@@ -1823,23 +1823,23 @@
     },
     {
       "path": "skills/fulltext-retrieval/SKILL.md",
-      "size": 8248,
-      "sha256": "d97c19a64d92f66e3c8a1445d893c0f55364f21dc99404fb6f012a3566556e73"
+      "size": 10954,
+      "sha256": "4d1defdcb710f727c15779fbeb9a10dee6088a1b70b250f6fe2339c87a76c3a1"
     },
     {
       "path": "skills/fulltext-retrieval/fetch_oa.py",
-      "size": 24810,
-      "sha256": "12bfbf094d338ac461267cea133c0a63a66bc0d2dadd28727921149bc5b72855"
+      "size": 32245,
+      "sha256": "09ca16bec5232d778940e2e3b49681c2e548720a1f20184130c39b23ca23d73e"
     },
     {
       "path": "skills/fulltext-retrieval/fetch_oa_report_challenge/expected/projection.json",
-      "size": 522,
-      "sha256": "f24bdb507f66932c0429acefc171abf5221bd644cacdeba5cd7b5c07670b04aa"
+      "size": 614,
+      "sha256": "cd983f0ce56d9fd500eeff4f8432bbb66759cc4b56983214d548ea40cf2ecccd"
     },
     {
       "path": "skills/fulltext-retrieval/fetch_oa_report_challenge/extracted_text.json",
-      "size": 351,
-      "sha256": "9b512bbea3780727e79355dd4b3689be182f086d4afb4184737524449fc44e4d"
+      "size": 407,
+      "sha256": "b55cd1dc0704527ca9c34ff6320e49cfa14a5b1310b50c7a8e7c39f1c2d9d3d2"
     },
     {
       "path": "skills/fulltext-retrieval/fetch_oa_report_challenge/results.json",
@@ -1873,8 +1873,8 @@
     },
     {
       "path": "skills/fulltext-retrieval/skill.yml",
-      "size": 2420,
-      "sha256": "7a457e5f5fde09f57a8ef9d2207dbaab241e56a9bca59ba577d26351bf225346"
+      "size": 2831,
+      "sha256": "cce683497dcb52905d603d7bab326dfc480d83436350d9435b75f7f67cdb9ed4"
     },
     {
       "path": "skills/generate-codebook/SKILL.md",
@@ -1943,8 +1943,8 @@
     },
     {
       "path": "skills/lit-sync/SKILL.md",
-      "size": 22758,
-      "sha256": "b0fc43eed00b1813f453614b89d9a29d2573115789c00daacca2f82a65d6350c"
+      "size": 23559,
+      "sha256": "d41481e90c1b4ca804f9686d4dcb066d5a2ba23504ed9e0080581991e45061ae"
     },
     {
       "path": "skills/lit-sync/references/bbt_lookup.md",
@@ -3688,14 +3688,24 @@
     },
     {
       "path": "skills/polish-language/SKILL.md",
-      "size": 7649,
-      "sha256": "27c9d79d48c6b4b3e5a840e30962c4e731f8486e9dab75c16ac70d6067bc4c76"
+      "size": 7709,
+      "sha256": "db2a3d7705c611185daed6d363d606cbda11b5e041bc84c41a61c5b28dc45058"
     },
     {
       "path": "skills/polish-language/scripts/lint_challenge/expected/report.txt",
       "size": 1032,
       "sha256": "bf7be677cd12d583fd958468a6e5ee7f08493cc5fd01a4f7c27af3770331da66"
     },
+    {
+      "path": "skills/polish-language/scripts/lint_challenge/fixture/consistent_uk.md",
+      "size": 524,
+      "sha256": "1b77ed2c859da126ce1aa6a8557d180e8e845c97271b2b898ca718df10e3de0c"
+    },
+    {
+      "path": "skills/polish-language/scripts/lint_challenge/fixture/consistent_us.md",
+      "size": 763,
+      "sha256": "3bd1ce288b08e27296dd67a5a2ad1261e61e1219344c3e2c59b9070e8f6ccda4"
+    },
     {
       "path": "skills/polish-language/scripts/lint_challenge/fixture/manuscript.md",
       "size": 709,
@@ -3703,18 +3713,18 @@
     },
     {
       "path": "skills/polish-language/scripts/lint_challenge/problem.md",
-      "size": 2169,
-      "sha256": "69037c9d85cf1a29a77dc77cd61e879b9a6befcec945b808d71468fff4278490"
+      "size": 2949,
+      "sha256": "df7c892a1131d76ee2f7614b465e0d677d09d595492eef2ece4f21bd9ff36583"
     },
     {
       "path": "skills/polish-language/scripts/lint_challenge/verify.sh",
-      "size": 615,
-      "sha256": "31ddc7fb64ac2f9180cdfa6a6ee15a29844c2e9c0955b83250b2c1b62f9e8fa6"
+      "size": 1132,
+      "sha256": "6b3faa91892bb4651795e4943b04171ef87e6162acce58a65390446e14251560"
     },
     {
       "path": "skills/polish-language/scripts/lint_consistency.py",
-      "size": 15665,
-      "sha256": "f380439fae1fd41b966862957ca4232467a1d1701dd5a19c35c1864b3df9aea2"
+      "size": 16136,
+      "sha256": "cc892d682ea4ccd648effb1facf8d404503d9c5d89b2cf954acfedd12a967857"
     },
     {
       "path": "skills/polish-language/scripts/lint_figure_locale.py",
@@ -3733,8 +3743,8 @@
     },
     {
       "path": "skills/polish-language/skill.yml",
-      "size": 2033,
-      "sha256": "1a513a7d532d5a335acd6fa91566a551b5dc17d6ba3021f9d39a52848a7df571"
+      "size": 2081,
+      "sha256": "aff8fcd8108ca1df38de11ce594005dfa94baec8947e14dba9214538e77b1eaa"
     },
     {
       "path": "skills/preprocess-imaging/SKILL.md",
@@ -3828,8 +3838,8 @@
     },
     {
       "path": "skills/present-paper/SKILL.md",
-      "size": 53093,
-      "sha256": "d94632764cd473f79ccf594bb6ecbd49bc270447a81d1f9cfce3d1d43701bbea"
+      "size": 54313,
+      "sha256": "f57f6bfcfdf4a016defcce34732e264c7ac11258f825e1244c681d0d6a52db5d"
     },
     {
       "path": "skills/present-paper/references/ai_slide_tells.md",
@@ -3898,8 +3908,8 @@
     },
     {
       "path": "skills/present-paper/references/slide_visual_styles/nature_lancet.md",
-      "size": 9116,
-      "sha256": "fd70cbe0edbc39b05a8c6f53da5637913c15182aeb4878983615a77af20c5846"
+      "size": 10721,
+      "sha256": "7f6bc69354220de042a8074d00e5e015972f232384efda72587208fbacd078e6"
     },
     {
       "path": "skills/present-paper/references/spoken_notes_and_bilingual.md",
@@ -3943,8 +3953,8 @@
     },
     {
       "path": "skills/present-paper/scripts/check_font_portability.py",
-      "size": 15788,
-      "sha256": "192f7107e47364ebe14e6db287d4e3c91b62d6c24391ac5669532f0461695c98"
+      "size": 15874,
+      "sha256": "182a214f32f4f9c73b7e4717d334cd81e94da77c78bc660a7367d69921451528"
     },
     {
       "path": "skills/present-paper/scripts/check_font_portability_challenge/make_fixtures.py",
@@ -3973,18 +3983,18 @@
     },
     {
       "path": "skills/present-paper/scripts/check_text_overflow.py",
-      "size": 11729,
-      "sha256": "211a6fd3b73d5d8b107f24648db2b0de5628ae6f52c7331253ec9f7664d8179b"
+      "size": 12150,
+      "sha256": "c0dde521a02b7f3d495a627003430c29eae199cd8fa4e1c5be4f778b32ff6c5b"
     },
     {
       "path": "skills/present-paper/scripts/check_text_overflow_challenge/make_fixtures.py",
-      "size": 4169,
-      "sha256": "6f9d577e43f10ad6f9d98bfa3d8a02f0cf1bb8a5b7c722c11054363dacf39b67"
+      "size": 4162,
+      "sha256": "473b8a58e8fefc62c1d3cf0f974aeb1b7ca1ddb3bb31abf2aa7ec612bded3fdd"
     },
     {
       "path": "skills/present-paper/scripts/check_text_overflow_challenge/verify.sh",
-      "size": 4013,
-      "sha256": "77366b614425a859c09942b233a9616b21bd1f33c50fdf20d5ca25a18eba837e"
+      "size": 4126,
+      "sha256": "5467d119389fb9b2787d18b5f67283c804cd22a5b112c3c82ece55f6ed720269"
     },
     {
       "path": "skills/present-paper/scripts/extract_pdf_figures.py",
@@ -4018,13 +4028,13 @@
     },
     {
       "path": "skills/present-paper/skill.yml",
-      "size": 3238,
-      "sha256": "6d45223886fa651661d13afbe18a8cd80907f11cbe1afadd94656630a83729ba"
+      "size": 3482,
+      "sha256": "28d8a5a32fc4a0c5ab63c7a506911e3c022a1b8c77ecccef350298b1755d0e37"
     },
     {
       "path": "skills/present-paper/templates/build_pptx_nature_lancet.py",
-      "size": 30327,
-      "sha256": "8a08bb4e981c76aa8b3d262037c7456dc4eab2ef12c809a26297c85be9508f6e"
+      "size": 32525,
+      "sha256": "9e14b3845d961d3bb9ab12bffc9709414ac1b517b08c345a85556868a619afb3"
     },
     {
       "path": "skills/profile-imaging/SKILL.md",
@@ -4153,8 +4163,8 @@
     },
     {
       "path": "skills/render-pdf-doc/SKILL.md",
-      "size": 9236,
-      "sha256": "97af21fac95af6dcd0e47bc6a547f6413f47d431c74d310174899c36cb86da17"
+      "size": 10667,
+      "sha256": "cb3856e4b0aefb6dd0f038a7c8389620c4b933d381d7ff6f653c1f5246abb16a"
     },
     {
       "path": "skills/render-pdf-doc/references/known_pitfalls.md",
@@ -4168,8 +4178,8 @@
     },
     {
       "path": "skills/render-pdf-doc/scripts/check_deps.sh",
-      "size": 2183,
-      "sha256": "782efdda541c0a84a8d978bb076d43a1d3a026a00b878205dd6d922a197186f6"
+      "size": 2218,
+      "sha256": "587b5890f82890a95647fb7f8b764f8f1c559c2c2806796387b88cfa90c803a7"
     },
     {
       "path": "skills/render-pdf-doc/scripts/infer_colwidths.py",
@@ -4178,18 +4188,18 @@
     },
     {
       "path": "skills/render-pdf-doc/scripts/render_pdf.sh",
-      "size": 3958,
-      "sha256": "b5a9ebcbb25b1ec85577c9864f60f4f363e90f88896903cff48f7626f5b6b95a"
+      "size": 4711,
+      "sha256": "0892681945d7599ca5c4dc5411297f8904a8595efe8f7401004c3dac06d68764"
     },
     {
       "path": "skills/render-pdf-doc/scripts/scan_glyph_coverage.py",
-      "size": 6602,
-      "sha256": "09415f60ef9fd96e4baee36bcd38da36dde604baf0656c436cde9f75fb001a17"
+      "size": 9266,
+      "sha256": "4795edba22e36e1ca28e30588f696628e203a573862e066961648896b7f6699d"
     },
     {
       "path": "skills/render-pdf-doc/skill.yml",
-      "size": 3133,
-      "sha256": "77fe112e5a013d3169290132f9882fbb05b3ebe9317729960582895509c21568"
+      "size": 3329,
+      "sha256": "3d7f542a2fe9a5d0de2e2e462f4177f68424dfbdc6f34a69758d847a954752cd"
     },
     {
       "path": "skills/render-pdf-doc/templates/anchor-doc.md",
@@ -4328,8 +4338,8 @@
     },
     {
       "path": "skills/search-lit/SKILL.md",
-      "size": 24427,
-      "sha256": "7b3b355e1cf8089b061e1dd5412cf69338a82b993c2e64bc6afd50708051c84d"
+      "size": 24942,
+      "sha256": "f16110416385b53317c0367da792cce91e1e86c5c1a35cff2afc2224fc5fd24e"
     },
     {
       "path": "skills/search-lit/references/parse_pubmed.py",
@@ -5468,8 +5478,8 @@
     },
     {
       "path": "skills/sync-submission/SKILL.md",
-      "size": 40770,
-      "sha256": "016b88b1d495a094104d7154724632178751f843623683fb8ebe447735ff5557"
+      "size": 40790,
+      "sha256": "45b228823952b028f0ec8160cd3e457f95b37a0a8fe692a09349a49d1e91054a"
     },
     {
       "path": "skills/sync-submission/references/journal_availability_policy.json",
@@ -5828,8 +5838,8 @@
     },
     {
       "path": "skills/verify-refs/scripts/verify_refs.py",
-      "size": 49238,
-      "sha256": "5e631278ab1b38960d6ba1865cc360855fb2d600024fb67a8e3a9c5a82d5ba9c"
+      "size": 49027,
+      "sha256": "289a91883045bbc38d8e16f65d3e858a106edbb3413ecf6e2d723f353b733362"
     },
     {
       "path": "skills/verify-refs/skill.yml",

package/metadata/distribution_manifest.json

@@ -1,6 +1,6 @@
 {
   "schema_version": 1,
-  "version": "5.26.0",
+  "version": "5.26.2",
   "owned_skills": [
     "academic-aio",
     "add-journal",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "medsci-skills",
-  "version": "5.26.0",
+  "version": "5.26.2",
   "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

@@ -43,7 +43,8 @@ python fetch_oa.py dois.txt -o pdfs/ -e your@email.com --verbose
 10.1002/mp.12524
 ```
 
-**TSV / CSV with header** — must contain a `DOI` column; optional `PMID` and `Title` columns:
+**TSV / CSV with header** — must contain a `DOI` column; optional `PMID`, `Title`, and
+`FirstAuthor` columns (first author's surname or full name for corroboration):
 ```tsv
 ID	Title	DOI	PMID	Year
 1	Some paper	10.1007/s00330-010-1783-x	20628747	2010
@@ -56,7 +57,9 @@ ID	Title	DOI	PMID	Year
 | 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).
+When a PMID is available, the PMC lookup is more reliable (PMID → PMCID conversion).
+Supply `Title` where available: a DOI-only worklist can download a PDF but cannot
+establish title agreement. `FirstAuthor` is optional additional evidence.
 
 ## PMC Download (JS-Challenge Resistant)
 
@@ -100,22 +103,54 @@ override with `--report PATH`):
 
 ```json
 {
-  "schema_version": 1,
+  "schema_version": 2,
   "generated_by": "fetch_oa.py",
-  "counts": {"total": 10, "retrieved": 6, "not_retrieved": 4, "title_mismatch": 1},
+  "counts": {"total": 4, "retrieved": 3, "not_retrieved": 1, "title_mismatch": 1,
+             "source_identity": {"consistent": 1, "conflict": 1, "unresolved": 1, "unavailable": 1}},
   "items": [
-    {"doi": "10.1007/...", "pmid": "20628747", "title": "...",
-     "status": "oa", "source": "unpaywall", "file": "10.1007_....pdf",
-     "size_bytes": 482113, "title_match": "match"}
+    {"doi": "10.1000/synthetic.example", "pmid": "", "title": "Example title",
+     "first_author": "", "status": "oa", "source": "unpaywall",
+     "file": "10.1000_synthetic.example.pdf", "size_bytes": 482113,
+     "file_sha256": "<SHA-256 of the downloaded file>", "title_match": "match",
+     "source_identity": {"status": "consistent", "reason": "title_and_identifier_agree",
+                         "text_scope": "first_page_front_matter", "title_match": "match",
+                         "doi_match": "match", "observed_identifiers": ["10.1000/synthetic.example"],
+                         "first_author_match": "unavailable"}}
   ]
 }
 ```
 
-- `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).
+The example abbreviates `items`. Legacy `status` (`arxiv | oa | pmc | skip | fail`),
+`source`, and `counts.retrieved` retain their resolver-result meaning, including existing
+files (`skip`). **They do not count identity-verified papers.** Report schema 2 adds the
+file hash and separate identity evidence; no PDF is automatically deleted or rejected.
+
+| `source_identity.status` | Meaning / action |
+|---|---|
+| `consistent` | Complete normalized title and a compatible DOI/arXiv identifier occur in the bounded first-page front matter; an optional supplied author must also match. Evidence agrees, but this is not independent source verification or claim validation. |
+| `conflict` | Both the title and observed identifier differ. Inspect the PDF and requested record. |
+| `unresolved` | Evidence is incomplete or ambiguous: title-only, DOI-only, missing author, multiple identifiers, or a matching title with another DOI/version. Inspect before using as evidence. |
+| `unavailable` | No usable extracted text, Poppler unavailable, no output PDF, or the PDF changed during assessment. No current identity assessment was possible. |
+
+`title_match` keeps its tri-state shape. A `match` now requires the complete normalized
+title on up to six consecutive front-matter lines. Case, punctuation and line wrapping
+are normalized. Scattered matching words cannot establish a match; partial overlap is
+`unavailable`, and low overlap is an advisory `mismatch`.
+
+Evidence is limited to the first page, before a recognized abstract/body/reference
+heading, at most 40 lines / 4,000 characters. Thus a title cited in the body or references
+does not establish a title match. These are conservative layout heuristics: cover sheets,
+unrecognized headings, short or changed titles, unusual reading order and DOI footers
+outside that area can remain unresolved. PDF metadata and the filename alone are not
+identity evidence. The CLI compares hashes before extraction and when reporting;
+changed files cannot inherit the previous text's assessment. Explicit arXiv versions
+must agree; preprint/published-version DOI
+differences require review rather than automatic rejection.
+
+Downstream reports must preserve `source_identity` and `file_sha256`, keep unresolved
+items visible, and check the hash still identifies the file being used. Older reports
+without identity evidence remain **unassessed**; do not infer identity from `retrieved`
+or `title_match=match`. Full-text conversion does not resolve an identity warning.
 
 ## Attach PDFs into Zotero ("Find Available PDF")