medsci-skills 5.10.0 → 5.12.0

package/metadata/distribution_files.json

@@ -153,8 +153,13 @@
     },
     {
       "path": "skills/analyze-stats/SKILL.md",
-      "size": 55302,
-      "sha256": "3809b6a55e8a79b7dc48f617e3be0a7faf2a96a6f0ba03d58977a39f267cce81"
+      "size": 55642,
+      "sha256": "5c4a966490cfb8da6e09ebda897599479bd527d7ee3957ccbfceb5abff06306a"
+    },
+    {
+      "path": "skills/analyze-stats/references/analysis_guides/agreement_reliability.md",
+      "size": 6674,
+      "sha256": "599ad2551f547043b2bec79e3139d9c2c3ae33c5025784359b22022f882504c2"
     },
     {
       "path": "skills/analyze-stats/references/analysis_guides/health_economic_evaluation.md",
@@ -1658,8 +1663,8 @@
     },
     {
       "path": "skills/humanize/SKILL.md",
-      "size": 13461,
-      "sha256": "78e12b996cacfa5b1b16b0a0fe26cee5dd72cb990b70f26e90041d6e0eb65c9a"
+      "size": 14240,
+      "sha256": "f179598c74b1ab0b3d6639fdd26b8cafa33713a9ebe9374aad5d31571340d836"
     },
     {
       "path": "skills/humanize/references/ai_patterns.md",
@@ -2923,8 +2928,8 @@
     },
     {
       "path": "skills/peer-review/SKILL.md",
-      "size": 68213,
-      "sha256": "51feccb82dca34a28a0b9ace5467d23ddc654056af2cd9e152a4559cf074cfc3"
+      "size": 69384,
+      "sha256": "94033b84b41304d7dbd7919c84c7e9502bdaff1b7e2ef8f5dd7ec9cd7147c532"
     },
     {
       "path": "skills/peer-review/references/aczel_2021_reviewer2_patterns.md",
@@ -2933,8 +2938,8 @@
     },
     {
       "path": "skills/peer-review/references/domain-probes/ai_overclaiming.md",
-      "size": 14205,
-      "sha256": "565aa362e20ea6ca923510ea393829fb851e0caaae3d732f99144dd48a25b951"
+      "size": 15410,
+      "sha256": "bdb07002bf0b351579036937af5bf149e35389a218198699b81d31dc2fda7ec9"
     },
     {
       "path": "skills/peer-review/references/domain-probes/case_report.md",
@@ -2948,8 +2953,8 @@
     },
     {
       "path": "skills/peer-review/references/domain-probes/diagnostic_accuracy.md",
-      "size": 9002,
-      "sha256": "8232e2023d3c4d52e6a2d9003ae335302d6fe78c54d39b81f591c07becaf4df0"
+      "size": 11692,
+      "sha256": "afc69e56578babcc1cf7c7952d2df301fdc829329fb480a5cf426ff6ab65d9f5"
     },
     {
       "path": "skills/peer-review/references/domain-probes/equity_fairness.md",
@@ -2993,8 +2998,8 @@
     },
     {
       "path": "skills/peer-review/references/domain-probes/observational_confounding.md",
-      "size": 33429,
-      "sha256": "ac1736047c069aa47df76deea92379cae407043b6989d8d3fc77db8fd84b0031"
+      "size": 34795,
+      "sha256": "ff8cb910c7fb83ec08a04ba88866bdf1e0d2f43d972e2861b825595a85b035ee"
     },
     {
       "path": "skills/peer-review/references/domain-probes/polygenic_risk_score.md",
@@ -3028,8 +3033,8 @@
     },
     {
       "path": "skills/peer-review/references/domain-probes/sr_ma.md",
-      "size": 17239,
-      "sha256": "486d569f559f16d62b882f7256ccfe7443e3e2b4cc72a407a5cd046162a98b25"
+      "size": 20154,
+      "sha256": "82ccb4abc1ab1fffaf528268baad6c79e67c9b2ff929c14d7dcccb9677e10ddc"
     },
     {
       "path": "skills/peer-review/references/domain-probes/survey_research.md",
@@ -3488,13 +3493,13 @@
     },
     {
       "path": "skills/self-review/SKILL.md",
-      "size": 102413,
-      "sha256": "97219c57684d4eaced9e35b0968ca09da7731095c186a4e97757b4039f43f2f6"
+      "size": 104731,
+      "sha256": "9c74f317d10c7b491e710debb619dcf536689092a59fe749050a0ad41f4aacd5"
     },
     {
       "path": "skills/self-review/references/domain-probes/ai_overclaiming.md",
-      "size": 14205,
-      "sha256": "565aa362e20ea6ca923510ea393829fb851e0caaae3d732f99144dd48a25b951"
+      "size": 15410,
+      "sha256": "bdb07002bf0b351579036937af5bf149e35389a218198699b81d31dc2fda7ec9"
     },
     {
       "path": "skills/self-review/references/domain-probes/case_report.md",
@@ -3508,8 +3513,8 @@
     },
     {
       "path": "skills/self-review/references/domain-probes/diagnostic_accuracy.md",
-      "size": 9002,
-      "sha256": "8232e2023d3c4d52e6a2d9003ae335302d6fe78c54d39b81f591c07becaf4df0"
+      "size": 11692,
+      "sha256": "afc69e56578babcc1cf7c7952d2df301fdc829329fb480a5cf426ff6ab65d9f5"
     },
     {
       "path": "skills/self-review/references/domain-probes/equity_fairness.md",
@@ -3553,8 +3558,8 @@
     },
     {
       "path": "skills/self-review/references/domain-probes/observational_confounding.md",
-      "size": 33429,
-      "sha256": "ac1736047c069aa47df76deea92379cae407043b6989d8d3fc77db8fd84b0031"
+      "size": 34795,
+      "sha256": "ff8cb910c7fb83ec08a04ba88866bdf1e0d2f43d972e2861b825595a85b035ee"
     },
     {
       "path": "skills/self-review/references/domain-probes/polygenic_risk_score.md",
@@ -3588,8 +3593,8 @@
     },
     {
       "path": "skills/self-review/references/domain-probes/sr_ma.md",
-      "size": 17239,
-      "sha256": "486d569f559f16d62b882f7256ccfe7443e3e2b4cc72a407a5cd046162a98b25"
+      "size": 20154,
+      "sha256": "82ccb4abc1ab1fffaf528268baad6c79e67c9b2ff929c14d7dcccb9677e10ddc"
     },
     {
       "path": "skills/self-review/references/domain-probes/survey_research.md",
@@ -3658,8 +3663,8 @@
     },
     {
       "path": "skills/self-review/scripts/check_binning_consistency.py",
-      "size": 19541,
-      "sha256": "e3bf7dd2e0871ce6905abc1d33a26c7afac76a93d184bfe2d431af97d0622f74"
+      "size": 20076,
+      "sha256": "c6467eb4a1d954d67da87e283d8a628604a9ec7558c966f8b20c1b661e23b9c9"
     },
     {
       "path": "skills/self-review/scripts/check_citation_order.py",
@@ -3668,13 +3673,13 @@
     },
     {
       "path": "skills/self-review/scripts/check_claim_artifact.py",
-      "size": 13065,
-      "sha256": "ac29a7e8145152e6641fce8eaf98766cfc943a034db72252cc38538d7ab59db2"
+      "size": 18475,
+      "sha256": "c99c8090205734b0eae981550ed09e6275d94add608e66df78f4533c35f20924"
     },
     {
       "path": "skills/self-review/scripts/check_classical_style.py",
-      "size": 12210,
-      "sha256": "c973ee8b776f28515439fb185e1254e08e62c2e1410e260f18a824241a331af0"
+      "size": 13124,
+      "sha256": "941d90559cdcdd24f3eba58daf00eb34a7d227c3fe44267b93b65b80b6092989"
     },
     {
       "path": "skills/self-review/scripts/check_cohort_arithmetic.py",
@@ -3686,15 +3691,30 @@
       "size": 21506,
       "sha256": "7d3e67074d58a28ffee52ce64b486231f103a3ddcaf6b3b6ee83ba5f89c63bc2"
     },
+    {
+      "path": "skills/self-review/scripts/check_cv_leakage.py",
+      "size": 6349,
+      "sha256": "431c5f14ad2c4f59e85b2a5e86150ac708d476e8f2f1da859d81953f522b2117"
+    },
     {
       "path": "skills/self-review/scripts/check_editorial_impression.py",
       "size": 22032,
       "sha256": "42e0e9315e1c97ca0f9943213c65ea91d7064773d25287b2577f0386dfb7fc41"
     },
+    {
+      "path": "skills/self-review/scripts/check_emphasis_density.py",
+      "size": 6626,
+      "sha256": "79e517942c1eca4f879fa2b05e6497f93fe6f4d53ed58ca98e240bf5b44c4821"
+    },
+    {
+      "path": "skills/self-review/scripts/check_figure_citation.py",
+      "size": 5298,
+      "sha256": "342bc1126a420111da9c0fe38c6cd68cc45542b0e485202689d7219de9d80712"
+    },
     {
       "path": "skills/self-review/scripts/check_null_calibration.py",
-      "size": 7594,
-      "sha256": "9ddff01722c34efb6ffd757ae762c6ee12f5993bf13b11313c2e20b60b26cab3"
+      "size": 8585,
+      "sha256": "e5bd71c515554b3acbaefd3807e584364a536dc6e1101bec5b524bc26b341309"
     },
     {
       "path": "skills/self-review/scripts/check_panel_diversity.py",
@@ -3716,20 +3736,25 @@
       "size": 15481,
       "sha256": "c9cd8e47cfef1ffcea12ecda5314a71ccd5415f35f4f296addadf53ccb6ceb3b"
     },
+    {
+      "path": "skills/self-review/scripts/check_rounded_delta.py",
+      "size": 7079,
+      "sha256": "2961dd0b25dcd06f202442004e08f2d98c6f2d4c337be3f8b0e3286a59952072"
+    },
     {
       "path": "skills/self-review/scripts/check_scope_coherence.py",
-      "size": 10818,
-      "sha256": "820dfc264c2a4f62c79c0c7123a3e1a8b59a100b89654617a08ff55deeb25a75"
+      "size": 11920,
+      "sha256": "e600e54fcbe308060a8dadd871ec274b6ae19f89456ae0194490e152c0d09a91"
     },
     {
       "path": "skills/self-review/scripts/check_supplement_hygiene.py",
-      "size": 11088,
-      "sha256": "f89027472cdf0258357c3b0f0b0f3fec09b5ea65cc1373292797b818d1acf444"
+      "size": 13579,
+      "sha256": "c61bd5e485d2bce4a6efd7bf2a7980aa0d31ebecb876a7c6895fd12cb6bf7f1c"
     },
     {
       "path": "skills/self-review/skill.yml",
-      "size": 2223,
-      "sha256": "4009f3148776fab2096da3dad8a15e503c5073b4cc66b42c57498948e2040270"
+      "size": 2381,
+      "sha256": "9499a87d985d981eac9418d6cd95ed79c1d9724aba8854b7d6713d89679d9f1d"
     },
     {
       "path": "skills/setup-medsci/SKILL.md",
@@ -3883,8 +3908,8 @@
     },
     {
       "path": "skills/write-paper/SKILL.md",
-      "size": 66426,
-      "sha256": "910808b73103a74c26a3a92acb9e7b99529de1b8d9af8efaf740e7ad737fdd09"
+      "size": 66771,
+      "sha256": "1a50c9ceb040a79feaa60e809c7196f9f04b85cab2f5f3402dcaed3f7aee552c"
     },
     {
       "path": "skills/write-paper/references/exemplar_abstract.md",
@@ -3903,8 +3928,8 @@
     },
     {
       "path": "skills/write-paper/references/exemplar_discussion/README.md",
-      "size": 2524,
-      "sha256": "46d1b9e874f669608cc2c2abc400ab5efa74e37958f59e0c3b8f842dd4934e7d"
+      "size": 2727,
+      "sha256": "3bfcd4eb4df4ca0309446a606550cb11adc4d88daa676f2217249691d2e6b042"
     },
     {
       "path": "skills/write-paper/references/exemplar_discussion/ai_validation_tripod_claim.md",
@@ -3916,6 +3941,11 @@
       "size": 2500,
       "sha256": "7d49d926eb9aa78c42ce0e6579ca299f528dec77dafc17ed9451ada0c2340b3c"
     },
+    {
+      "path": "skills/write-paper/references/exemplar_discussion/meta_analysis_prisma.md",
+      "size": 3357,
+      "sha256": "3cc8542c754372b19acbc25b3c6d6211479b4bbec361c7638c5d2550db3ecc5f"
+    },
     {
       "path": "skills/write-paper/references/exemplar_discussion/observational_cohort_strobe.md",
       "size": 3652,
@@ -3928,8 +3958,8 @@
     },
     {
       "path": "skills/write-paper/references/exemplar_methods/README.md",
-      "size": 2247,
-      "sha256": "158c4894b92c1b6c19bda8becd947e455c5050cbef4d7d3606c2c46c3123d006"
+      "size": 2342,
+      "sha256": "6966e8b723d0c4ccc012d54e2b8a22ef59b39c22619e63a8597f9badb380b4e7"
     },
     {
       "path": "skills/write-paper/references/exemplar_methods/ai_validation_tripod_claim.md",
@@ -3941,6 +3971,11 @@
       "size": 2739,
       "sha256": "f403613a0f3625c5c7dab8fa16a21635007821ede2b58d265440db51b55165a6"
     },
+    {
+      "path": "skills/write-paper/references/exemplar_methods/meta_analysis_prisma.md",
+      "size": 4160,
+      "sha256": "a0e696e2f581fa6ae8b1aeb86ff7b9a5aaa6bdb2184fee4352e74d2ee6559d90"
+    },
     {
       "path": "skills/write-paper/references/exemplar_methods/observational_cohort_strobe.md",
       "size": 2364,
@@ -3948,8 +3983,8 @@
     },
     {
       "path": "skills/write-paper/references/exemplar_results/README.md",
-      "size": 2588,
-      "sha256": "0ececbb937fa44a2d89d56124bc7d5d2fea540a459fd0328b0cf534c463baaa1"
+      "size": 2799,
+      "sha256": "14b588f1f4433be71c39f11627148fff797eb87b3b74be75e61514095d4c38ea"
     },
     {
       "path": "skills/write-paper/references/exemplar_results/ai_validation_tripod_claim.md",
@@ -3961,6 +3996,11 @@
       "size": 2772,
       "sha256": "8e45e0b30b4ab505b4eb8c37007f970bfb5aa81375fd011915b07d85c9419598"
     },
+    {
+      "path": "skills/write-paper/references/exemplar_results/meta_analysis_prisma.md",
+      "size": 3170,
+      "sha256": "8aed3ee5d36c15515843d77b5f69fe76f433c9972827a9e18303b38802fac782"
+    },
     {
       "path": "skills/write-paper/references/exemplar_results/observational_cohort_strobe.md",
       "size": 2452,
@@ -4273,8 +4313,8 @@
     },
     {
       "path": "skills/write-paper/references/paper_types/meta_analysis.md",
-      "size": 10163,
-      "sha256": "5384224227f54deb1829a400ec6994b45a1b7cb34c167c158804e9d361466b26"
+      "size": 10536,
+      "sha256": "2c237409005214baab63627966d8f2b31498e3c28bea34c571a6d5591a068ed8"
     },
     {
       "path": "skills/write-paper/references/paper_types/nhis_cohort.md",

package/metadata/distribution_manifest.json

@@ -1,6 +1,6 @@
 {
   "schema_version": 1,
-  "version": "5.10.0",
+  "version": "5.12.0",
   "owned_skills": [
     "academic-aio",
     "add-journal",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "medsci-skills",
-  "version": "5.10.0",
+  "version": "5.12.0",
   "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/analyze-stats/SKILL.md

@@ -411,6 +411,7 @@ tbl %>% as_flex_table() %>% flextable::save_as_docx(path = "table.docx")
 
 ### Inter-rater Agreement
 
+- **Methodology guide**: `references/analysis_guides/agreement_reliability.md` (**load before generating code** — the pseudoreplication trap for clustered/repeated measurements + the pseudoreplication-safe per-subject / mixed-effects code, ICC model/type selection, agreement-vs-reliability distinction; pairs with self-review probe O18)
 - Table type guide: `references/table-standards/table-types/agreement.md` (ICC with model/type + CI, weighted κ for ordinal, Bland–Altman bias + LoA, reliability-vs-agreement distinction, common errors)
 - Template: `references/templates/agreement_analysis.py`
 - 2 raters + categorical: Cohen's kappa

package/skills/analyze-stats/references/analysis_guides/agreement_reliability.md

@@ -0,0 +1,130 @@
+# Inter-rater Agreement & Reliability Guide
+
+Quantifying how well two or more raters (or a rater and a reference, or repeated
+measurements) **agree**. The coefficient is easy to compute; the two ways these
+analyses fail review are (1) treating **clustered** measurements as independent
+(pseudoreplication) and (2) confusing **agreement** with **reliability**.
+
+---
+
+## When to Use
+
+- **Cohen's kappa** — 2 raters, categorical (nominal) labels.
+- **Weighted kappa** — 2 raters, **ordinal** labels (linear or quadratic weights; disagreement
+  by one category counts less than by three).
+- **Fleiss' kappa** — ≥3 raters, categorical.
+- **Krippendorff's alpha** — any number of raters, any measurement level, tolerates missing data.
+- **ICC (intraclass correlation)** — **continuous** measurements; report the model + type (below).
+- **Bland–Altman** — two continuous methods/raters: bias (mean difference) + 95% limits of agreement.
+- NOT for: a single 2×2 vs a reference standard (that is diagnostic accuracy — see
+  `table-types/diagnostic_accuracy.md`); not for a multi-reader AI-vs-human comparison with reader +
+  case variance (that is an MRMC reader study — see `table-types/reader_study.md`).
+
+---
+
+## Pseudoreplication comes first (this, not the coefficient, is the issue)
+
+If each **subject contributes more than one measurement** — several lesions, aneurysms, nodules,
+slices, or time-points per patient — the rows are **not independent**. Computing agreement on the
+**pooled** rows (or on all pairwise distances) uses an inflated *n*, narrows the CI, and gives an
+**anti-conservative** p-value. This is the single most common reliability-study error a reviewer
+catches (it is flagged by the self-review probe **O18** in `observational_confounding.md`).
+
+Two correct paths — pick one and state it:
+
+1. **Aggregate to the independent unit first**, then compute agreement per subject. This is the
+   simplest defensible analysis when a per-subject summary is meaningful (e.g. mean measurement,
+   majority label, or one index lesion per subject).
+2. **Model the clustering** — a mixed-effects / variance-components ICC with a **subject random
+   effect** (or a GEE with an exchangeable working correlation), so the within-subject correlation
+   is estimated rather than ignored.
+
+A pooled-pairwise test can *flip* on correction: e.g. Mann–Whitney p = 0.02 on 448 pooled
+pairwise distances became p = 0.59 at the per-aneurysm level (n = 112). **Report the unit of
+analysis explicitly**, and when subjects have multiple measurements report a per-subject
+sensitivity analysis.
+
+### Produce the pseudoreplication-safe version
+
+```python
+import pandas as pd
+import pingouin as pg   # ICC with model/type + CI
+
+# long format: one row per (subject, measurement); rater columns rater1..raterK
+df = pd.read_csv("ratings.csv")
+
+# 1) DETECT clustering: more rows than independent subjects
+n_rows, n_subjects = len(df), df["subject_id"].nunique()
+if n_rows > n_subjects:
+    print(f"CLUSTERED: {n_rows} measurements from {n_subjects} subjects "
+          f"({n_rows / n_subjects:.1f} per subject) — do NOT pool as independent.")
+
+# 2a) PER-SUBJECT AGGREGATION (continuous): mean per subject, then ICC on subject means
+per_subj = df.groupby("subject_id")[["rater1", "rater2"]].mean().reset_index()
+long = per_subj.melt(id_vars="subject_id", var_name="rater", value_name="score")
+icc = pg.intraclass_corr(data=long, targets="subject_id", raters="rater", nan_policy="omit")
+print(icc[["Type", "ICC", "CI95%"]])   # report Type (e.g. ICC2/ICC2k) + CI
+
+# 2b) OR MODEL THE CLUSTERING (keep every measurement, subject random effect)
+import statsmodels.formula.api as smf
+df_long = df.melt(id_vars="subject_id", value_vars=["rater1", "rater2"],
+                  var_name="rater", value_name="score")
+m = smf.mixedlm("score ~ 1", data=df_long, groups=df_long["subject_id"])
+res = m.fit()
+var_between = float(res.cov_re.iloc[0, 0]); var_resid = float(res.scale)
+icc_clustered = var_between / (var_between + var_resid)
+print(f"variance-components ICC (subject random effect) = {icc_clustered:.3f}")
+```
+
+---
+
+## ICC: state the model and the type (they are not interchangeable)
+
+- **Model**: one-way random (raters differ per subject), two-way random (same raters, generalise to
+  a rater population), two-way mixed (same raters, these raters only).
+- **Type**: **agreement** vs **consistency** (agreement penalises systematic rater bias; consistency
+  does not), and **single** vs **average** measurement (average-of-k is higher — only report it if
+  the clinical use averages k raters).
+- Report as e.g. **ICC(2,1) = 0.82 (95% CI 0.74–0.88), two-way random, absolute agreement, single
+  rater**. An ICC with no model/type is not interpretable.
+
+---
+
+## Agreement is not reliability
+
+- **Agreement** = do raters give the *same value* (absolute; Bland–Altman bias, absolute-agreement ICC).
+- **Reliability** = can raters *rank/discriminate subjects* consistently (relative; consistency ICC,
+  Pearson/Spearman). A method can be highly reliable yet have poor agreement (a constant offset).
+  State which one the clinical claim needs, and use the matching coefficient.
+
+---
+
+## Reporting
+
+- The coefficient **with a 95% CI** (bootstrap or analytic), the model/type (for ICC), and the
+  **unit of analysis** (per-subject vs per-lesion, and the clustering handling).
+- The interpretation band used (e.g. Landis–Koch), but do not over-interpret a point estimate whose
+  CI spans two bands.
+- For continuous methods: Bland–Altman **bias + 95% limits of agreement**, not just a correlation.
+
+---
+
+## Common failures (flag at review)
+
+- **Pooled/pairwise agreement on clustered data** (pseudoreplication) — the headline coefficient's
+  CI is too narrow; re-run per-subject or with a subject random effect (probe O18).
+- **ICC reported with no model/type** — uninterpretable; the same data yields different ICCs.
+- **Reliability coefficient used to claim agreement** (or vice versa) — a high consistency ICC does
+  not establish that the two methods are interchangeable.
+- **Correlation (r) reported as agreement** for two methods — r ignores a constant/proportional bias;
+  Bland–Altman is required.
+- **Kappa on ordinal labels unweighted** — treats a one-category disagreement as a full disagreement.
+
+---
+
+## Anti-Hallucination
+
+- Never hand-type a coefficient or CI — compute it from the ratings CSV with a seeded script.
+- Do not quote an ICC without the model/type actually estimated by the code.
+- If subjects have multiple measurements, the per-subject sensitivity analysis is **mandatory** —
+  do not report only the pooled number.

package/skills/humanize/SKILL.md

@@ -178,6 +178,7 @@ If the density remains above 2.0, run another fix-verify cycle (max 3 rounds).
 | 19 | § (section sign) marker | "as in §2.3", "(see §Discussion)", "§Results" | Delete or replace with section name ("Methods", "Results") — `grep -c "§"` = 0 |
 | 20 | Methods/Results self-reference parenthetical | "(Methods §X)", "(Results §3.1)", "(Methods, Section 2.3)" | Drop the parenthetical or shorten to "(see Methods)" |
 | 21 | AI Disclosure boilerplate (body) | "## Artificial Intelligence Disclosure", "Generative AI was not used to create..." in manuscript body | Remove from body → place in cover letter / submission form only (per `~/.claude/rules/journal-ai-image-policies.md`) |
+| 25 | Inline-emphasis over-use (typographic over-signposting) | Single-word italics (*into*, *passive*, *same*), whole-clause italics (*a redesign of the relationship itself*), bold used mid-paragraph to signpost | Remove inline emphasis; keep only legitimate italics — statistical symbols (*P*, *t*, *n*), Latin (*in vivo*, *et al.*), gene/species (*BRCA1*). A bold **run-in subheading** at line start is fine (Nature/npj style) |
 
 ### Response-Letter Patterns (R2R)
 
@@ -247,6 +248,7 @@ the pass/fail status.
 | Pattern 19 — `§` symbol | ENFORCED (senior MA reviewer prep) | `grep -c "§" manuscript.md` > 0 | auto-strip; verify post-rewrite count == 0 |
 | Pattern 20 — `(see Methods §X)` self-reference | ENFORCED | match found | rewrite to direct section name reference |
 | Pattern 21 — AI Disclosure paragraph in body | ENFORCED | "Generative AI was not used..." paragraph in manuscript body | move to cover letter or remove |
+| Pattern 25 — inline-emphasis over-use | ENFORCED | italic-emphasis density over threshold after allowlist | run `/self-review` `scripts/check_emphasis_density.py --manuscript manuscript.md`; `EMPHASIS_OVERUSE` (Minor) means strip inline italics (keep only stat symbols / Latin / gene-species); whole-clause italics are the strongest tell |
 | Patterns 22-24 — R2R editing-mechanism / draft line-number / tooling leak | TRIAGE (response letters); `§` = 0 hard | detection greps in ai_patterns.md R2R section surface candidates | review each hit (analysis narration, quoted additions, revised-manuscript page/line are NOT tells); rewrite confirmed tells to substantive prose |
 | Citation preservation invariant | ENFORCED | any pre-existing `[@bibkey]` removed by rewrite | revert that single rewrite; flag for user |
 | Numerical preservation invariant | ENFORCED | any number changed by rewrite | revert; flag for user |

package/skills/peer-review/SKILL.md

@@ -118,6 +118,17 @@ within the current submission (poolability of incommensurable studies, a broken
 evaluation instrument). When both classes are present, the **unfixable** class governs the recommendation —
 do not let a long list of fixable items reframe an unfixable core as "addressable in revision."
 
+**Salvage-reframe that shrinks the contribution is NOT a fixable major revision.** When your proposed fix
+for a construct/validity flaw is to *narrow the claim* (e.g. "reframe from a clinical classifier to a
+re-identifiability signal", "scope down to a proof-of-concept"), check whether that narrower framing survives
+the novelty/importance bar. If novelty/importance is ALREADY weak — a co-reviewer or your own scorecard flags
+the work as "expected / well-known finding / unconvincing motivation / limited use case" (Originality or
+Reader-interest ≤ mid) — then the reframe *reduces* the contribution and makes the importance problem worse,
+not better. A contribution shrunk to survive a validity flaw is a **Reject-leaning** outcome (the contribution
+is the product, not addressable-in-revision), not an encourage-major-revision. Deterministic trigger to
+self-audit: if your confidential note says the claim is "narrower than / more modest than claimed" AND your
+recommendation is Reject-family-adjacent, do not upgrade it to major revision on the strength of the reframe.
+
 **Review/narrative/primer escalation** *(the contribution IS the product)*: for a review article there is no
 data to re-analyze; the distinct contribution — novelty, integrative synthesis, domain-specificity — is the
 deliverable itself. Therefore **weak novelty / no distinct contribution / not domain-specific is
@@ -135,11 +146,11 @@ confidential note and the recommendation are consistent.
 
 ### Phase 2A: Systematic Review / Meta-Analysis Extension
 
-Apply this internal-consistency-first gate (P0) plus 17-probe checklist (P1–P17) **only when manuscript type is "Systematic Review", "Meta-Analysis", or "Systematic Review and Meta-Analysis"**. These probes complement (do not replace) the generic Phase 2 issue checklist.
+Apply this internal-consistency-first gate (P0) plus 19-probe checklist (P1–P19) **only when manuscript type is "Systematic Review", "Meta-Analysis", or "Systematic Review and Meta-Analysis"**. These probes complement (do not replace) the generic Phase 2 issue checklist.
 
 **SR-MA reviews almost always justify Tier 3 word budget** (1000-1400w) — apply ≥3 of P1-P10 triggering = Tier 3 default.
 
-**Probe detail (P0–P17), with output templates and the leads-vs-findings discipline:** `${CLAUDE_SKILL_DIR}/references/domain-probes/sr_ma.md`. Load it and apply each probe when the trigger above fires. In this skill, map each probe finding to the review draft as a Major / Minor comment; route conclusion-threatening or integrity findings into the Confidential Comments to the Editor, and place a confirmed error that drives a headline claim as the Major #1 candidate.
+**Probe detail (P0–P19), with output templates and the leads-vs-findings discipline:** `${CLAUDE_SKILL_DIR}/references/domain-probes/sr_ma.md`. Load it and apply each probe when the trigger above fires. In this skill, map each probe finding to the review draft as a Major / Minor comment; route conclusion-threatening or integrity findings into the Confidential Comments to the Editor, and place a confirmed error that drives a headline claim as the Major #1 candidate.
 
 ### Phase 2B: Survival / Prognostic Model Extension
 
@@ -182,14 +193,14 @@ The original-research probes (Phase 2 issue checklist, Phase 2A/2B/2C) do not tr
 
 ### Phase 2E: Observational / Confounding Extension
 
-Apply this 16-probe checklist (O1–O16) **only when the manuscript is an observational study** (cohort, case-control, cross-sectional, health-screening / registry) **whose central claim is an adjusted exposure–outcome association** estimated by covariate adjustment rather than randomization. These probes complement (do not replace) the generic Phase 2 issue checklist and the STROBE reporting items; they target the gap between the stated adjustment set and what the exposure-stratified Table 1 shows.
+Apply this 18-probe checklist (O1–O18) **only when the manuscript is an observational study** (cohort, case-control, cross-sectional, health-screening / registry) **whose central claim is an adjusted exposure–outcome association** estimated by covariate adjustment rather than randomization. These probes complement (do not replace) the generic Phase 2 issue checklist and the STROBE reporting items; they target the gap between the stated adjustment set and what the exposure-stratified Table 1 shows.
 
 **Exempt**:
 - Randomized trials (confounding controlled by design → Phase 2 + CONSORT)
 - Purely descriptive / prevalence reports with no adjusted association claim
 - Diagnostic-accuracy studies with no exposure–outcome estimand (→ Phase 2A DTA cells + categories A–C)
 
-**Probe detail (O1–O16), with output templates:** `${CLAUDE_SKILL_DIR}/references/domain-probes/observational_confounding.md`. Load it and apply each probe when the trigger above fires. O1 (a measured covariate imbalanced by exposure in Table 1 yet absent from the adjustment set), O7 (an outcome consequence/mediator wrongly adjusted — the opposite-direction failure, e.g. serum uric acid in an eGFR model), and O8 (records > subjects with the analysis unit undisclosed) are data-checkable and the highest-yield probes — verify O1/O7 against the manuscript's own Table 1 and run the records-vs-subjects check for O8. In this skill, map each probe finding to the review draft as a Major / Minor comment; a confounding-completeness gap (O1), over-adjustment that moves the headline estimate (O7), a selection/collider structure (O3), undisclosed repeat-subject clustering (O8), an undisclosed complete-case collapse (O5), a report-derived outcome with no construct-validity defence (O9), an inferential effect-size gradient across overlapping/nested subsets with no difference/interaction test (O10), an ignored/mis-specified complex-survey design (O11, NHANES/KNHANES weights without strata+PSU, or a subgroup by row-deletion), a data-mined inflection-point/'saturation' cutoff (O12), a cross-sectional mediation claimed as a causal chain without a temporal-order caveat / M–Y-confounding sensitivity (O13), or a synergy/joint-effect claim on the wrong interaction scale — multiplicative-only or joint-category ORs with no additive RERI/AP/S (O14) — is design-level, so surface it in the Confidential Comments to the Editor and place it as the Major #1 candidate rather than softening it to a reporting fix.
+**Probe detail (O1–O18), with output templates:** `${CLAUDE_SKILL_DIR}/references/domain-probes/observational_confounding.md`. Load it and apply each probe when the trigger above fires. O1 (a measured covariate imbalanced by exposure in Table 1 yet absent from the adjustment set), O7 (an outcome consequence/mediator wrongly adjusted — the opposite-direction failure, e.g. serum uric acid in an eGFR model), and O8 (records > subjects with the analysis unit undisclosed) are data-checkable and the highest-yield probes — verify O1/O7 against the manuscript's own Table 1 and run the records-vs-subjects check for O8. In this skill, map each probe finding to the review draft as a Major / Minor comment; a confounding-completeness gap (O1), over-adjustment that moves the headline estimate (O7), a selection/collider structure (O3), undisclosed repeat-subject clustering (O8), an undisclosed complete-case collapse (O5), a report-derived outcome with no construct-validity defence (O9), an inferential effect-size gradient across overlapping/nested subsets with no difference/interaction test (O10), an ignored/mis-specified complex-survey design (O11, NHANES/KNHANES weights without strata+PSU, or a subgroup by row-deletion), a data-mined inflection-point/'saturation' cutoff (O12), a cross-sectional mediation claimed as a causal chain without a temporal-order caveat / M–Y-confounding sensitivity (O13), or a synergy/joint-effect claim on the wrong interaction scale — multiplicative-only or joint-category ORs with no additive RERI/AP/S (O14) — is design-level, so surface it in the Confidential Comments to the Editor and place it as the Major #1 candidate rather than softening it to a reporting fix.
 
 ### Phase 2E-2: Clinical Prediction-Model Extension
 
@@ -201,7 +212,7 @@ Apply this 4-probe checklist (CP1–CP4) **only when the manuscript develops or
 
 Apply when an AI/ML **primary study** (diagnostic, prognostic, triage, detection) makes a clinical claim in the Title/Abstract/Conclusion — generalizable, outperforms clinicians, deployment-ready, can replace a reader. Complements Phase 2F (recommendation calibration) and the signature "Overclaiming vs evidence level" check; co-applies with Phase 2C for radiomics-AI and Phase 2B for prognostic-AI.
 
-**Probe detail (AO0–AO6), with output templates and the leads-vs-findings discipline:** `${CLAUDE_SKILL_DIR}/references/domain-probes/ai_overclaiming.md`. Load it and apply each probe when the trigger fires. Run AO0 first — locate the load-bearing claim and read it together with its cited evidence before alleging over-reach (a hedged Discussion qualifier is not a headline). In this skill, map each probe finding to the review draft as a Major / Minor comment; a headline generalizability (AO1), superiority/replacement (AO2/AO3), or deployment-readiness (AO4) claim that outruns the design is framing-level — surface it in the Confidential Comments to the Editor and place it as the Major #1 candidate when it is the paper's headline. AO5 catches over-reach in the reported metric itself (best-fold headline without cross-fold CI/SD, unstated/test-tuned operating point, rebalanced-accuracy, or a code-vs-claims mismatch); pair it with the `exemplar_reviews/optimistic_validation_reporting.md` phrasing model and raise it as Major when it carries the headline.
+**Probe detail (AO0–AO7), with output templates and the leads-vs-findings discipline:** `${CLAUDE_SKILL_DIR}/references/domain-probes/ai_overclaiming.md`. Load it and apply each probe when the trigger fires. Run AO0 first — locate the load-bearing claim and read it together with its cited evidence before alleging over-reach (a hedged Discussion qualifier is not a headline). In this skill, map each probe finding to the review draft as a Major / Minor comment; a headline generalizability (AO1), superiority/replacement (AO2/AO3), or deployment-readiness (AO4) claim that outruns the design is framing-level — surface it in the Confidential Comments to the Editor and place it as the Major #1 candidate when it is the paper's headline. AO5 catches over-reach in the reported metric itself (best-fold headline without cross-fold CI/SD, unstated/test-tuned operating point, rebalanced-accuracy, or a code-vs-claims mismatch); pair it with the `exemplar_reviews/optimistic_validation_reporting.md` phrasing model and raise it as Major when it carries the headline.
 
 ### Phase 2G-2: Model-Development / Validation-Integrity Extension
 
@@ -223,9 +234,9 @@ Apply this 8-probe checklist (RC0–RC7) **only when the manuscript is a randomi
 
 ### Phase 2I: Diagnostic-Accuracy / Reader-Study Extension
 
-Apply this 8-probe checklist (D1–D8) **only when the manuscript is a diagnostic test accuracy (DTA) primary study** — an index test against a reference standard — including **multi-reader multi-case (MRMC)** reader studies (AI-vs-reader or modality comparison). These probes complement (do not replace) the generic Phase 2 issue checklist and the STARD / QUADAS-2 items; they target verification/spectrum/blinding bias and the MRMC design/variance issues a reader study adds. (For a DTA **meta-analysis**, use Phase 2A / `sr_ma.md`.)
+Apply this 11-probe checklist (D1–D11) **only when the manuscript is a diagnostic test accuracy (DTA) primary study** — an index test against a reference standard — including **multi-reader multi-case (MRMC)** reader studies (AI-vs-reader or modality comparison). These probes complement (do not replace) the generic Phase 2 issue checklist and the STARD / QUADAS-2 items; they target verification/spectrum/blinding bias and the MRMC design/variance issues a reader study adds. (For a DTA **meta-analysis**, use Phase 2A / `sr_ma.md`.)
 
-**Probe detail (D1–D8), with output templates and the leads-vs-findings discipline:** `${CLAUDE_SKILL_DIR}/references/domain-probes/diagnostic_accuracy.md`. Load it and apply each probe when the trigger fires. In this skill, map each probe finding to the review draft as a Major / Minor comment; two-gate (case-control) sampling (D2), verification/incorporation bias (D1), or an MRMC analysis that ignores reader variance (D6) is design/analysis-level — surface it in the Confidential Comments to the Editor and place it as the Major #1 candidate. Pairs the `analyze-stats` `table-types/reader_study.md` table and the `make-figures` `exemplar_plots/mrmc_roc.md` figure; a test-set-tuned operating threshold pairs with `exemplar_reviews/optimistic_validation_reporting.md`.
+**Probe detail (D1–D11), with output templates and the leads-vs-findings discipline:** `${CLAUDE_SKILL_DIR}/references/domain-probes/diagnostic_accuracy.md`. Load it and apply each probe when the trigger fires. In this skill, map each probe finding to the review draft as a Major / Minor comment; two-gate (case-control) sampling (D2), verification/incorporation bias (D1), or an MRMC analysis that ignores reader variance (D6) is design/analysis-level — surface it in the Confidential Comments to the Editor and place it as the Major #1 candidate. Pairs the `analyze-stats` `table-types/reader_study.md` table and the `make-figures` `exemplar_plots/mrmc_roc.md` figure; a test-set-tuned operating threshold pairs with `exemplar_reviews/optimistic_validation_reporting.md`.
 
 ### Phase 2J: Case-Report Extension
 
@@ -396,7 +407,7 @@ After drafting, verify mechanically:
    - ≥50% of Minor requests use hedged forms ("I'd suggest," "could," "would help") rather than imperative ("must," bare "Please [verb]")
    - General Comments names ≥2 specific strengths before listing concerns
    - At most 1 typo/grammar Minor Comment, only if in formal section or systematic
-9. **SR-MA-specific QC** (if Phase 2A applied): Confirm the P0 internal-consistency gate was run before any fabrication claim. For each P1–P17 probe used, verify the corresponding Major comment cites source PMID + source page/table reference + verbatim quote, and that no probe lead was promoted to a finding without source confirmation (leads-vs-findings discipline). Reviews citing extraction errors without source-page reference are not actionable for authors.
+9. **SR-MA-specific QC** (if Phase 2A applied): Confirm the P0 internal-consistency gate was run before any fabrication claim. For each P1–P19 probe used, verify the corresponding Major comment cites source PMID + source page/table reference + verbatim quote, and that no probe lead was promoted to a finding without source confirmation (leads-vs-findings discipline). Reviews citing extraction errors without source-page reference are not actionable for authors.
 10. **Radiomics-reproducibility QC** (if Phase 2C applied): If an acquisition-parameter sweep predicts an outcome from its own grid axes (R1 design-grid circularity) or the substantive result is a cross-domain failure framed as success (R3), confirm the recommendation reflects design-level severity and is not softened to a reporting fix. Where a model × threshold/cohort grid yields a few p < 0.05, confirm the multiplicity / expected-false-positive count is named (R4), not deferred to "statistical review needed."
 11. **Review-article QC** (if Phase 2D applied): Confirm RV1–RV9 are reflected — in particular that novelty/value-add (RV1) is raised for a saturated topic and that gap-filling (RV8) is present, not just error-spotting. Verify SANRA is used as an appraisal aid, not over-enforced as a reporting guideline (no PRISMA demand on a narrative review; only RV3 is SANRA-aligned and phrased as a suggestion). Verify every suggested addition uses "consider adding" phrasing (no "must cite"), is source-confirmed, and that preprints are labeled as preprints (not equated with peer-reviewed guidelines). Confirm Phase 2F was run for the recommendation: when RV1 novelty is a Major in a saturated space with no distinct contribution, the recommendation is escalated toward Reject (the contribution IS the product — weak novelty is unfixable-in-current-form), not defaulted to the revision/Reconsider tier.
 12. **AI/method/review priority QC**: Before a Major Revision (or Reconsider) recommendation, confirm Phase 2F
@@ -466,7 +477,7 @@ For radiomic feature-reproducibility / phantom parameter-sweep / reliability-fil
 
 For Review / narrative / primer / state-of-the-art manuscripts, apply the Phase 2D 9-probe audit (novelty/value-add, scope/aims, evidence-gathering transparency, technical/medical accuracy, taxonomy/synthesis coherence, balance/currency/citation accuracy, load-bearing figures/tables, constructive gap-filling, curated-base circularity) in place of the original-research probes — error-spotting plus proportionate gap-filling, with SANRA used as an appraisal aid only.
 
-For observational studies whose central claim is an adjusted exposure–outcome association, also apply the Phase 2E 16-probe audit (confounding completeness, adjustment-set provenance, selection/collider bias, exposure measurement validity, missing-data / complete-case collapse, residual-confounding E-value, over-adjustment, analysis-unit/clustering, outcome construct validity, overlapping-subset gradient, complex-survey design & weighting, data-driven threshold mining, cross-sectional mediation, interaction scale, selection on modality/procedure availability, serial-imaging lesion-tracking), with O1 (a measured covariate imbalanced by exposure in Table 1 yet absent from the adjustment set) and O7 (an outcome consequence/mediator wrongly adjusted) checked against the manuscript's own Table 1.
+For observational studies whose central claim is an adjusted exposure–outcome association, also apply the Phase 2E 18-probe audit (confounding completeness, adjustment-set provenance, selection/collider bias, exposure measurement validity, missing-data / complete-case collapse, residual-confounding E-value, over-adjustment, analysis-unit/clustering, outcome construct validity, overlapping-subset gradient, complex-survey design & weighting, data-driven threshold mining, cross-sectional mediation, interaction scale, selection on modality/procedure availability, serial-imaging lesion-tracking, many-exposure agnostic-scan multiplicity, pseudoreplication in multi-rater agreement), with O1 (a measured covariate imbalanced by exposure in Table 1 yet absent from the adjustment set) and O7 (an outcome consequence/mediator wrongly adjusted) checked against the manuscript's own Table 1.
 
 For cross-modality image-synthesis manuscripts (MRI→PET / MRI→CT / non-contrast→contrast / low-dose→full-dose) that claim functional/molecular information or a substitute for the unavailable target modality, also apply the Phase 2K 4-probe audit (IS1 determinism/information-ceiling vs a source→label baseline, IS2 target-derived-preprocessing/slice-selection leakage, IS3 global vs lesion-level quantitative agreement, IS4 mechanistic/proxy-signal plausibility); IS2 and IS4 are typically unfixable-in-current-form and govern the recommendation per Phase 2F.
 

package/skills/peer-review/references/domain-probes/ai_overclaiming.md

@@ -49,6 +49,11 @@ A 5-probe checklist (AO1–AO5, with AO0 as a gate) for medical-AI/ML primary st
   - (b) **Success-conditioned selection** — the arm or the analyzed subset is gated on an AI-success condition (cases where the model produced an output, segmentations that "passed", studies the pipeline did not fail on), so the comparison is conditioned on the very thing under test.
 - This is a **design/paradigm-level** defect: the operationalized task, not the prose, is mis-specified, so it cannot be fixed by rewording the claim — escalate **past an ordinary Major** (editors read it as a Reject-grade construct-validity failure; a panel that files it as a fixable Major under-rates it). The fix is a re-designed arm whose task matches the intended deployment workflow and an unconditioned (consecutive / intention-to-diagnose) analysis set.
 
+**AO7 — Comparative "within/comparable-to X variability" claim whose benchmark X was never quantified**:
+- When the Abstract / hypothesis / Conclusion asserts that a result falls **"within inter-expert variability"**, **"comparable to the reference range"**, or **"on par with human readers"**, the named comparator quantity (the inter-expert spread, the human-reader range) must actually be **computed and reported** in Results / a Table. A benchmark claim whose benchmark does not exist in the paper is an unbenchmarked overclaim — the reader cannot check the comparison because the "within X" bound was never measured (e.g. an agreement-envelope was computed but the *volume* inter-expert spread it is compared against was not).
+- Lead: for each "within / comparable-to / on par with `<comparator>` variability|range|performance" claim, verify the `<comparator>` quantity appears in Results or a Table with a number; if absent → flag as unbenchmarked.
+- Severity: MAJOR when the comparative claim is a headline; the fix is to compute and report the benchmark, or to drop the comparative framing. Distinct from AO5 (metric overstates evidence) — here the comparison *target* is simply missing.
+
 ## Decision-impact / early-deployment probes (DECIDE-AI axis, DI1–DI5)
 
 Co-apply when a study claims **clinical utility, deployment, or decision impact** of an AI system, or *is* an early-stage live clinical evaluation. The reporting axis is then DECIDE-AI (early-stage clinical evaluation of AI decision-support); these probes check that a utility/deployment claim rests on real-use evidence, not retrospective accuracy. They sharpen AO4 for the deployment-evaluation case.