radiology-bibliometrics
Build reproducible radiology bibliometrics with corpus identity, disambiguation and sensitivity; not reviews.
Install / Use
npx skills add huang-sir1/radiology-skills --skill radiology-bibliometricsInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
LegalSupported Platforms
Our assessment of radiology-bibliometrics
radiology-bibliometrics scores 80/100 on our quality scale, 190th of 208 Legal skills we index.
Its SKILL.md is 7.8 KB long, split into 7 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-bibliometrics is actively maintained.
- 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 2026-10-01. Automated pattern scan on 2026-10-01. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
radiology-bibliometrics compared with similar skills
All 4 of these similar skills score higher than radiology-bibliometrics; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| radiology-bibliometrics (this skill)by huang-sir1 | 80 | 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-bibliometrics?
- Run
npx skills add huang-sir1/radiology-skills --skill radiology-bibliometrics. The install tabs above show the steps for each supported agent. - Which AI agents does radiology-bibliometrics work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is radiology-bibliometrics 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-bibliometrics still maintained?
- The repository was last updated about 2 months ago, so radiology-bibliometrics is actively maintained.
Skill content
View source on GitHubname: radiology-bibliometrics description: "Build reproducible radiology bibliometrics with corpus identity, disambiguation and sensitivity; not reviews."
Radiology Bibliometrics
Use this skill to describe and map a frozen scholarly corpus: publication/citation patterns, collaboration, topical structure and network change. It owns the bibliometric analysis contract and responsible interpretation. It does not determine whether an intervention works, whether evidence is trustworthy, or whether a topic is scientifically innovative.
Non-negotiable boundaries
- Corpus before metrics. Consume a versioned
corpus passportcontaining database/index coverage, exact query, filters, document types, languages, retrieval date, export/API route and deduplication state.radiology-searchsupplies or freezes the scientific corpus. - Coverage is part of the result. Web of Science, Scopus, PubMed, OpenAlex, Crossref and regional indexes cover different works, references and document types. Counts from one source are not a census of scholarship and should not be silently merged with another.
- Identity is evidence, not a name string. Use authenticated/persistent identifiers where available, then affiliation, coauthor, topic and time evidence. Preserve unresolved author and institution clusters; name-only matching is insufficient.
- Counting choices change claims. Declare full or fractional counting, the fractional unit, denominator, treatment of multi-affiliation and hyperauthorship, and sensitivity to alternatives.
- Normalize before comparison. Citation comparisons require an explicit field/classification, document type, publication year and citation window. Recent work is right-censored.
- Networks are model outputs. Edge definition, normalization, thresholds, pruning, clustering algorithm, resolution, seed and label rules must be recorded. A colored community is not a natural scientific truth; test threshold and community stability.
- Metrics are not merit. Citation, centrality, journal metrics and altmetrics indicate forms of attention or network position; they do not establish quality, causal impact, clinical benefit or innovation. Quantitative indicators support, not replace, expert and qualitative judgment.
- No evidence-synthesis laundering. Co-citation, keyword frequency or publication volume cannot answer a diagnostic, prognostic or treatment-effect question.
Input passport and STOP gates
Start with corpus-passport.md. Required fields include:
- purpose, unit of assessment, date range and intended comparison;
- database/platform, indexes, coverage limits, query and retrieval timestamp;
- export fields, cited-reference availability, API/snapshot/version and access/license constraints;
- inclusion/exclusion, document types, preprints/proceedings, language and correction/retraction rules;
- DOI and non-DOI deduplication; work/version/family policy;
- author/institution identifiers, disambiguation evidence and unresolved cases;
- metric definitions, counting method, normalization, citation window and network specification.
Return a STOP state when:
STOP_CORPUS: query, database coverage, retrieval date or inclusion logic is missing;STOP_IDENTITY: unresolved author/institution identity materially changes ranks or networks;STOP_METRIC: a requested indicator lacks a denominator, window or reproducible definition;STOP_NETWORK: the network is dominated by arbitrary thresholds, disconnected fragments or unstable communities without sensitivity analysis;STOP_INTERPRETATION: the requested conclusion equates metrics with quality, clinical impact or innovation;STOP_ACCESS: data reuse, API terms or export rights do not support the proposed analysis.
A STOP may still permit a diagnostic audit and repair plan; it blocks definitive comparative claims.
Route by mode
| Need | Mode | Main contract |
|---|---|---|
| Check search/export fitness | corpus-audit | coverage, query, retrieval, fields, DOI/version dedup and missingness |
| Describe output and attention | descriptive-impact | time series, document/citation distributions and normalized indicators |
| Map coauthorship or institutions | collaboration-network | identity resolution, full/fractional counting, edge and consortium policy |
| Co-word, co-citation or coupling map | science-mapping | feature construction, normalization, thresholds, clustering and labels |
| Compare authors/institutions/countries | benchmarking | fair comparison set, counting, normalization, uncertainty and responsible metrics |
| Examine longitudinal topic/network change | temporal-evolution | fixed/moving windows, database drift, label continuity and stability |
| Reproduce or challenge a prior map | audit-reanalysis | frozen inputs, method replay, sensitivity matrix and claim-drift ledger |
For methods read analysis-contract-and-methods.md. For claim limits read responsible-interpretation.md. Use the source registry for source/version status.
Radiology-specific controls
- Search across radiology, nuclear medicine, medical physics, imaging informatics, engineering and computer-science venues when the question crosses them; report conference/preprint asymmetry.
- Preserve modality, anatomy, task, clinical purpose, reference-standard and development/validation/ deployment state. Keyword presence alone cannot reliably assign clinical maturity.
- Disambiguate hospitals, university systems, cancer centers and consortia; report whether networks count authors, addresses, organizations or countries.
- Treat multi-center imaging consortia and hyperauthored AI papers explicitly; a consortium edge can dominate maps without representing ordinary collaboration.
- Vendor names, scanner families and software ecosystems may be affiliation/technology entities, not scholarly authors; do not mix entity types.
- High publication volume in imaging AI does not prove clinical uptake, regulatory authorization or improved patient outcomes.
Workflow and output contract
- Freeze the corpus passport and an immutable record-ID/DOI list with exclusions and reasons.
- Resolve work versions and identities; keep a disambiguation ledger and manual-review queue.
- Define every metric, denominator, count, normalization and time window before computing it.
- Define networks completely, run threshold/resolution/seed and counting sensitivities, and assess community/centrality stability rather than presenting a single attractive map.
- Build bibliometric-analysis-and-claim-ledger.md.
- Return:
Corpus flow,Coverage and missingness,Identity ledger,Metric dictionary,Network specification,Sensitivity/stability results,Claim-source ledger,Limitations, andReproducibility manifest.
Label conclusions as DESCRIPTIVE, COMPARATIVE, NETWORK_STRUCTURAL, HYPOTHESIS_GENERATING or
NOT_SUPPORTED. Never promote them to evidence-effect, quality or innovation conclusions.
Handoffs and non-ownership
- Corpus retrieval/search reproducibility →
radiology-search. - Novel question and qualitative opportunity assessment →
radiology-frontier. - Intervention/diagnostic/prognostic evidence conclusions and risk-of-bias appraisal →
radiology-systematic-review. - Verification of an individual citation or reference metadata →
radiology-citation. - Statistical uncertainty methods beyond the bibliometric contract →
radiology-stats. - Figures and tables for publication →
radiology-figure/radiology-table. - This skill does not rank people for hiring/funding, infer research quality from journal metrics, or make causal claims about collaboration, policy or clinical impact.
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.
