medsci-skills 5.20.0 → 5.20.1

package/README.md

@@ -288,6 +288,8 @@ The E2E pipeline (`orchestrate --e2e`) produces everything up to `qc/`. The `sub
 
 ## What's New
 
+**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.
+
 **v5.20** — reviewer-arithmetic gates. Five deterministic `self-review` detectors promoted from a peer-review cycle, each recomputing what a manuscript already prints: `check_table_percentages` (an `n (%)` cell vs its column denominator), `check_nested_group_comparison` (a P value comparing an analysed subset against the parent cohort that **contains** it — nested, invalid), `check_reported_p_from_counts` (rebuilds each 2×2 row and recomputes Fisher / Pearson χ² ± Yates in **pure stdlib**, calibrating the family on rows that reproduce), `check_dta_denominators` (sensitivity/specificity denominators vs the reference-standard category counts, behind a matching grand total), and `check_paired_difference_estimator` (an odd-n integer-scale median cannot be non-integer; a zero-width CI; an unnamed estimator). Plus `/peer-review` request-type discipline (disclosure vs computation) and impossibility-claim verification. Additive and backward-compatible; **55 skills / 46 guidelines / 57 integrity detectors / 22 domain-probe modules**. (See the [CHANGELOG](CHANGELOG.md) for v5.0–v5.19.)
 
 **v5.19** — reviewer-safety + reporting-checklist batch. A **PDF hidden-text / prompt-injection guard** for `/peer-review` — a PyMuPDF extractor plus a stdlib detector that catch a review-steering instruction hidden in a submitted PDF (white-on-white text, sub-visible fonts, off-page glyphs, invisible render mode, or a document-metadata field) before an LLM ingesting the text layer can be steered by it, and emit visible-only text to feed a model instead of the raw PDF; plus the **TARGET** (target-trial emulation; Cashin et al., *JAMA* 2025) and **REMARK** (prognostic tumour-marker; McShane et al.) reporting checklists. Additive and backward-compatible; **55 skills / 46 guidelines / 52 integrity detectors / 22 domain-probe modules**. (See the [CHANGELOG](CHANGELOG.md) for v5.0–v5.18.)
@@ -356,7 +358,7 @@ The E2E pipeline (`orchestrate --e2e`) produces everything up to `qc/`. The `sub
 
 **v4.1** ships distribution levers and a submission pre-flight gate — analysis-integrity detectors **24 → 25** (still 43 skills):
 
-- **Claude Code plugin marketplace** — `/plugin marketplace add Aperivue/medsci-skills`, then `/plugin` discovery of eight `medsci-*` category plugins generated from the catalog SSOT (`.claude-plugin/marketplace.json`).
+- **Claude Code plugin marketplace** — `/plugin marketplace add Aperivue/medsci-skills`, then `/plugin` discovery of nine `medsci-*` category plugins generated from the catalog SSOT (`.claude-plugin/marketplace.json`).
 - **MedSci-Audit detector registry** — the deterministic verification layer is now a named, enumerated, citable suite ([`MEDSCI_AUDIT.md`](MEDSCI_AUDIT.md) + generated `metadata/detectors_catalog.json`, six audit families).
 - **Hero-skill standalone mirrors** — `scripts/sync_hero_skill.py` mirrors a focused skill to its own star-funnel repo; first two live: [`Aperivue/verify-refs`](https://github.com/Aperivue/verify-refs) and [`Aperivue/check-reporting`](https://github.com/Aperivue/check-reporting).
 - **Placeholder/marker gate** — `check_placeholders.py` flags leftover `[@NEW:]` / `[version]` / `TODO` / template-URL markers before submission (the 25th detector).

package/metadata/distribution_files.json

@@ -3023,8 +3023,8 @@
     },
     {
       "path": "skills/orchestrate/SKILL.md",
-      "size": 35203,
-      "sha256": "ef8b919606efbf794d7ebe67b011bd676c129cd1d9d51bac16d85dcaaae5e12e"
+      "size": 40144,
+      "sha256": "6535b55a55791f1339c32d4b8ee8e7ebdaf749a6c3dc1677ef8f3a653ef424ca"
     },
     {
       "path": "skills/orchestrate/references/dialogue_nodes.md",

package/metadata/distribution_manifest.json

@@ -1,6 +1,6 @@
 {
   "schema_version": 1,
-  "version": "5.20.0",
+  "version": "5.20.1",
   "owned_skills": [
     "academic-aio",
     "add-journal",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "medsci-skills",
-  "version": "5.20.0",
+  "version": "5.20.1",
   "description": "MedSci Skills — a medical/scientific research skill suite for AI coding agents (Claude Code, Codex, Cursor, Copilot). The npm package is a terminal-friendly installer shortcut; the canonical distribution remains the GitHub repository and the Claude Code plugin marketplace.",
   "license": "SEE LICENSE IN LICENSE",
   "homepage": "https://github.com/Aperivue/medsci-skills#readme",

package/skills/orchestrate/SKILL.md

@@ -73,6 +73,26 @@ You do NOT do the work yourself. You classify, plan, and delegate.
 | **fill-icmje-coi** | Form filling | Batch ICMJE COI Disclosure Form generation per author from a synthetic seed |
 | **sync-submission** | Submission | SSOT-to-submission drift audit; journal-specific submission manifest creation from canonical manuscript artifacts |
 | **peer-review** | Review | External manuscript peer review draft generation (journal-specific formatting). Use ONLY for reviewing other authors' work, never for self-review |
+| **review-paper** | Writing | Scaffold/draft a literature review (narrative / scoping PRISMA-ScR / systematic); reuses the self-review narrative-review probes for QC. Distinct from `write-paper` (original research) and `meta-analysis` (pooling) |
+| **polish-language** | Quality | Academic-English consistency lint + non-native clarity polish (abbreviation define-once, US/UK spelling drift, hyphen/en-dash ranges, P/p case, value/unit spacing). Style-only; distinct from `humanize` (AI-tell removal) and `check-reporting` (guideline items) |
+| **author-strategy** | Analysis | PubMed author-profile analysis: study-type classification, trajectory-archetype, publication-strategy report from a name |
+| **batch-cohort** | Analysis | Generate N analysis scripts from one validated methodology template × many exposure/outcome combinations (same method, swap variables) + summary matrix |
+| **replicate-study** | Analysis | Replicate an existing cohort study's methodology on a different database: design extraction, variable-harmonization table, replication-difference report |
+| **cross-national** | Analysis | Cross-national comparison study (KNHANES + NHANES + CHNS or parallel surveys): variable harmonization + parallel weighted analysis |
+| **ma-scout** | Systematic review | Meta-analysis topic discovery + feasibility (professor-first profile→gap, or topic-first question→gap→co-author) before a protocol exists |
+| **find-cohort-gap** | Methodology | Research-gap discovery from a longitudinal cohort DB: profile strengths, match PI expertise, literature-saturation scan, ranked topic proposals |
+| **design-ai-benchmarking** | Methodology | Design/validity review for benchmarking one or more AI systems against a human-expert reference panel (decoupled rubrics, planted calibration probes, reviewer-panel construction, IRR targets, rating-export schema) — before data collection |
+| **architecture-zoo** | Modeling | Choose a medical-imaging model architecture (classification / segmentation / detection / transfer) before scaffolding — maps task + modality + labelled-data scale + imbalance to a paper-grounded shortlist |
+| **preprocess-imaging** | Modeling | Design/audit DICOM/NIfTI intake, resampling, normalisation, and augmentation so the pipeline is leakage-safe before `model-scaffold`; emits a preprocessing manifest + data-stage leakage gate |
+| **model-scaffold** | Modeling | Generate a reproducible runnable PyTorch training repo (patient-level seed-locked split, task model, train/eval scripts, repro record) — the link between choosing an architecture and validating a trained model |
+| **radiomics-ml** | Modeling | Produce/audit a radiomics / tabular-ML study (imaging or clinical features → penalised logistic / SVM / RF / gradient-boosting / MLP → outcome) with a learner-agnostic nested-CV / feature-stability / calibration / external-validation gate (no GPU) |
+| **model-validation** | Validation | Design/audit the clinical-validation study for an engineer-built imaging model (segmentation / classification / detection): patient-level split disjointness, internal-vs-external validation, comparator, metric fit — with a deterministic split-leakage gate |
+| **model-evaluation** | Evaluation | Compute task-correct held-out metrics for a trained imaging model (segmentation Dice + boundary; classification AUROC + AUPRC + Se/Sp with bootstrap CIs; detection FROC/mAP; calibration; subgroup slices) → per-case results table |
+| **mllm-eval** | Evaluation | Design/audit a model-agnostic evaluation harness for an LLM/MLLM clinical task (report generation, VQA, extraction/classification): adjudicated reference, clinical-efficacy metrics beyond BLEU/ROUGE, hallucination, contamination, prompt-sensitivity, reader study |
+| **explainability** | Modeling | Produce/audit a medical-imaging model's interpretability analysis (Grad-CAM / saliency / integrated-gradients) held to the reviewer bar — Adebayo sanity checks, quantitative localisation vs ground truth, cohort-level results, attribution-not-validation framing |
+| **uncertainty-imaging** | Modeling | Design/audit the uncertainty-quantification / OOD-detection / selective-prediction layer of a deployment-framed imaging model (MC-dropout / ensemble / conformal, held-out OOD set, abstention at a pre-specified point) + deployment-claim gate |
+| **model-card** | Documentation | Generate a Model Card + Datasheet + METRIC-informed data-quality pass for an engineer-built imaging model, filled from user-supplied facts, with a completeness gate (never fabricates numbers/provenance/licence) |
+| **setup-medsci** | Setup | Diagnostic checklist for the runtime (Python, R, Node, Claude Code, Git, Zotero, MCP servers) — read-only pass/fail table pointing to the right setup doc for any missing component |
 
 ---
 
@@ -287,7 +307,7 @@ After each skill completes, verify that expected output files exist. If validati
 |-------|-----------------|------------|
 | `/analyze-stats` | At least one file in `analysis/tables/*.csv` OR `analysis/_analysis_outputs.md` | Check file existence and non-empty |
 | `/make-figures` | `analysis/figures/_figure_manifest.md` with at least 1 entry | Parse manifest, verify listed files exist |
-| `/write-paper` | `manuscript/manuscript.md` (required), `manuscript/manuscript_final.docx` (required in --e2e) | Check file existence and non-empty |
+| `/write-paper` | `manuscript/manuscript.md` (required) | Check file existence and non-empty. Do NOT require the DOCX here — `manuscript_final.docx` is rendered later by `/manage-refs` (step 7); requiring it at this step would halt an `--e2e` run before the DOCX exists |
 | `/check-reporting` | `qc/reporting_checklist.md` or inline report | Check file existence |
 | `/verify-refs` | `qc/reference_audit.json` (sole output) | Parse JSON; halt if `submission_safe == false` (i.e., `FABRICATED` / `MISMATCH` count > 0 OR `duplicate_findings[]` nonempty) |
 | `/self-review` | Review report with JSON block (when --json) | Check JSON block is parseable. In `--panel` mode each issue may carry an additional optional `consensus` array plus R1/R2/R3 attribution annotations on the `M`/`m` comments — these are additive and backwards-compatible; accept them |