radiology-prereview
Run author, peer or editorial scientific review with traceable findings; not checklists or upload audits. CN: 模拟审稿、预审、大修风险
Install / Use
npx skills add huang-sir1/radiology-skills --skill radiology-prereviewInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
MarketingSupported Platforms
Our assessment of radiology-prereview
radiology-prereview scores 87/100 on our quality scale, 362nd of 642 Marketing skills we index.
Its SKILL.md is 14 KB long, well organised into 8 sections and no code examples: a thorough specification that gives an agent plenty to work with.
With 1,785 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so radiology-prereview is actively maintained.
- Our last check on 2026-11-02 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-02. Automated pattern scan on 2026-10-02. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
radiology-prereview compared with similar skills
All 4 of these similar skills score higher than radiology-prereview; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| radiology-prereview (this skill)by huang-sir1 | 87 | 1.8k | 56d ago | SKILL.md |
| x402by browser-use | 100 | 121.0k | 3d ago | SKILL.md |
| algorithmic-artby anthropics | 100 | 177.9k | 55d ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 55d ago | SKILL.md |
| designby nextlevelbuilder | 100 | 149.0k | 6d ago | SKILL.md |
Frequently asked questions
- How do I install radiology-prereview?
- Run
npx skills add huang-sir1/radiology-skills --skill radiology-prereview. The install tabs above show the steps for each supported agent. - Which AI agents does radiology-prereview work with?
- It is written for Zed, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is radiology-prereview safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is radiology-prereview still maintained?
- The repository was last updated about 2 months ago, so radiology-prereview is actively maintained.
Skill content
View source on GitHubname: radiology-prereview description: "Run author, peer or editorial scientific review with traceable findings; not checklists or upload audits. CN: 模拟审稿、预审、大修风险"
Scientific Prereview and Journal Peer Review
Use this skill to be the harshest fair reviewer before the real one is, or to structure an authorized confidential journal review. It reads the manuscript the way a methods-literate Radiology/Lancet-DH/Nature-Medicine reviewer would, finds the dealbreakers, and returns a reviewer-style report you can act on — so issues are fixed on your terms, not surfaced in a rejection.
Core stance
- Adversarial but on the author's side. Hunt for the weakness a reviewer will weaponise, then hand back the fix — not just the criticism.
- Dealbreakers first. Invalid independent-unit splits, data leakage, missing claim-required validation, undefined labels, unclear segmentation, incomplete statistics, overclaiming — these decide the outcome. Triage them before cosmetics. Apply each criterion to the study's actual design and claim; retrospective or single-center design alone does not establish invalidity.
- Map to the guideline. Tie each issue to the specific CLAIM/CLEAR/TRIPOD+AI/STARD/IBSI item or methodological risk a reviewer would cite (→ radiology-reporting).
- Check the claims against the evidence. Does the abstract/Discussion overstate AUC, correlation, or retrospective results? Flag every claim the data don't support.
- Honest readiness verdict. Give an editor-style recommendation (ready / minor / major / not yet) with the reasons — don't reassure.
- Integrity. Never invent compliance, never wave through a real weakness to be encouraging.
- Mode before content.
author-prereview,journal-peer-review,editorial-synthesisandthesis-prereviewshare a scientific engine but have different audiences, confidentiality, conflicts, outputs and authority. Never leak editor-only material into author comments.
When to use
- "Mock-review my paper before I submit." / "投稿前帮我模拟审稿、做预审。"
- "Find the holes a reviewer will find."
- "Is this ready for [target journal], or what must I fix first?"
- After drafting, before
radiology-journalselection and submission. - "I was invited to review this confidential manuscript; write comments to authors and editor."
- "Audit my dissertation chapter chain and defense claims before committee review."
For mechanism-only, use radiology-radiogenomics: manuscript-review as the scientific owner. For
imaging-mechanism, require its mechanism/bridge findings before synthesizing this imaging panel.
Do not impose scanner, AUC, reader-study or deployment criteria on a standalone transcriptomic study
unless its actual question and design activate them.
For evidence-synthesis, use radiology-systematic-review as the scientific owner and select
evidence-synthesis-review. Require frozen protocol, search, selection-flow, extraction,
risk-of-bias-applicability, synthesis, and certainty artifacts. Set the radiogenomics
scientific_handoff_digest to not-applicable; review the study-family/report/effect-row hierarchy,
dependence, pooling decision, certainty and synthesized claim ceiling instead of imposing a
primary-data or mechanism handoff.
When to open extra files
| File | Open when |
|---|---|
| references/review-dimensions.md | The full set of dimensions to review (design, data, labels, leakage, stats, reporting, figures, claims, sharing) |
| references/review-modes-and-editorial-governance.md | Always before a journal-review, editorial-synthesis or thesis-prereview route; also when author-side versus reviewer-side authority is ambiguous |
| references/dealbreakers.md | The hard issues that trigger desk-reject / major revision, with how to detect and fix each |
| references/review-report-format.md | The reviewer-report + editor-recommendation output structure |
| references/pre-submission-hard-gates.md | Final submission readiness audit, rejected-paper rescue, contribution map, reviewer objection register, or when deciding whether a paper is truly ready |
| references/ai-radiogenomics-pitfall-audit.md | Imaging-AI, foundation-model, VLM, radiomics, deep radiomics, or radiogenomics manuscripts need a targeted audit for leakage, external validation, site/scanner confounding, superficial XAI, weak clinical utility, or mechanism overclaim |
| references/multi-reviewer-panel.md | Full manuscripts, top-tier targets, conflicting strengths/risks, or when the user wants independent reviewer reports rather than one blended checklist |
| references/scientific-prereview-receipt-contract.md | Final scientific prereview/re-review needs a canonical digest-bound receipt for response or submission handoff |
| templates/evidence-synthesis-source-artifacts.template.json | evidence-synthesis-review needs the complete seven-role frozen artifact set before the generic prereview receipt is instantiated |
| templates/prereview-governance-gates.template.json | Any final-readiness review needs separate human-subjects authorization and data/code-sharing gate receipts |
Workflow
- Select the review mode and governance state using
review-modes-and-editorial-governance.md. In a real journal review, freeze the journal policy, confidentiality, COI/recusal, assistance and AI/tool authorization before processing content. Unknown external-processing permission isSTOP_CONFIDENTIALITY_UNRESOLVED. - Intake — manuscript (or sections), study scope, source artifact/version/SHA-256, canonical project-state digest, modality-role digest, analysis-lock digest, claim-registry digest, scientific packet digest when present, study type, target journal/tier if known.
- Classify the study and load the dimensions (review-dimensions.md); pull the right
guideline stack via
radiology-reporting. Forevidence-synthesis, first consume the frozen review packet fromradiology-systematic-review, then audit protocol deviations, search/selection completeness, extraction traceability, RoB/applicability, synthesis reproducibility and certainty. - For final readiness checks, open
pre-submission-hard-gates.mdand score each hard gate as PASS / CONDITIONAL / FAIL before writing softer reviewer comments. For any applicable human-subjects activity, consume a versionedradiology-ethics: human-subjectsreceipt whose approval, consent/waiver and data-use authorization fields areDOCUMENT_VERIFIED; bind its artifact path and SHA-256 intemplates/prereview-governance-gates.template.json, then runscripts/validate_prereview_governance_gates.py <receipt> --artifact-root <project-root> --require-ready. Missing, author-reported, expired, conflicting or out-of-scope authority is an absoluteSTOP, neverCONDITIONAL. Evaluate Data Availability and Code Availability in the separate sharing gate; a sharing statement cannot repair missing authorization and an ethics receipt does not prove that promised sharing is feasible. Any applicable authorizationSTOPforcesNot ready; venue choice, lower-scope claims, declared risk or editor preference cannot override it. - Hunt dealbreakers (dealbreakers.md) — partition hygiene, leakage, external validation, labels/reference standard, segmentation reproducibility, statistical completeness, overclaim, data/code availability.
- For AI/radiogenomics manuscripts, open
ai-radiogenomics-pitfall-audit.mdand audit the common failures that make a high-AUC paper look untrustworthy. - Review each dimension — give every decision-bearing issue a stable Finding ID and record
Finding ID | source artifact digest | evidence anchor | Severity (P0/P1/P2) | criterion | affected Claim IDs | source_review_state | minimum repair | closure evidence | residual boundary. P0/P1 findings always setrequired_for_pass=true; only advisory P2 findings may be nonblocking. - For full/high-impact review, open
multi-reviewer-panel.md. The default is alens-separatedpanel: clinical, methods/statistics and imaging-AI/reproducibility reports are distinct, but they are not called independent when one agent/person shares context across them. Use the wordindependentonly when reviewer contexts are isolated, all reviewers receive the same frozen fact base/source digests, no reviewer sees another report, and each report is frozen with its own output SHA-256 before editor synthesis. Do not invent reviewer identities. - Run two-pass claim audit for submission-facing text — abstract, Key Results, figure
legends, tables, graphical abstract, and Discussion comparison/novelty claims should be
extracted first, then verified via
radiology-citation/references/claim-verification-gate.md. - Check claims vs evidence — abstract, Key Results, Discussion: is every claim bounded by the data?
- Write the report (review-report-format.md) — reviewer comments by severity + an editor-style
recommendation + a prioritised fix order (what unlocks the most). In
journal-peer-review, keep comments to authors and confidential comments to editor separate; the recommendation is advisory and must not be presented as an official decision. - Freeze the re-review yardstick — preserve finding IDs, criteria, source digest, affected
Claim IDs, immutable source-review state and closure evidence for
radiology-responseand later revision verification. - Generate the canonical prereview receipt — open
scientific-prereview-receipt-contract.md, instantiatetemplates/scientific-prereview-receipt.template.json, bind every source artifact and upstream digest, then runscripts/validate_scientific_prereview_receipt.py <receipt> --write-digest. Forevidence-synthesis, copy the seven rows fromtemplates/evidence-synthesis-source-artifacts.template.jsonintosource_artifacts; do not replace them with a manuscript-only row or a radiogenomics handoff. A global PASS cannot conceal a requiredNOT_VERIFIED/PARTIAL/MADE_WORSEfinding or any unresolved placeholder.
Output contract
Summary assessment— 3–5 sentences: what the paper does, its real strength, its decisive weakness, and the readiness verdict.Review-mode governance receipt— mode, audience, frozen source/version, review policy, confidentiality, COI/recusal, assistance, AI/tool authorization and authority boundary.Major/Blocker comments— numbered, reviewer-style, each with location, the guideline/risk, and the concrete fix.Minor comments— numbered, smaller issues.Claims vs evidence— overclaims and the bounded rewording.Claim audit status— for final readiness: extraction complete? verification complete? unsupported/numerical/visual-table claims remaining?Hard-gate table— if final readiness is requested: contribution, data integrity, validation, statistics, reporting, figures, citation, human-subjects authorization, data/code sharing, and reviewer-objection status. Keep authorization and sharing in separate rows.Scientific prereview state—SCIENTIFIC_PREREVIEW_PASS,SCIENTIFIC_PREREVIEW_CONDITIONAL, orSCIENTIFIC_PREREVIEW_FAIL, with reasons. This is not the submission Skill'sREADY*namespace.Canonical prereview receipt— validated receipt path, scope route, finding/arti
Truncated for display — read the full file on GitHub.
Related Skills
x402
121.0kSet up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
design
149.0kComprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini, Atlas Cloud, or MuAPI AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG…
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
