medsci-skills 4.1.0

package/skills/design-study/SKILL.md

@@ -0,0 +1,298 @@
+---
+name: design-study
+description: >
+  Study design and validity review for radiology and medical AI research. Identifies analysis unit,
+  cohort logic, leakage risks, comparator design, validation strategy, and reporting guideline fit before
+  drafting or submission.
+triggers: study design, leakage check, cohort design, analysis plan, validation strategy, comparator design, bias check
+tools: Read, Write, Edit, Bash, Grep, Glob
+model: inherit
+---
+
+# Design-Study Skill
+
+## Purpose
+
+This skill pressure-tests whether a study is answerable, interpretable, and defensible before large amounts of drafting or analysis work accumulate.
+
+Use it when:
+- a study question is known but the analysis plan is still fluid
+- the user wants a methods sanity check
+- a manuscript feels vulnerable to reviewer criticism
+- a peer review requires explicit methodological diagnosis
+
+---
+
+## Communication Rules
+
+- Communicate with the user in their preferred language.
+- Use English for statistical, radiologic, and reporting-guideline terminology.
+- Be direct about validity risks, but always propose the smallest feasible fix first.
+
+---
+
+## Core Review Questions
+
+Always inspect these dimensions:
+
+1. What is the exact research question?
+2. What is the analysis unit: patient, lesion, exam, study, phase, report?
+3. What is the index date or decision point?
+4. How are inclusion and exclusion criteria applied?
+5. Is there any information leakage?
+6. What is the reference standard or endpoint definition?
+7. What comparator is clinically meaningful?
+8. What validation strategy is used?
+9. What uncertainty reporting is required?
+10. Which reporting guideline best fits?
+11. Are exposure/outcome/covariate **definitions literature-grounded**, or invented ad-hoc from the data dictionary? If ad-hoc, defer to `/define-variables` before drafting Methods.
+
+---
+
+## Standard Output
+
+```text
+## Study Design Review
+Question: ...
+Study type: ...
+Analysis unit: ...
+Index date / prediction timepoint: ...
+
+### Strengths
+- ...
+
+### Major validity risks
+1. ...
+2. ...
+
+### Minimal fixes
+- ...
+
+### Reporting fit
+- Recommended guideline: ...
+
+### Decision
+- Ready for analysis / Needs redesign / Drafting can proceed with limitations
+```
+
+---
+
+## Workflow
+
+### Phase 1: Reconstruct the study
+
+Extract from protocol, draft, slides, tables, or notes:
+- clinical problem
+- intended use case
+- population
+- inputs
+- outputs
+- outcome definition
+- timing of variable availability
+
+**Gate:** Present the reconstructed study summary (question, analysis unit, intended use)
+to the user. Confirm before proceeding — if the reconstruction is wrong, the entire
+validity review will be misdirected.
+
+### Phase 2: Check structural validity
+
+#### A. Analysis unit
+
+Look for mismatches such as:
+- patient-level claim from lesion-level analysis
+- exam-level split with patient overlap
+- phase-level samples treated as independent
+
+#### B. Leakage
+
+Look for:
+- postoperative features used for preoperative prediction
+- normalization or thresholding performed before data split
+- repeated exams across train/test
+- reader annotations derived from outcome information
+- **input-text contamination for NLP/LLM extraction tasks**: if the model input includes report
+  sections such as clinical history, indication, impression, prior diagnosis, or referral text, confirm
+  that those fields do not literally name or strongly imply the target label. If the target is already
+  present in the supplied text, the task is information retrieval under label leakage, not phenotype
+  inference; redesign the input mask, report a sensitivity analysis excluding leaky fields, or reframe the
+  claim.
+- **construct dependence** (a predictor that is a definitional component of the outcome). Two cases:
+  (i) *mathematical definition* — an input that computes the outcome (when the outcome is HOMA-IR =
+  f(fasting insulin, fasting glucose), those two inputs are not independent predictors); (ii)
+  *near-tautological composite* — a ratio or score built from the outcome's defining components, which
+  shows an inflated, near-circular association. Test: "could this predictor be derived, in whole or
+  part, from the outcome's definition or the same measurement?" If yes, exclude it, or retain it only
+  as a labeled calibration probe rather than a reported discovery.
+
+#### F. Time origin & survivorship (incident / transition models)
+
+For any time-to-event or incident/transition design, check before drafting:
+- **Time origin per model.** Each incident model starts its at-risk clock at the correct origin. Watch for **immortal-time bias** (a span in which the event cannot occur, misattributed to one group) and **left-truncation / delayed entry** (subjects entering the risk set after the origin).
+- **Mediator-ascertainment-window survivorship.** A "progressor" / transition label that is conditional on *surviving to* a later ascertainment (a second scan, a follow-up visit) is survivorship-biased; plan a landmark time or an explicit intermediate-state (multistate / illness-death) model.
+- **Primary-analysis-set selection.** If the primary will not be the full cohort (e.g., complete-case while a large fraction is missing), pre-specify the selection justification and a MAR rationale; do not let the complete-case model become primary because it is the significant one (an outcome-dependent choice).
+- A design that cannot yet answer these should say so honestly — but note that at review time a Methods/Limitations admission that the issue was *"not formally assessed"* is escalated to a MAJOR by the survival probe (S1), not waved through as a limitation.
+
+#### C. Reference standard
+
+Check:
+- who established ground truth
+- when it was established
+- whether blinding was possible
+- whether only a subset had gold standard verification
+- **Construct ↔ nominal-definition match.** Does the exposure/finding *construct* stay inside its stated definition, or does it quietly exceed it? An "incidentaloma" defined as an *indeterminate* finding must not include frank malignancy reads; a label that overshoots its definition inflates the apparent cohort and breaks the κ. For each construct, restate the nominal definition and confirm every included case satisfies it.
+- **Per-flag reference-standard concordance.** When the index finding is flagged against a reference standard, report the concordance *per flag category* (not just overall). A construct where a large fraction of flags do not match the reference standard (e.g., ~86% non-match) is measuring something other than the named construct.
+- **Manuscript definition ↔ `variable_operationalization.md`.** The variable definitions written in Methods must match the operationalization table verbatim (dictionary-first). A blinded re-classification form must quote the analytic protocol's definition verbatim — paraphrase / "common-sense extension" in the form (but not the Methods) is the documented cause of a low κ that is a *definition mismatch*, not real disagreement. Cross-check with `/define-variables` output before drafting.
+
+#### D. Validation
+
+Classify:
+- apparent only
+- internal split
+- cross-validation
+- temporal validation
+- external validation
+- multi-center external validation
+
+#### E. Reader / Expert-Elicitation Study Design
+
+When the study elicits expert ratings (reader study, annotation panel, AI-output evaluation), check
+the following before data collection.
+
+**Rubric design**
+- **Decouple the axes.** Each rated dimension should measure one construct. Keep "is the finding
+  valid/correct" separate from "is it novel", "is it feasible to measure", "does it add value over
+  current tools", and "would it change action". A candidate can be high-validity yet low-added-value
+  ("real but redundant"); a single blended score hides this.
+- **Anchor every Likert point** with a short verbal descriptor; pilot the anchors with at least one
+  reviewer before locking.
+- **Pre-specify discriminant validity**: hypothesize which dimensions should correlate vs be
+  orthogonal, then report the full inter-dimension correlation matrix to confirm the rubric measures
+  distinct constructs.
+
+**Calibration probes (planted control items)**
+Insert a small number of deliberate control items, blinded and randomized across raters (record who
+received which, e.g. a `probe_arm` flag), to (i) anchor the scale, (ii) measure rater drift and
+fatigue, and (iii) audit the rubric and pipeline itself. Four useful flavors:
+- **Positive control / "too-good" item** — a known-strong or near-tautological item; tests whether
+  raters equate "largest effect" with "best", and whether an upstream construct-independence gate works.
+- **Known-bad negative control** — an engineered defect (fabricated reference, missing key statistic);
+  expected to score low.
+- **Instability item** — an estimate that reverses or fails to replicate on holdout; tests caveat handling.
+- **Mechanism-contradiction item** — an empirical direction that opposes the proposed mechanism.
+
+Report inter-rater reliability **on the control items separately** as primary evidence of rubric and
+scale validity; a low overall ICC is interpretable only if raters at least converge on the controls.
+
+**Operational rigor**
+- Randomize item order **per reviewer** (not one global seed); analyze order and fatigue effects.
+- Collect reviewer metadata (years of experience, prior AI-evaluation experience, subspecialty) for
+  descriptive reporting.
+- Define a structured export schema (per-item ratings, free-text justifications, follow-ups, timing) up front.
+- Require each item to be judged standalone; discourage cross-item references in free-text, which
+  signal non-independent rating.
+
+For an AI-system-versus-human-expert benchmark specifically, route to `/design-ai-benchmarking`, which
+extends this subsection with arm definition, LLM-as-judge versus human-as-judge adjudication, and a
+structured export schema.
+
+### Phase 3: Clinical framing
+
+Ask whether the comparator and endpoint support the stated claim:
+- is the model better than current practice or just another model?
+- is the endpoint clinically meaningful?
+- does performance translate to action?
+- **incremental value**: if the study frames the model/marker as adding value *beyond* / *on top of* / *incremental to* an existing tool (a clinical score, a routine test, a baseline model), the design must pre-specify the baseline comparator built from the in-routine-use predictors **and** an incremental-value metric — ΔC-index / ΔAUC (with a paired CI, e.g. DeLong), categorical or continuous NRI, IDI, or decision-curve net benefit. A standalone discrimination number ("our model's AUC was 0.84") does not support a "beyond X" claim; without the nested-model comparison the finding may be real but redundant. Plan this at design time — it cannot be added post hoc without the baseline model.
+- **fine-tuning contribution baseline**: if an NLP/LLM study claims that fine-tuning, LoRA, prompt
+  engineering, or a multi-agent wrapper improves extraction/classification, pre-specify a same-backbone
+  zero-shot or few-shot comparator on the identical input, output schema, and test split. A comparison
+  only against a weaker or unrelated baseline cannot establish that the proposed adaptation adds value.
+- **endpoint↔conclusion scope**: decide up front what *kind* of conclusion the design can support, so the manuscript does not overreach. A cross-sectional / single-visit / prevalence design cannot support a prognostic or surveillance claim (rescreen interval, disease progression) — that needs longitudinal follow-up. A binary surrogate endpoint (present/absent, >0, dichotomized) is risk stratification, not a patient-care directive (defer/withhold/initiate therapy). At review time `/self-review` §D + `check_scope_coherence.py` flag `CROSS_SECTIONAL_PROGNOSTIC` / `SURROGATE_CARE_DIRECTIVE` against the conclusion.
+
+### Phase 4: Reporting fit
+
+Recommend one primary guideline:
+- `TRIPOD-AI`
+- `CLAIM`
+- `STARD`
+- `STROBE`
+- `PRISMA`
+- `CARE`
+- `ARRIVE`
+- journal-specific additions if needed
+
+---
+
+## Frequent Failure Modes
+
+### Diagnostic AI
+- no clinically relevant comparator
+- exam-level split instead of patient-level split
+- unclear reference standard
+- AUROC-only reporting without threshold metrics
+
+### Prognostic modeling
+- unclear time zero
+- immortal time bias
+- feature timing mismatch
+- no calibration
+
+### Retrospective cohort / screening database
+- **time zero misalignment**: cohort entry ≠ follow-up start → immortal time bias
+- interval-censored outcomes treated as exact → underestimation of event times
+- healthy volunteer bias unacknowledged → inflated external validity claims
+- surveillance bias from unequal follow-up frequency between groups
+- **3 bias classification (Hernan/Robins)**: selection bias (who enters), information bias (how measured), confounding (what else differs) — explicitly map each threat
+- **confounding completeness**: pre-specify the adjustment set from a DAG (not a Table-1 p < 0.05 rule), and plan to report whether any measured covariate that turns out imbalanced by exposure but outside the adjustment set leaves the primary estimate robust (an extended-adjustment sensitivity model). At review time `/self-review` Phase 2.5e + the O1–O6 probes in `observational_confounding.md` check this against Table 1.
+
+### Multimodal LLM / report generation
+- no clear rubric for clinical correctness
+- benchmark labels derived from noisy reports without adjudication
+- unsupported claims about safety or workflow benefit
+- input text contains the target label or diagnosis being predicted
+- no same-backbone zero-shot/few-shot baseline for a fine-tuning or prompt-engineering claim
+
+### Imaging meta-analysis
+- overlapping cohorts
+- paired modalities analyzed as independent
+- heterogeneity metrics missing
+- zero-cell handling unspecified
+
+---
+
+## Minimal-Fix Principle
+
+Whenever possible, recommend the smallest feasible repair first:
+
+- clarify the claim
+- narrow the target population
+- add a limitation statement
+- add a clinically relevant baseline
+- re-run one key sensitivity analysis
+- redefine the endpoint more explicitly
+
+Escalate to redesign only when the central claim is not defensible otherwise.
+
+---
+
+## Handoff Rules
+
+- route to `analyze-stats` when the design is basically sound but analysis details need refinement
+- route to `check-reporting` after the design is locked
+- route to `self-review` when the user wants a pre-submission quality check on their own manuscript
+- route back to `write-paper` only after the main validity risks are documented
+
+---
+
+## What This Skill Does NOT Do
+
+- It does not compute statistics directly
+- It does not draft full manuscript prose
+- It does not resolve raw data engineering issues
+- It does not replace a full peer review when journal-facing tone is required
+
+## Anti-Hallucination
+
+- **Never fabricate references.** All citations must be verified via `/search-lit` with confirmed DOI or PMID. Mark unverified references as `[UNVERIFIED - NEEDS MANUAL CHECK]`.
+- **Never invent clinical definitions, diagnostic criteria, or guideline recommendations.** If uncertain, flag with `[VERIFY]` and ask the user.
+- **Never fabricate numerical results** — compliance percentages, scores, effect sizes, or sample sizes must come from actual data or analysis output.
+- If a reporting guideline item, journal policy, or clinical standard is uncertain, state the uncertainty rather than guessing.

package/skills/design-study/skill.yml

@@ -0,0 +1,33 @@
+schema_version: 2
+name: design-study
+layer: D
+owner_domain: study_design
+
+when_to_use: "Review study design and validity (analysis unit, cohort logic, leakage, comparator, validation, reporting fit) before drafting or submission."
+when_NOT_to_use: "Sample-size math (use calc-sample-size); variable definitions (use define-variables)."
+
+inputs:
+  - "study description / draft protocol"
+outputs:
+  - "design and validity review (decision notes)"
+side_effects:
+  - writes_decision_notes
+downstream_consumers:
+  - calc-sample-size
+  - define-variables
+  - write-protocol
+forbidden_actions:
+  - write_project_artifacts_beyond_decision_notes
+  - approve_design_with_uncorrected_leakage
+
+# v2.1 quality card
+purpose: "Surface design and validity risks (leakage, analysis unit, comparator, validation strategy) before a study is built or written."
+safety_boundaries:
+  - "Advisory only: writes decision notes, not analysis or manuscript artifacts."
+  - "Names validity threats explicitly rather than rubber-stamping a design."
+known_limitations:
+  - "A review reduces but cannot eliminate design risk; it is not a guarantee of validity."
+  - "No standalone demo; recommendations require researcher judgement."
+validation_commands:
+  - "carry findings into write-protocol Methods and re-check with /self-review"
+evidence_surface: manual_workflow

package/skills/fill-icmje-coi/SKILL.md

@@ -0,0 +1,216 @@
+---
+name: fill-icmje-coi
+description: >
+  Batch-generate per-author ICMJE Conflict of Interest Disclosure Forms
+  (`coi_disclosure.docx`) for manuscript submission. Pre-fills all 13 disclosure
+  items as "☒ None" + final certification ☒ using a synthetic seed template
+  shipped with the skill, then clones the seed per author with Date, Name, and
+  Manuscript Title replaced. Designed for the common case of hospital-based
+  observational research where no author has real financial conflicts; the
+  circulated forms become "reply 'no changes' + sign" for most authors and only
+  flag those who need to amend.
+triggers: ICMJE, COI form, conflict of interest form, disclosure form, coi_disclosure.docx, 이해상충, 이해상충 폼, icmje 폼, 저자 동의서, submission forms
+tools: Read, Write, Edit, Bash, Grep, Glob
+model: inherit
+---
+
+# Fill-ICMJE-COI Skill
+
+You are helping a researcher prepare ICMJE Conflict of Interest Disclosure Forms
+for every co-author on a manuscript about to be submitted to an ICMJE member
+journal (CHEST, NEJM, JAMA, Lancet, Radiology, etc.). This skill batch-generates
+one personalized `.docx` per author from a synthetic all-None seed shipped with
+the skill, avoiding 10–20 minutes of repetitive Word clicking per author.
+
+## Why This Skill Exists
+
+The official ICMJE `coi_disclosure.docx` puts every field inside Word Content
+Controls (Structured Document Tags, a.k.a. SDTs). Naive `python-docx`
+manipulation of `cell.text` silently ignores SDT content, so the straightforward
+programmatic approach does not work. The historical workaround was to open the
+template in Word and manually fill each author's form (21 authors × 13
+checkboxes × 2 clicks = ~500 clicks). This skill replaces that by operating
+directly on `word/document.xml` inside the docx zip and doing literal-string
+replacement — but that requires the target strings to already exist in the
+seed, so the skill ships a pre-filled synthetic seed.
+
+**Precedent:** a multi-author cohort manuscript submission — 6 authors
+auto-filled in ~5 seconds from the synthetic seed with zero Word clicks.
+
+## Core Principles (Do Not Violate)
+
+1. **Never author SDT XML from scratch.** Only replace existing strings in an
+   already-populated seed. Creating Content Controls programmatically is
+   fragile and Word-version-dependent.
+2. **Never ship a real author's filled form as the seed.** The template
+   directory contains `icmje_coi_seed_synthetic.docx` with all PII scrubbed
+   (synthetic name, title, date; metadata reset to `ICMJE` / `Anonymous`).
+   Real-person seeds leak PII through both document.xml and docProps.
+3. **Never modify the 13 disclosure items or certification checkbox.** The
+   script only replaces Date/Name/Title. If any author has a real disclosure,
+   they must edit in Word manually — the skill's purpose is the common
+   all-None case.
+4. **Always verify before circulation.** Each output must have 14 × ☒ and
+   13 × "None" in document.xml. The script runs this check implicitly by
+   preserving the seed structure; a post-generation grep is cheap insurance.
+
+## When to Use This Skill
+
+- Manuscript accepted for submission to an ICMJE member journal
+- 3+ co-authors with no real financial conflicts
+- Editorial Manager / submission portal requires per-author ICMJE disclosure docx
+- About to hand-fill the same form 6–21 times
+
+Skip this skill when:
+- Any author has a real financial disclosure to list (they fill their own form
+  in Word; this skill does not help)
+- Target journal uses its own declaration form (not ICMJE) — check author
+  guidelines first
+- Only 1 author (not worth the setup)
+
+## Execution
+
+### Phase 1 — Intake
+
+Ask the user (or extract from conversation):
+1. **Manuscript title** (exact, as it will appear on title page)
+2. **Submission date** (e.g., "April 20, 2026")
+3. **Author list** — ordered, one name per slot: `[(1, "Author One"), (2, "Author Two"), ...]`
+4. **Output directory** — typically `submission/{journal}/icmje_forms/`
+
+Present the intake back to the user for confirmation (**Gate 1 — user approval**)
+before generating anything. Explicitly name which authors will get all-None
+forms and remind that anyone with a real disclosure must instead fill their own
+form in Word.
+
+### Phase 2 — Generate
+
+Invoke the script with the synthetic seed that ships with this skill:
+
+```bash
+python3 ${SKILL_DIR}/scripts/fill_icmje_coi.py \
+  --seed ${SKILL_DIR}/templates/icmje_coi_seed_synthetic.docx \
+  --seed-name "Placeholder Author" \
+  --seed-title "Placeholder Manuscript Title" \
+  --seed-date "January 1, 2000" \
+  --new-title "{exact manuscript title}" \
+  --new-date "{submission date}" \
+  --out-dir {out_dir} \
+  --authors '[[1,"Author One"],[2,"Author Two"],...]'
+```
+
+The script exits nonzero if any seed string is not found, preventing silent
+failures.
+
+### Phase 3 — Verify
+
+For each generated docx, confirm:
+- ☒ count = 14 (13 disclosure items + 1 final certification)
+- "None" count = 13
+- Correct name appears after "Your Name:"
+- Correct title appears after "Manuscript Title:"
+- No leakage of seed placeholder strings (`Placeholder Author`, `Placeholder Manuscript Title`, `January 1, 2000`)
+
+Verification one-liner:
+```bash
+for f in {out_dir}/*.docx; do
+  python3 -c "
+import zipfile, sys
+xml = zipfile.ZipFile('$f').read('word/document.xml').decode()
+assert xml.count('☒') == 14, 'bad ☒ count'
+assert xml.count('None') == 13, 'bad None count'
+assert 'Placeholder' not in xml, 'seed leak'
+print('✓ $f')
+"
+done
+```
+
+Present verification results to user (**Gate 2 — user review**) before handing
+off files.
+
+### Phase 4 — Circulation Guidance
+
+Provide the user with circulation copy to send with each personalized form (write it in the co-authors' preferred language — Korean is common for Korean co-authors):
+
+> Please review the attached ICMJE COI form.
+> - If the contents are correct, sign and reply with a PDF.
+> - If a change is needed, edit/check the relevant item, sign, and reply.
+> - If there are no changes at all, reply "no changes" and return the signed PDF separately.
+
+All 6–21 authors can be emailed in one `gws gmail draft` batch (**Gate 3 — user
+approves batch send** before actually dispatching).
+
+## Custom Seeds
+
+If the user wants a custom seed (e.g., different default wording, pre-filled
+items 2/3 with a common grant), generate it once as follows:
+
+1. Open `templates/icmje_coi_seed_synthetic.docx` in Word
+2. Edit the desired fields
+3. Save as a new file under `{project}/submission/{journal}/` or a
+   local private seeds directory (outside this repo)
+4. Pass `--seed /path/to/custom.docx` to the script along with the new seed
+   values for `--seed-name`, `--seed-title`, `--seed-date`
+
+Do NOT commit custom seeds that contain real author names to the public
+medsci-skills repo. Keep them in private per-project directories or a
+local private seeds directory (outside this repo).
+
+## Seed Provenance (how the shipped synthetic seed was created)
+
+The shipped `templates/icmje_coi_seed_synthetic.docx` was derived from the
+official ICMJE `coi_disclosure.docx` through the following steps:
+
+1. Downloaded the official ICMJE template (`https://www.icmje.org/downloads/coi_disclosure.docx`)
+2. Opened in Word, typed placeholder values:
+   - Date: `January 1, 2000`
+   - Your Name: `Placeholder Author`
+   - Manuscript Title: `Placeholder Manuscript Title`
+3. Checked each of the 13 disclosure items' "None" option (14 checkboxes total including final certification)
+4. Typed "None" in the "Name all entities" column for each item
+5. Scrubbed `docProps/core.xml` metadata: creator=`ICMJE`, lastModifiedBy=`Anonymous`, dates=`2000-01-01`
+6. Scrubbed `docProps/app.xml` Company/Manager fields
+
+No real author's disclosure data is embedded. The file is safe to redistribute.
+
+## Anti-Hallucination
+
+- **Never invent author names, email addresses, or ORCIDs.** Pull them
+  verbatim from the manuscript's title page or the user's author list.
+- **Never claim to have filled the 13 disclosure items** — they come from the
+  seed unchanged. If the user asks whether the script "handled the
+  disclosures," the honest answer is "it cloned the seed's ☒ None entries;
+  no author-specific disclosure reasoning happened."
+- **Never promise the script works on a blank ICMJE template.** It does not —
+  the seed must be pre-filled with all-None ☒ + text.
+- **Never edit seed XML by authoring new SDT elements.** If an error requires
+  altering the seed structure, stop and escalate to the user; Word-generated
+  SDT XML is the ground truth.
+- **Never push private seed files to public repos.** If the user asks to
+  promote a custom seed, verify by `unzip -p seed.docx docProps/core.xml` that
+  no real names remain in metadata before committing.
+
+## References
+
+- ICMJE Disclosure of Interest page: https://www.icmje.org/disclosure-of-interest/
+- ICMJE COI form download: https://www.icmje.org/downloads/coi_disclosure.docx
+- ICMJE FAQ on disclosure forms: https://www.icmje.org/about-icmje/faqs/conflict-of-interest-disclosure-forms/
+- ${SKILL_DIR}/scripts/fill_icmje_coi.py — generator CLI + Python API
+- ${SKILL_DIR}/templates/icmje_coi_seed_synthetic.docx — shipped synthetic seed (PII-free)
+
+## Related Skills
+
+| Skill | Relationship |
+|---|---|
+| `write-paper` | Completes the manuscript whose title is used as input |
+| `find-journal` | Identifies whether the target journal requires ICMJE form |
+| `add-journal` | Journal profile records whether ICMJE form is required |
+| `revise` | After revision, updated title may require re-generating forms |
+
+## Non-Goals
+
+- Filling journal-specific disclosure forms (Elsevier Declaration of Interest,
+  BMJ ICMJE derivative, etc.) — only the canonical ICMJE form
+- Handling authors with real disclosures — those authors fill their own forms
+- Signing the forms — authors sign manually after receiving their personalized docx
+- Uploading to Editorial Manager — that remains manual, post-signature