agentsclimarketplace

Jama oncology

Skill brycewang-stanford/Awesome-Journal-Skills/Clinical-Medicine-Journal-Skills/skills/jama-oncology

Use when targeting JAMA Oncology or deciding whether a clinical-oncology study fits this venue. Encodes the journal's fit, the cancer-trial and outcomes-research evidence bar, reporting-guideline and trial-registration requirements, JAMA Network house style, official-submission re-check, and desk-reject heuristics. Venue-fit aid only, not clinical advice.From its SKILL.md

Install
npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill jama-oncology

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

7.6 KB, ~1.6k tokens by cl100k_base, as published. Nobody here has run it

JAMA Oncology (jama-oncology)

Journal positioning

JAMA Oncology is a JAMA Network specialty journal for clinical and translational oncology research aimed at a broad cancer-care readership — medical, surgical, and radiation oncologists, as well as cancer-epidemiology and outcomes researchers. It favors practice-relevant work: randomized cancer trials, comparative-effectiveness and real-world outcomes analyses, screening and prevention studies, and biomarker work tied to a clinically meaningful endpoint. It is positioned as a general oncology venue with JAMA's emphasis on absolute benefit, toxicity, and patient-centered outcomes, distinct from a society flagship such as Annals of Oncology (ESMO). Single-arm early-phase reports with no comparator, descriptive molecular series, and surrogate-only signals with weak clinical translation are a weak fit. This skill is a fit / venue-selection / re-framing aid; it is not clinical or regulatory advice and does not replace the journal's current instructions for authors. Before submitting, re-check the live JAMA Oncology author instructions.

When to trigger

  • The author names JAMA Oncology for a clinical, epidemiologic, or outcomes oncology study and wants a fit/framing check.
  • A cancer study must be re-framed around a clinically meaningful survival, toxicity, or quality-of-life endpoint for a broad oncology audience.
  • The author is choosing between JAMA Oncology, JAMA, and a society or subspecialty oncology journal (e.g., Annals of Oncology).
  • The author needs the journal's reporting-guideline, registration, and desk-reject expectations for oncology work.

Scope & topic fit

  • Randomized oncology trials (phase 2/3) reporting survival, response, toxicity, or patient-reported outcomes, including practice-de-escalation trials.
  • Comparative-effectiveness and real-world-evidence studies using cancer registries, claims, or institutional cohorts with rigorous confounding control.
  • Cancer screening, early-detection, and prevention studies with clinically meaningful endpoints and harms accounting.
  • Prognostic and predictive biomarker studies validated against an outcome, not just associated with a molecular feature.
  • Health-services, disparities, financial-toxicity, and survivorship research in oncology.
  • Pooled analyses and meta-analyses answering a focused, decision-relevant cancer question.

Method & evidence bar

  • Trials must be adequately powered with a prespecified primary endpoint; overall survival and validated surrogates are preferred, and surrogate-only endpoints need explicit justification of clinical relevance.
  • The applicable reporting guideline and checklist are required: CONSORT for trials, STROBE for observational/registry studies, PRISMA for systematic reviews, REMARK-style rigor for tumor-marker work.
  • Trials require prospective registration; registration number, protocol, and statistical-analysis plan are expected, including amendments.
  • Survival analyses must report absolute differences, hazard ratios with confidence intervals, and adequate follow-up; toxicity (graded per a standard scheme) must be reported alongside efficacy.
  • Real-world/registry claims must address immortal-time, selection, and indication bias; causal language must match the design.
  • Biomarker claims need a prespecified cut-point, an independent validation set, and reporting of analytic performance.

Structure & house style

  • JAMA Network format with a structured abstract and a Key Points box; re-check current article types (Original Investigation, Brief Report, Research Letter, etc.) and limits on the live guide.
  • The introduction frames a focused, decision-relevant cancer question; the discussion states the practice implication and net clinical benefit plainly.
  • Tables/figures follow JAMA Network statistical-reporting standards; CONSORT/STROBE flow diagrams, Kaplan-Meier curves with numbers at risk, and toxicity tables are expected where applicable.
  • Supplements carry the protocol, SAP, full toxicity and subgroup analyses, and consort/biomarker checklists.

Official-submission checklist

  • Before giving submission-ready advice, read ../../resources/source-basis.md and ../../resources/official-source-map.md; start from the ICMJE and JAMA Network anchors, then cite the current JAMA Oncology page you checked.
  • Search the live site for "JAMA Oncology instructions for authors" and follow the current version.
  • Re-check article types and word/reference/table limits, structured-abstract and Key Points format, and the JAMA Network statistical-reporting requirements.
  • Confirm trial registration, the reporting checklist (CONSORT/STROBE/PRISMA), the data-sharing statement, and protocol/SAP submission.
  • Re-check IRB/ethics and consent statements, ICMJE authorship and conflict-of-interest disclosure (industry ties are scrutinized in oncology), funding, and AI-use disclosure.
  • If the live official instructions conflict with this skill, the official instructions win.

Pre-submission self-check

  • The study answers a decision-relevant cancer question with a clinically meaningful endpoint and net-benefit framing.
  • The primary endpoint is prespecified; survival/toxicity are reported with absolute and relative measures and adequate follow-up.
  • The correct reporting checklist (CONSORT/STROBE/PRISMA) is completed and attached.
  • Trials are prospectively registered with the number in the manuscript; protocol/SAP provided.
  • Registry/real-world analyses address immortal-time, selection, and indication bias; biomarkers are independently validated.
  • IRB/consent, ICMJE disclosures (including industry funding), and a data-sharing statement are prepared.

Common desk-reject triggers

  • Single-arm early-phase reports with no comparator presented as practice-relevant.
  • Surrogate-only endpoints (e.g., response rate, PFS) framed as definitive clinical benefit without justification.
  • Registry/real-world analyses with immortal-time or indication bias and overstated causal claims.
  • Biomarker associations with no prespecified cut-point or independent validation.
  • Missing trial registration, protocol, or toxicity reporting alongside efficacy.
  • Narrow molecular or subspecialty interest better served by a society or basic-science cancer journal.

Re-routing decision

  • ESMO-society readership or European practice framing → annals-of-oncology.
  • Broadly practice-changing, top-tier cancer trial → general medicine (jama / NEJM / The Lancet in the natural-science bundle).
  • General internal-medicine relevance over oncology specialty → jama-internal-medicine.
  • Cancer imaging with an imaging-method core → radiology.
  • Surgical-oncology technique or perioperative focus → jama-surgery.

Output format

[Fit] High / Medium / Low (one-line reason)
[Target] JAMA Oncology
[Specialty tags] <2–3 closest oncology topics>
[Study design / reporting guideline] <RCT-CONSORT / registry-STROBE / review-PRISMA / biomarker-REMARK>
[Method/evidence] <does power, endpoint, registration, and validation clear the bar?>
[Top risk] <the single most likely reason for rejection>
[Official items to re-check] <article type / registration / checklist / toxicity / ethics / disclosures>
[Re-route suggestion] <if not a fit, a better-matched venue>

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most healthcare skills give in ~1.6k tokens

Counted across 147 of the 152 authors here whose files we hold, read 2026-08-07

  • Export trial data to CSV formatin 11 of 147, across 2 files
  • Retrieve trial details using an NCT IDin 11 of 147, across 2 files
  • Split clinical datasets strictly by patientin 11 of 147, across 3 files
  • Use the ClinicalTrials.gov API v2in 10 of 147, across 1 file
  • Search trials by condition, drug, location, status or phasein 10 of 147, across 1 file
  • Use maximum page size for bulk data retrievalin 10 of 147, across 1 file
  • Extract and summarize key study informationin 10 of 147, across 1 file
  • Combine multiple filters for targeted searchesin 10 of 147, across 1 file
  • Print and review dataset statistics before modelingin 8 of 147, across 1 file
  • Start model development with simple baselinesin 8 of 147, across 1 file
  • Match preprocessing processors directly to data typesin 8 of 147, across 1 file
  • Monitor validation metrics for task type and class imbalancein 8 of 147, across 1 file

Said here and by no other author read

  • Check live author instructions before submission
  • Format manuscripts using JAMA Network style
  • Require prospective trial registration
  • Attach applicable reporting checklists
  • Address immortal-time and indication biases
  • Validate biomarker claims against outcomes

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.