radiology-consensus-guideline
Design/audit consensus and evidence-to-recommendation products; not review synthesis or endorsement.
Install / Use
npx skills add huang-sir1/radiology-skills --skill radiology-consensus-guidelineInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
LegalSupported Platforms
Our assessment of radiology-consensus-guideline
radiology-consensus-guideline scores 82/100 on our quality scale, 164th of 208 Legal skills we index.
Its SKILL.md is 9.9 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-consensus-guideline is actively maintained.
- Our last check on 2026-11-07 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 2026-10-01. 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-consensus-guideline compared with similar skills
All 4 of these similar skills score higher than radiology-consensus-guideline; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| radiology-consensus-guideline (this skill)by huang-sir1 | 82 | 1.8k | 56d ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 116.8k | 8d ago | CLAUDE.md |
| Claude-Code-Game-Studiosby Donchitos | 100 | 39.7k | 7d ago | CLAUDE.md |
| x402by browser-use | 100 | 121.0k | 3d ago | SKILL.md |
| algorithmic-artby anthropics | 100 | 177.9k | 55d ago | SKILL.md |
Frequently asked questions
- How do I install radiology-consensus-guideline?
- Run
npx skills add huang-sir1/radiology-skills --skill radiology-consensus-guideline. The install tabs above show the steps for each supported agent. - Which AI agents does radiology-consensus-guideline 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-consensus-guideline 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-consensus-guideline still maintained?
- The repository was last updated about 2 months ago, so radiology-consensus-guideline is actively maintained.
Skill content
View source on GitHubname: radiology-consensus-guideline description: "Design/audit consensus and evidence-to-recommendation products; not review synthesis or endorsement."
Radiology Consensus and Guideline Development
Use this skill to design, run-plan or audit a consensus statement, appropriateness project, practice parameter, technical standard or clinical practice guideline. It owns the panel/process, evidence-to-decision record, consensus protocol, recommendation ledger and lifecycle plan. It does not perform the underlying systematic review, confer society endorsement, set a legal standard of care or let expert voting substitute for evidence.
Choose the product and mode
First declare the product: clinical-practice-guideline, appropriateness-criteria,
practice-parameter, technical-standard, expert-consensus-statement or
research-priority/definition-consensus. Do not use these labels interchangeably.
| Mode | Use when | Required result |
|---|---|---|
| scoping | product, users, questions or authority are unsettled | scope, product decision, stakeholders, evidence needs and stop conditions |
| protocol | a versioned development plan is needed before evidence/panel decisions | panel, COI, evidence, consensus, consultation and update protocol |
| evidence-to-decision | a frozen evidence synthesis must become recommendation judgments | GRADE/compatible EtD ledger with explicit uncertainty |
| formal-consensus | Delphi, RAND/UCLA or nominal group work is planned or audited | prespecified rounds, thresholds, denominator, feedback, dissent and reporting record |
| audit-update-retire | an existing statement/guideline is reviewed for trustworthiness or currency | method audit, surveillance result, update/retirement and supersession map |
Read references/evidence-to-recommendation.md for the systematic-review handoff, GRADE/EtD and recommendation wording. Read references/formal-consensus-methods.md only for a formal consensus exercise. Read references/radiology-guidance-lifecycle.md for appropriateness criteria, practice parameters, technical standards, implementation, updating and retirement. Verify methods and authority through references/source-registry.md.
Input passport
Record:
product and mode | sponsor/developer and actual adoption authority | jurisdiction/organization | scope, population, modality/test/intervention/comparator/outcomes/setting | intended users and affected people | panel roles, patient/public members and COI records | frozen systematic-review handoff/version/currency | certainty framework | consensus method and prespecified rule | draft and consultation artifacts | implementation context | publication/update/retirement owner | user authority for edits or external communication.
Missing adoption authority, panel decisions, COI management, patient/public participation, evidence
certainty or official status remains NOT_VERIFIED. Advisory drafting is not an endorsed guideline.
Choose the evidence lane for the declared product. A clinical recommendation presented as
evidence-based requires the relevant systematic-review/EtD handoff. A research-priority or
definition-consensus exercise instead requires transparent item generation, search/mapping or
stakeholder evidence, panel judgments and limits; use NOT_APPLICABLE_GRADE when it makes no
clinical-effect or recommendation-strength claim. A generic Delphi protocol does not require an
invented effect synthesis or GRADE rating.
Core evidence and recommendation states
- Evidence handoff:
EVIDENCE_READY,EVIDENCE_PARTIAL,EVIDENCE_ABSENTorEVIDENCE_STALE. - Recommendation:
DRAFT,CONDITIONAL,STRONG,NO_RECOMMENDATION,RESEARCH_ONLY,SUPERSEDEDorRETIREDonly when defined by the selected framework and authorized process. - Consensus result:
CONSENSUS_REACHED,CONSENSUS_NOT_REACHED,STABLE_DISAGREEMENT,ATTRITION_LIMITEDorNOT_ASSESSABLE.
Evidence certainty, recommendation strength and consensus percentage are different fields. A high vote does not upgrade low/absent evidence, and a low-certainty body does not automatically prohibit a strong recommendation when a transparent framework supports an exceptional case.
Required workflow
- Lock the product and authority. Define who will use the output, for which decision, and who can officially adopt/endorse it. Use “draft” or “advisory” until a verified process confers status.
- Scope the decision. Specify population, imaging scenario, modality/test, comparator, downstream action, patient-important outcomes, setting, exclusions and equity/access questions.
- Constitute the panel. Include relevant clinical disciplines, radiologists, referrers, technologists/medical physicists when technical decisions are material, methodologists, implementers and patients/public or other affected representatives. Record balance, recruitment, roles, COI assessment, management and recusals.
- Accept the product-appropriate evidence handoff. For an evidence-based clinical
recommendation, require search currency, study-family/effect-row identity, risk-of-bias/
applicability, synthesis and certainty from
radiology-systematic-review. For priorities or definitions, record item sources, mapping/search limits, stakeholder input and traceable revision; a full effect review is required only if the intended claim needs it. Do not relabel selected references or panel memory as a systematic review. - Run the applicable decision process. For clinical recommendations, record benefits/harms, certainty, values/preferences, resources, equity, acceptability and feasibility. Link diagnostic accuracy to downstream management and patient outcomes. For priorities or definitions, report explicit selection criteria, content/semantic judgments and dissent without inventing clinical effects, GRADE certainty or recommendation strength.
- Use formal consensus only for its declared purpose. Prespecify method, panel, rounds, anonymity/interactions, feedback, denominator, threshold, stability, attrition, tie/disagreement handling and stopping. Use templates/consensus-guideline-protocol.md.
- Draft atomic recommendations or consensus items. Each clinical recommendation states population/scenario, action, comparator/conditions, strength, certainty, rationale, harms/burden, implementation conditions, exceptions, dissent and research gaps. Use templates/recommendation-etd-ledger.md. For priorities/definitions, use the item register and formal-consensus result sections instead; include wording, provenance, scope, rationale and status, with clinical EtD fields not applicable.
- Consult and quality-control. Preserve stakeholder comments, responses, panel changes, unresolved disagreement and external review. Reporting-checklist completion does not prove method quality or endorsement.
- Plan implementation and lifecycle. Define dissemination, feasibility tools, monitoring, surveillance, update triggers, versioning, supersession and retirement. Imaging technology, contrast/tracers, dose, reconstruction, AI versions and clinical standards can make guidance stale.
Stop and escalation gates
Return GUIDANCE_STOP_AND_REFRAME when product or adoption authority is misrepresented; scope or
decision scenarios are undefined; the evidence packet is missing/stale for a claim presented as
evidence-based; material panel COI cannot be managed; affected patients/public or essential
disciplines are systematically excluded without justification; consensus thresholds are chosen after
results; attrition, dissent or denominator is hidden; expert votes are used to manufacture evidence;
or a current clinical recommendation could expose patients to unreviewed harm.
Escalate formal endorsement, legal/regulatory interpretation and individual patient decisions to the responsible society, institution, regulator or clinical team. The skill may prepare evidence and drafts but cannot adopt, endorse or implement official guidance.
Output contract
Product, scope and authority passportPanel/stakeholder/patient-public and COI matrixProduct-appropriate evidence handoff and currency verdict— systematic review for the clinical evidence claim, or item-generation/mapping/stakeholder evidence for priorities and definitionsQuestion/outcome and imaging-scenario mapGRADE or compatible evidence-to-decision ledgerwhen applicable; otherwiseNOT_APPLICABLE_GRADEplus the item-selection/definition rationaleConsensus protocol and result— rounds, thresholds, denominator, attrition and dissentRecommendation or consensus-item ledger— strength, certainty and consensus kept separate; clinical strength/certainty is not invented for a terminology or research-priority itemImplementation, equity, monitoring and research-gap planConsultation, external-review and change-response recordVersion, update, supersession and retirement plan with exact non-endorsement boundary
Handoffs and non-ownership
- Search, screening, extraction, risk of bias, synthesis and evidence certainty ->
radiology-systematic-review; current clinical facts ->radiology-clinical-domain. - Quantitative Delphi/RAND agreement or comparative inference ->
radiology-stats; CEA/CUA, budget impact, ICER/QALY, PSA/VOI and economic-model evidence consumed by an EtD ->radiology-health-economics. This skill weighs the supplied economic evidence in a recommendation; it does not build or authorize the economic model. - Reporting guideline/quality checklist ->
radiology-reporting; prose, tables, figures and decks -> their artifact owners. - Society boards, institutions, regulators and clinical teams retain endorsement, adoption, implementation, legal and patient-care authority.
Related Skills
taste-skill
116.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
Claude-Code-Game-Studios
39.7kTurn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.
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.
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.
