medsci-skills 5.23.0 → 5.24.0

package/README.md

@@ -301,6 +301,8 @@ The E2E pipeline (`orchestrate --e2e`) produces everything up to `qc/`. The `sub
 
 ## What's New
 
+**v5.24.0** — a precision release: the gates were wrong about correct work. Fourteen shipped detectors were telling users something false, and the pattern behind most of them is one thing — a checker that accepts only its own generator's output and rejects the notation the world actually uses. `check_xref` did not recognise **"Figures 1 and 2"**, so a float cited the ordinary way scored `UNCITED` and the submission blocker **turned itself off** (`submission_safe: true` on a package missing a figure). `verify_refs` read BibTeX's own **`and others`** — the et-al. every reference manager writes — as `AUTHOR MISMATCH`, the render-aborting verdict, on correct consortium references; and an entry whose **last** field was the DOI parsed as having none, silently disabling the CrossRef and author cross-checks that skill exists to perform. `check_table_percentages` **invented a denominator** for the most common table in clinical research and printed specific wrong replacement percentages at MAJOR. `lint_consistency` advised writing **"type two diabetes"**. `check_asset_anonymization` passed a **double-blind institution leak** because it sat in a `.yaml`. `check_slide_tells` flagged the page numbers **this repository's own template generator** writes. `fill_journal_abbrev.py` had **never run** — it raised on its first entry, for every input, while another gate named it to the user as the remedy. And `refinement_stop` called a leftover `TODO` an *optional Minor* and told the loop to stop. Also: the release job's own failure had left v5.23.0 with **zero assets** and npm a version behind, with no way to retry a pushed tag — now create-or-update, outcome-asserted, and dispatchable; two of the four documented install paths were broken, and the worse one **succeeded** while making `~/.claude/skills` itself the skill; and the front page said **36** detectors while the catalog, the audit document and the paper said 84. Every fix ships a regression test that goes red against the previous behaviour. No new skill or detector; **58 skills / 47 guidelines / 84 integrity detectors / 23 domain-probe modules**. (See the [CHANGELOG](CHANGELOG.md) for v5.0–v5.23.)
+
 **v5.21** — verification-layer batch, mostly promoted from real submission failures. A **marked (tracked-changes) manuscript** is now built by driving Word's Compare from the command line and proved by a **round trip** — accepting every revision must reproduce the revised paper exactly, rejecting every revision must reproduce the original — and the gate is **move-aware**, because Word encodes a relocated paragraph as `w:moveFrom`/`w:moveTo` and an insert-and-delete-only verifier calls a good file corrupt. Every detector's `qc/*.json` now **names the detector that wrote it**, so an artifact can be traced back to the check that produced it (a CI-enforced contract). Two `/verify-refs` precision defects: a Unicode hyphen in a surname fired `MISMATCH` — the verdict that means *fabricated author* — on a correct reference, and a Better BibTeX brace-protected surname was read as a corporate author, **silently skipping** the author check the tool exists to perform. New gates: publisher markup in a `.bib` title (`<scp>WHO</scp>` renders as garbage and no gate looked at the printed title), **complete/quasi separation** before a logistic model is fitted (a pathognomonic sign has an empty cell by construction; `glm` returns OR = 0.00, *p* = 0.99, and an AUC that gets reported), and a probe + gate for manuscripts claiming a system **improved itself** (which rung of the verification hierarchy said so?). `/find-cohort-gap` now accepts a **local codebook** — an institutional registry or EMR export, not only a named public cohort — enumerating variables verbatim with provenance rather than letting a model summarise them. Additive and backward-compatible; **55 skills / 46 guidelines / 61 integrity detectors / 23 domain-probe modules**. (See the [CHANGELOG](CHANGELOG.md) for v5.0–v5.20.)
 
 **v5.20.1** — audit-driven coherence fixes. A real `/orchestrate --e2e` state-transition bug (the pipeline halted at step 3 because it required a DOCX that is only rendered at step 7), all 55 skills made routable from the single entry point with a CI reachability gate, and a README plugin-count that had drifted from the marketplace SSOT (now gated). No skill/detector change.
@@ -416,7 +418,7 @@ Earlier in this series: analysis-integrity guards (confounding completeness, cla
 | **Battle-tested** | Used on real manuscript submissions by a practicing physician-researcher | Unknown provenance and validation |
 | **Depth per skill** | 150-600 lines of documentation + bundled reference files (curated journal profile library, checklists, formula sheets, code templates) | Typically thin SKILL.md templates |
 
-**MedSci-Audit** — the verification edge in the first rows above is a named suite of **36 deterministic detectors** (citation & reference integrity, cohort & pool arithmetic, scope/estimand contracts, reporting compliance, and more) that catch fabricated or drifted content before a manuscript reaches a reviewer. See **[`MEDSCI_AUDIT.md`](MEDSCI_AUDIT.md)** for the suite, its six families, and its evaluation evidence.
+**MedSci-Audit** — the verification edge in the first rows above is a named suite of **84 deterministic detectors** (citation & reference integrity, cohort & pool arithmetic, scope/estimand contracts, reporting compliance, and more) that catch fabricated or drifted content before a manuscript reaches a reviewer. See **[`MEDSCI_AUDIT.md`](MEDSCI_AUDIT.md)** for the suite, its six families, and its evaluation evidence.
 
 ---
 
@@ -592,6 +594,7 @@ MedSci Skills가 설치됐는지 확인하고, 오늘 실습에 쓸 대표 스
 
 ```bash
 git clone https://github.com/Aperivue/medsci-skills.git
+mkdir -p ~/.claude/skills
 cp -r medsci-skills/skills/* ~/.claude/skills/
 ```
 
@@ -599,6 +602,7 @@ cp -r medsci-skills/skills/* ~/.claude/skills/
 
 ```bash
 git clone https://github.com/Aperivue/medsci-skills.git
+mkdir -p ~/.claude/skills
 cp -r medsci-skills/skills/check-reporting ~/.claude/skills/
 ```
 

package/metadata/distribution_files.json

@@ -83,8 +83,8 @@
     },
     {
       "path": "skills/academic-aio/SKILL.md",
-      "size": 32276,
-      "sha256": "d893714e70af45b6f9d162d5220875685995e4a2c428331348689566e672989c"
+      "size": 32767,
+      "sha256": "5ed6874b7aa1036b1867f96149247eebffb2e61332c39696027811530de5282f"
     },
     {
       "path": "skills/academic-aio/references/ai_tool_citation_framing.md",
@@ -633,8 +633,8 @@
     },
     {
       "path": "skills/check-reporting/SKILL.md",
-      "size": 39537,
-      "sha256": "0a291a80d8d98e2930683990bdfde14bff341a900f79a7b002f167cda86c1226"
+      "size": 40028,
+      "sha256": "8b0de01f805febed31de0218f64ebcbde0cc8b5fb89efb7ace3bab79c468b270"
     },
     {
       "path": "skills/check-reporting/references/LICENSES.md",
@@ -1028,8 +1028,8 @@
     },
     {
       "path": "skills/define-variables/SKILL.md",
-      "size": 10800,
-      "sha256": "10d32f068440d9b55b26c884e0bbd0f183cbceb52d3ec8c078d18d9dd23851d8"
+      "size": 11291,
+      "sha256": "bcbc6775dbb73d0e456076796764f1c540704c47dcc08ba98c8dae7b3b4a06d2"
     },
     {
       "path": "skills/define-variables/references/common_definitions.md",
@@ -1396,6 +1396,11 @@
       "size": 6869,
       "sha256": "620ba1c55272908a16125ba69074491df5246d6cf9afa14e6b08a08e8dc4e866"
     },
+    {
+      "path": "skills/find-journal/references/journal_profiles/AJKD.md",
+      "size": 1764,
+      "sha256": "4852b353847a9fa166a9b874be9cd4dc90231e791a3b4ca86835872fcf54c0f1"
+    },
     {
       "path": "skills/find-journal/references/journal_profiles/AJNR.md",
       "size": 1451,
@@ -1551,6 +1556,11 @@
       "size": 1796,
       "sha256": "0bd38b7ae4139a856c6aba5917d3444e2e86e16bb0a5f7f41869600174e00648"
     },
+    {
+      "path": "skills/find-journal/references/journal_profiles/JASN.md",
+      "size": 2133,
+      "sha256": "5f7311ff8e8270caaaf8a3c22a16cf185a6cb034f58f222ca3ca1f60c635eb79"
+    },
     {
       "path": "skills/find-journal/references/journal_profiles/JCSM.md",
       "size": 3969,
@@ -1616,6 +1626,11 @@
       "size": 4061,
       "sha256": "0849de001a47038b8bfc92b337285372c80ccf4861162cae876295d82ea4f1c8"
     },
+    {
+      "path": "skills/find-journal/references/journal_profiles/Kidney_International.md",
+      "size": 1871,
+      "sha256": "60792a1f6b5466bb7ca740904f123c62cb54c9ddb7cea422a89ed2768d02b51d"
+    },
     {
       "path": "skills/find-journal/references/journal_profiles/Korean_Circulation_Journal.md",
       "size": 2567,
@@ -1888,8 +1903,8 @@
     },
     {
       "path": "skills/humanize/SKILL.md",
-      "size": 18644,
-      "sha256": "9bdaaa4d13c360022388b89c9fdc4fb16864ffa2d999e815f2acf48f6b7c9dcb"
+      "size": 19135,
+      "sha256": "0372a021d140a8fb6be3ab5eac67ef8cdcb6e525f0c5b8202e259dfe42ad5d3f"
     },
     {
       "path": "skills/humanize/references/ai_patterns.md",
@@ -1903,8 +1918,8 @@
     },
     {
       "path": "skills/humanize/scripts/check_sentence_variety.py",
-      "size": 7643,
-      "sha256": "a5091ebca81761341e95d61b01b9998e637763f414c22d31eec658f6b6376835"
+      "size": 10498,
+      "sha256": "aeb0ac10a9889087301206c2024dc90368bd6165547023594646e5d403e2c473"
     },
     {
       "path": "skills/humanize/skill.yml",
@@ -1958,8 +1973,8 @@
     },
     {
       "path": "skills/make-figures/SKILL.md",
-      "size": 47581,
-      "sha256": "0d3955068a6bbe1d8b3be5b4d6fcb09636c87b65147793500c49330a49df9619"
+      "size": 48072,
+      "sha256": "e343de9c90b9d36dae85a580305daa6cb769f67e0f8484f2db0365b64f2e37ad"
     },
     {
       "path": "skills/make-figures/references/critic_rubrics/data_plot.md",
@@ -2488,19 +2503,24 @@
     },
     {
       "path": "skills/manage-refs/SKILL.md",
-      "size": 19110,
-      "sha256": "1f23594657e523540fafb94b0292d73604df0c3348c6fb569334978dcdbed4ac"
+      "size": 20729,
+      "sha256": "16a7ddf4412580c0797baa52821054114f434b82b302a6d67fec023d56427a8d"
     },
     {
       "path": "skills/manage-refs/citation_styles/README.md",
-      "size": 2205,
-      "sha256": "d957bbdd13df10884fd54f9eb4efb096a73824c69167f872b0cb9819be031cdf"
+      "size": 4358,
+      "sha256": "b8935886559c1491a8aa06f8f809f82a492bfc0fceb4b32f2fbc19ccc379e83f"
     },
     {
       "path": "skills/manage-refs/citation_styles/american-journal-of-roentgenology.csl",
       "size": 6944,
       "sha256": "62db40358fd006af9109490ba358489096d18a8d48026077ed4502e5d44af61a"
     },
+    {
+      "path": "skills/manage-refs/citation_styles/american-medical-association.csl",
+      "size": 11575,
+      "sha256": "d70f843d93c2b1e8c59c0e26e2396bea4ed99fb4a1aac69b6dddc249a10fadf7"
+    },
     {
       "path": "skills/manage-refs/citation_styles/cardiovascular-and-interventional-radiology.csl",
       "size": 1299,
@@ -2578,8 +2598,8 @@
     },
     {
       "path": "skills/manage-refs/references/check_xref_symptoms.md",
-      "size": 2426,
-      "sha256": "f3261841492aba9812529419b351cb77e07c49f3da7156773299048f51d9deee"
+      "size": 4501,
+      "sha256": "4d0da877aca64367cbf13fa8b1008f39b0f258648a5e2a955ca5b8fc8915236f"
     },
     {
       "path": "skills/manage-refs/scripts/_vendor_citation_writer.py",
@@ -2593,8 +2613,8 @@
     },
     {
       "path": "skills/manage-refs/scripts/check_citation_keys.py",
-      "size": 4125,
-      "sha256": "b336b661b9d68e42d8829f017d2d55fba22585de6f9d59e2441ffc1c7f5ba3a7"
+      "size": 6593,
+      "sha256": "acf0b653df453ef3d9ed905f09656212ae5f8de6471a19cde52ca415b980fb47"
     },
     {
       "path": "skills/manage-refs/scripts/check_citation_keys_challenge/fixture/manuscript.md",
@@ -2628,13 +2648,13 @@
     },
     {
       "path": "skills/manage-refs/scripts/check_xref.py",
-      "size": 24044,
-      "sha256": "e7f035af887c581eb98b57c865b2ed358b541091c30deeb8e6652145f0929acf"
+      "size": 31099,
+      "sha256": "13d89487a740fdac9b55f6f92d8228fea2c7ae4b8d1c32f96bab3616be8a5b32"
     },
     {
       "path": "skills/manage-refs/scripts/fill_journal_abbrev.py",
-      "size": 4533,
-      "sha256": "2782190044944526e1f27572062192466b34e116a4a50c9f3aecc59117b06e6e"
+      "size": 5370,
+      "sha256": "a9d6ceab5a12832c3cbf9a329afef4afa9ed4964ad0e2a34dc5fa7ced5646bd1"
     },
     {
       "path": "skills/manage-refs/scripts/inject_zotero_cwyw.py",
@@ -2648,8 +2668,8 @@
     },
     {
       "path": "skills/manage-refs/scripts/pre_submission_gate.sh",
-      "size": 8932,
-      "sha256": "73ae8e4f32c9fc6d3676d3f4a5b41a74ad7dc2c9f5f5e39d4d5ec7c2e4fcbfb5"
+      "size": 9309,
+      "sha256": "b306abe55ea639cdf2d4044db4af70d9450b8ec2dfa3b5b78e9222966e8bd97a"
     },
     {
       "path": "skills/manage-refs/scripts/render_pandoc.sh",
@@ -2743,8 +2763,8 @@
     },
     {
       "path": "skills/meta-analysis/references/phase4_extraction_detail.md",
-      "size": 11199,
-      "sha256": "6aee96c0d9ab99e1a014d849de2e6b6fb711e673b96e6eb593fd56afe16c10e3"
+      "size": 11216,
+      "sha256": "ab7a10591f6c6c49e70ad6ba68061fcb5ed0d9435b8fdb8746f7042e31a39220"
     },
     {
       "path": "skills/meta-analysis/references/phase4_km_composite.md",
@@ -3248,8 +3268,8 @@
     },
     {
       "path": "skills/orchestrate/SKILL.md",
-      "size": 41275,
-      "sha256": "f128ee6ccd96d7c3ada6d50f0da2856d73ce01824668e9f839153349bf56d24d"
+      "size": 41766,
+      "sha256": "c3deb040d4d8e7881b32210513b93e1629e0a25e25ab8fa8e45e21ca531c0f51"
     },
     {
       "path": "skills/orchestrate/references/dialogue_nodes.md",
@@ -3273,8 +3293,8 @@
     },
     {
       "path": "skills/peer-review/SKILL.md",
-      "size": 81126,
-      "sha256": "d1783e25bcd55642cb42c200ef4151525758e1080a498e4ba6db01b54b036a98"
+      "size": 81702,
+      "sha256": "18d9c54589be0e30086b43ff50ac285815e1e852ae527905cf2225977492c35d"
     },
     {
       "path": "skills/peer-review/references/aczel_2021_reviewer2_patterns.md",
@@ -3343,8 +3363,8 @@
     },
     {
       "path": "skills/peer-review/references/domain-probes/observational_confounding.md",
-      "size": 35839,
-      "sha256": "32343fb2ed0d20cb76593c8d07842d0628ce363a7c24a6739f10fa29b37e6398"
+      "size": 36257,
+      "sha256": "6f1933d4314308dd9131c6c5baa16553270c1f406a9ac1077562fcc41958667b"
     },
     {
       "path": "skills/peer-review/references/domain-probes/polygenic_risk_score.md",
@@ -3603,8 +3623,8 @@
     },
     {
       "path": "skills/polish-language/scripts/lint_consistency.py",
-      "size": 13850,
-      "sha256": "ed6067e9d8968dec7d913aec92be06676d1d250aaee613b390355dcb872392c1"
+      "size": 15665,
+      "sha256": "f380439fae1fd41b966862957ca4232467a1d1701dd5a19c35c1864b3df9aea2"
     },
     {
       "path": "skills/polish-language/scripts/lint_figure_locale.py",
@@ -3678,8 +3698,8 @@
     },
     {
       "path": "skills/present-paper/SKILL.md",
-      "size": 39097,
-      "sha256": "da139de9b1633bc789b8f3e59f72aa315186192351fccfdbcfcb3f99405db993"
+      "size": 39588,
+      "sha256": "d7179b91b4b1146302731ce6b8fb9d114171040748a403162213bebb07f00b61"
     },
     {
       "path": "skills/present-paper/references/ai_slide_tells.md",
@@ -3768,8 +3788,8 @@
     },
     {
       "path": "skills/present-paper/scripts/check_slide_tells.py",
-      "size": 24730,
-      "sha256": "3b91a0f6850b2badaf1657208a779b892931f50ae4962a7c7ccdfc50836a5396"
+      "size": 26077,
+      "sha256": "7f41906b49d38663cc64de2f9dea69208d73f7f45648b4b65c294efbc88de831"
     },
     {
       "path": "skills/present-paper/scripts/check_slide_tells_challenge/make_fixtures.py",
@@ -3948,8 +3968,8 @@
     },
     {
       "path": "skills/render-pdf-doc/SKILL.md",
-      "size": 8300,
-      "sha256": "fad21da8e60907c212b6d216ffe591502941c8defa4ce212b521306e00332836"
+      "size": 9236,
+      "sha256": "97af21fac95af6dcd0e47bc6a547f6413f47d431c74d310174899c36cb86da17"
     },
     {
       "path": "skills/render-pdf-doc/references/known_pitfalls.md",
@@ -4068,8 +4088,8 @@
     },
     {
       "path": "skills/revise/SKILL.md",
-      "size": 31941,
-      "sha256": "3d6bd4fa1db09d6bae88a2e7b8470f3494df8f4c03d45abba924184ead3977bc"
+      "size": 32217,
+      "sha256": "a6694b2dac943f65ae0690085ae2951bb9107f42ba429b668829d63bdc154a51"
     },
     {
       "path": "skills/revise/references/r2r_voice.md",
@@ -4183,8 +4203,8 @@
     },
     {
       "path": "skills/self-review/SKILL.md",
-      "size": 61424,
-      "sha256": "fcaa491e8b90fda1a017b4b9fde584f9abbab58c3b32c0a10734593f238097ee"
+      "size": 62498,
+      "sha256": "891b019237132a910e1157a9f0d6e5ac58bcab2a7077ab969b68e95e3ae5a63b"
     },
     {
       "path": "skills/self-review/references/domain-probes/ai_overclaiming.md",
@@ -4248,8 +4268,8 @@
     },
     {
       "path": "skills/self-review/references/domain-probes/observational_confounding.md",
-      "size": 35839,
-      "sha256": "32343fb2ed0d20cb76593c8d07842d0628ce363a7c24a6739f10fa29b37e6398"
+      "size": 36257,
+      "sha256": "6f1933d4314308dd9131c6c5baa16553270c1f406a9ac1077562fcc41958667b"
     },
     {
       "path": "skills/self-review/references/domain-probes/polygenic_risk_score.md",
@@ -4373,8 +4393,8 @@
     },
     {
       "path": "skills/self-review/references/phases/phase2_5d_xref_qc.md",
-      "size": 4974,
-      "sha256": "81756d0713842faa1f603a34500dd6aaa699be6526ee6fbbc1ace06467b10143"
+      "size": 5639,
+      "sha256": "5a574035962626a5a758a335906414c709f2d5cb04b3ac5c5e7dfefa7ba6f8b5"
     },
     {
       "path": "skills/self-review/references/phases/phase2_5f_claim_artifact.md",
@@ -4413,8 +4433,8 @@
     },
     {
       "path": "skills/self-review/scripts/_qc_findings.py",
-      "size": 3187,
-      "sha256": "eac1b20db8c5c66d12243602e9272d60e1fcc9ef3ed0046d5081a74ef33a9343"
+      "size": 6409,
+      "sha256": "f8426cd3bdfb7c80796956b8d7e85afe5ba77a3b6df5a8f0f1fe92be0446d6b4"
     },
     {
       "path": "skills/self-review/scripts/check_analysis_definitions.py",
@@ -4528,8 +4548,8 @@
     },
     {
       "path": "skills/self-review/scripts/check_claim_artifact.py",
-      "size": 22106,
-      "sha256": "890ba1834c86d864e40c4ad3c9afb7db6824ffb5f50c2b8896b2a9bbea611ab0"
+      "size": 22558,
+      "sha256": "98e7fa5cc5539d753e5cdd429d9640a63ab149606c85f57f51c4fbe5b128bbcf"
     },
     {
       "path": "skills/self-review/scripts/check_classical_style.py",
@@ -4633,8 +4653,8 @@
     },
     {
       "path": "skills/self-review/scripts/check_figure_citation.py",
-      "size": 11137,
-      "sha256": "92847a5ca4faf32b94bceaf4369a6a9ca4c83a5aaa503606dd7b581c0770e093"
+      "size": 12859,
+      "sha256": "831aa1ef79cf6d2311adf4c9f97c766084d472b7e6dfa17e7f4f70b31ea89b43"
     },
     {
       "path": "skills/self-review/scripts/check_figure_citation_challenge/fixture/panel_regression.md",
@@ -4898,8 +4918,8 @@
     },
     {
       "path": "skills/self-review/scripts/check_table_percentages.py",
-      "size": 8760,
-      "sha256": "32405faecca4b8c28a38a90d272d8849c0451c048938440301bfe9a732d99a37"
+      "size": 11061,
+      "sha256": "faeed0132193a9bc3ca90d061d6e2d185a2e29d50b46165154e76d43edd90d5f"
     },
     {
       "path": "skills/self-review/scripts/check_table_percentages_challenge/expected/bad.txt",
@@ -5093,8 +5113,8 @@
     },
     {
       "path": "skills/self-review/scripts/refinement_stop.py",
-      "size": 9006,
-      "sha256": "3da6d19311211c4be42984bd0d0d1a134f770e70a4746a8853bc6409458f9ae6"
+      "size": 9684,
+      "sha256": "ba3f88d4eff6d35bf8d3ca56994ca5f56b060b414918efd5f6ee2343d6f2ec20"
     },
     {
       "path": "skills/self-review/scripts/refinement_stop_challenge/expected/continue.txt",
@@ -5268,8 +5288,8 @@
     },
     {
       "path": "skills/sync-submission/scripts/check_asset_anonymization.py",
-      "size": 13914,
-      "sha256": "a4552caa7bfcfba93c32d1b8f5b24fdcde49b4201768e977cd10a3d8fba06dc0"
+      "size": 14907,
+      "sha256": "9d826fc7f408ccc5d679774cd8e9c8921763b2a0066536b14173610301265587"
     },
     {
       "path": "skills/sync-submission/scripts/check_checklist_dump_leak.py",
@@ -5279,7 +5299,7 @@
     {
       "path": "skills/sync-submission/scripts/check_credit_integrity.py",
       "size": 18645,
-      "sha256": "c0ab9a7aa3008af3d23901ee93a764d01ae46786dbedfc287dc6cf031b7248e1"
+      "sha256": "d67a72305d2f3c1a8d5a823a272171d96db925b64b3cf4ada2997bb81234ebd2"
     },
     {
       "path": "skills/sync-submission/scripts/check_cross_artifact_stale.py",
@@ -5338,8 +5358,8 @@
     },
     {
       "path": "skills/sync-submission/scripts/check_wordcount_cap.py",
-      "size": 9827,
-      "sha256": "4d1c3403efeb4d891c4558d6e784c4088a0d349aad1625f1c348e50665c17f8d"
+      "size": 11299,
+      "sha256": "93b251185bd2168f4d50161e3d0b3c9d2a8f7b2fa36973b01bc89caf194160ee"
     },
     {
       "path": "skills/sync-submission/scripts/cover_letter_drift_check.py",
@@ -5588,8 +5608,8 @@
     },
     {
       "path": "skills/verify-refs/scripts/verify_refs.py",
-      "size": 44683,
-      "sha256": "8b1bfee367b638cd49f5b6f92bfb353edef05ec71b5a9d8b44be9c5aa475b100"
+      "size": 47979,
+      "sha256": "4631625bb9a5bb2514d6c3f910d1f6d1cf443710e8aec554e5d35522ca6deebb"
     },
     {
       "path": "skills/verify-refs/skill.yml",
@@ -5618,8 +5638,8 @@
     },
     {
       "path": "skills/write-paper/SKILL.md",
-      "size": 49536,
-      "sha256": "a36ddb90db795de04bca34a4623c62be128305b023e42b256bedc0a0c16a5774"
+      "size": 50120,
+      "sha256": "6ac3072d67dfabfaeae11a0bf1890e9d616d073cd56b0758669d3b3f4ff59c50"
     },
     {
       "path": "skills/write-paper/references/exemplar_abstract.md",
@@ -5731,6 +5751,11 @@
       "size": 2356,
       "sha256": "6a0becfe8f24db7f686bd23f26c9caec749dd996914705679ea915398fc7c3dd"
     },
+    {
+      "path": "skills/write-paper/references/journal_profiles/AJKD.md",
+      "size": 5809,
+      "sha256": "b0183fb94e2cb41a534807b0cb79e861683aee00e95b6850e3ddcb5036e15014"
+    },
     {
       "path": "skills/write-paper/references/journal_profiles/AJNR.md",
       "size": 6381,
@@ -5861,6 +5886,11 @@
       "size": 8114,
       "sha256": "0b7c00a4cf1616e134cfe3fff0d389268d275c0795f233733d685f56fc3018f9"
     },
+    {
+      "path": "skills/write-paper/references/journal_profiles/JASN.md",
+      "size": 6619,
+      "sha256": "9f64bc923ec708e10f514636fa31cac57f1611167304ea9d4d86920a18b6bd58"
+    },
     {
       "path": "skills/write-paper/references/journal_profiles/JCSM.md",
       "size": 13680,
@@ -5906,6 +5936,11 @@
       "size": 13088,
       "sha256": "42d45781f252ada19a4086f200c407bd3c85d3d9a88c30151d9c14390616354d"
     },
+    {
+      "path": "skills/write-paper/references/journal_profiles/Kidney_International.md",
+      "size": 5538,
+      "sha256": "d370e1706d7e9972d2764ce1321d930ba7d6f006fae873019a49c6fdcd10c84e"
+    },
     {
       "path": "skills/write-paper/references/journal_profiles/Korean_Circulation_Journal.md",
       "size": 8764,
@@ -6068,8 +6103,8 @@
     },
     {
       "path": "skills/write-paper/references/phase7_polish_detail.md",
-      "size": 19036,
-      "sha256": "5c44f6ccdfc6eaa64587c62d68fe0911175e6df7a37bfc7f71b65a7f6d5a1c12"
+      "size": 19696,
+      "sha256": "ca5d6c1c900d9ef0b4659d18daabdc3322bba3ecef3ec5955e9dc76de958f7e9"
     },
     {
       "path": "skills/write-paper/references/section_guides/discussion.md",
@@ -6113,8 +6148,8 @@
     },
     {
       "path": "skills/write-paper/scripts/build_title_page_affiliations.py",
-      "size": 11749,
-      "sha256": "d42dfe6972f04103f61f47f1f7774d534117e1538024c336240f505f1c436112"
+      "size": 11723,
+      "sha256": "ff1b29d66c8272c62423f7c31f945041ce2c097b0452097fd88f25777641a3db"
     },
     {
       "path": "skills/write-paper/scripts/check_placeholders.py",
@@ -6133,8 +6168,8 @@
     },
     {
       "path": "skills/write-protocol/SKILL.md",
-      "size": 11089,
-      "sha256": "2df7b2e5827fd2f6d4c0126c63e26f18c03bf94163af0f59c661ae85ec86b7af"
+      "size": 11580,
+      "sha256": "3d2041be27da4aa32c648ae4eba6036fdcb99a648ab003721ccfaf7c93bd2c06"
     },
     {
       "path": "skills/write-protocol/references/ethics_checklist.md",

package/metadata/distribution_manifest.json

@@ -1,6 +1,6 @@
 {
   "schema_version": 1,
-  "version": "5.23.0",
+  "version": "5.24.0",
   "owned_skills": [
     "academic-aio",
     "add-journal",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "medsci-skills",
-  "version": "5.23.0",
+  "version": "5.24.0",
   "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/academic-aio/SKILL.md

@@ -411,3 +411,11 @@ Section 3.5 (post-acceptance channel checklist) is unordered; Section 12 prescri
 - **Never fabricate discoverability metrics** (Perplexity/Elicit/Consensus retrieval scores) — only report observed behavior from a recorded probe.
 - **Never auto-complete author lists, ORCIDs, or affiliations** in CITATION.cff or Zenodo metadata; surface empty slots to the user.
 - If a compliance item, journal policy, or AI-search platform behavior is uncertain, state the uncertainty rather than guessing.
+
+## Global-rule references
+
+Some passages in this skill cite a path of the form `~/.claude/rules/<name>.md`. Those are the
+maintainer's personal global rules, kept outside this repository. They are **not shipped with
+this skill** and will not exist on your machine; they appear only as provenance for where a
+convention came from. If one of them looks like it is standing in for an instruction you actually
+need, that is a bug — please open an issue, because the instruction belongs here.

package/skills/check-reporting/SKILL.md

@@ -540,3 +540,11 @@ Page numbers should be filled in by the user after final formatting. Use section
 | Step 4d PRISMA Figure 1 arithmetic & cross-reference audit (PRISMA / PRISMA-DTA only) | ENFORCED for SR/MA | flow numbers don't sum (e.g., screened ≠ included + excluded), or in-text counts mismatch flow diagram | HALT; reconcile against extraction artifacts |
 | Optional items (e.g., supplementary AI declarations) | ADVISORY | < 80% of optional items present | warn; user accepts |
 | Cross-reporting-guideline routing (study type → guideline) | ENFORCED | study type undeclared or guideline missing | Ask user; do not silently default |
+
+## Global-rule references
+
+Some passages in this skill cite a path of the form `~/.claude/rules/<name>.md`. Those are the
+maintainer's personal global rules, kept outside this repository. They are **not shipped with
+this skill** and will not exist on your machine; they appear only as provenance for where a
+convention came from. If one of them looks like it is standing in for an instruction you actually
+need, that is a bug — please open an issue, because the instruction belongs here.

package/skills/contribute/tests/test_contribution_safety.sh

@@ -38,8 +38,8 @@ The pipeline failed on patient MRN 4471903 during the review.
 Subject 880101-1234567 was excluded after chart review.
 Approved under IRB 2024-0451 at Severance Hospital.
 I was reviewing EURE-D-26-00203 when this happened.
-Prof. Kim Namkuk suggested the change; reach me at yj.nam@hospital.or.kr.
-Output was written to /Users/yoojinnam/manuscripts/draft.docx.
+Prof. Alan Poe suggested the change; reach me at a.poe@hospital.or.kr.
+Output was written to /Users/apoe/manuscripts/draft.docx.
 MD
 
 # --- an ordinary, entirely publishable contribution -------------------------------------------

package/skills/define-variables/SKILL.md

@@ -144,3 +144,11 @@ Every variable definition, cutoff, and era anchor must be grounded in a verified
 4. **Silent ad-hoc** — introducing a novel cutoff without the `Ad-hoc: yes` flag.
 5. **Sweep-style /search-lit** — running a generic lit search instead of one focused query per gap variable. Wastes tokens and buries the signal.
 6. **Dose/duration structural-missingness** — operationalizing a dose/duration covariate (pack-years, cessation-years, alcohol grams/week) anchored to a categorical exposure (smoking status, alcohol use) without specifying what the *reference level* (never-smoker, never-drinker) does to the dose. A never-smoker's pack-years is a structural zero, not a missing value; conflating the two collapses the analytic sample under complete-case modeling and lets MICE fabricate a non-zero dose for the unexposed. Operationalize it explicitly — add a row with `Role = covariate` and `Implementation = "IF status == 'never' THEN dose = 0 ELSE measured_value"` — and adjust on the categorical **status** variable, reserving the continuous **dose** for an exposed-only secondary analysis. `/clean-data` (categorical-implied-zero flag) and `/analyze-stats` ("Covariate Pitfalls") enforce this downstream.
+
+## Global-rule references
+
+Some passages in this skill cite a path of the form `~/.claude/rules/<name>.md`. Those are the
+maintainer's personal global rules, kept outside this repository. They are **not shipped with
+this skill** and will not exist on your machine; they appear only as provenance for where a
+convention came from. If one of them looks like it is standing in for an instruction you actually
+need, that is a bug — please open an issue, because the instruction belongs here.

package/skills/find-journal/references/journal_profiles/AJKD.md

@@ -0,0 +1,34 @@
+# American Journal of Kidney Diseases
+
+## Identity
+- **Abbreviation:** Am J Kidney Dis
+- **Publisher:** Elsevier (NKF)
+- **ISSN:** 0272-6386 / 1523-6838
+- **Homepage:** https://www.ajkd.org
+- **Author guidelines:** https://www.ajkd.org/content/authorinfo
+
+## Scope
+AJKD is a premier clinical nephrology journal, publishing clinical investigations, epidemiologic studies, health services research, clinical trials, and educational articles. It is highly valued for translating clinical research into actionable kidney care.
+
+## Scope Keywords
+clinical nephrology, chronic kidney disease, acute kidney injury, hemodialysis, peritoneal dialysis, kidney transplantation, hypertension, cardiorenal syndrome, glomerulonephritis, electrolyte disorders, mineral bone disorder, health policy, clinical practice, teaching cases, kidney stones
+
+## Article Types Accepted
+- Original Investigation
+- Research Letter
+- Review
+- Teaching Case
+- Editorial
+
+## Classification
+- **Tier:** Q1
+- **Open Access:** Hybrid
+- **Field:** Nephrology (clinical)
+
+## Special Notes
+AJKD (IF ~10.4) requires a highly specific structured abstract (max 300 words) with headings like Rationale & Objective, Setting & Participants, Predictors, Outcomes, Measurements, and Limitations. Requires a Clinical Summary section at the beginning. AI policy: language editing only, disclose before references, AI images banned.
+
+## Verification
+- **Source:** AJKD Information for Authors — https://www.ajkd.org/article/S0272-6386(11)01206-6/fulltext
+- **Date:** 2026-07-14
+- **Note:** the 300-word abstract limit is quoted verbatim from that page in the PR #330 review (https://github.com/Aperivue/medsci-skills/pull/330#issuecomment-4968075916). The 3,500-word body limit was confirmed on the same page.