Radiology Innovation Transfer logo

Radiology Innovation Transfer

CommunityPopular
huang-sir1
radiology-innovation-transfer

Assess disclosure, prior-art handoff, rights and transfer readiness; not patentability, FTO or legal advice.

Overview

Publisherhuang-sir1
Repositoryradiology-skills
Skill nameradiology-innovation-transfer
Stars
2K
Forks
20
Bundled files
9
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 9 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by huang-sir1 on GitHub. Read the source before you install it.

Installation

Install the Radiology Innovation Transfer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/huang-sir1/radiology-skills/tree/main/radiology-skills/skills/radiology-innovation-transfer
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/huang-sir1/radiology-skills.git /tmp/radiology-skills
mkdir -p .claude/skills
cp -r /tmp/radiology-skills/radiology-skills/skills/radiology-innovation-transfer .claude/skills/radiology-innovation-transfer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Radiology Innovation Transfer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Radiology Innovation Transfer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Radiology Innovation Transfer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Radiology Innovation Transfer

Use this skill to organize research assets for responsible transfer from an imaging laboratory to a technology-transfer, development or partnership decision. It owns invention-disclosure preparation, patent-landscape research framing, readiness evidence, value hypotheses, rights/dependency mapping, non-confidential summaries and diligence handoffs. It does not give patentability, freedom-to-operate, ownership, inventorship, regulatory, quality-system, contracting or investment advice.

Non-negotiable boundaries

  • Protect before publicizing. Record prior/public disclosure dates, planned abstracts/papers, presentations, repositories, demonstrations and partner conversations. If potentially protectable confidential information has not been reviewed by the institutional TTO/IP owner, return STOP_PUBLIC_DISCLOSURE; prepare only a non-public disclosure packet.
  • Landscape is not a legal opinion. A patent landscape describes search scope, patent families, classifications, assignees, claims/topics and trends. It is not a patentability, validity, inventorship, ownership or freedom-to-operate (FTO) opinion. Preliminary searches are incomplete.
  • Maturity axes remain separate. TRL, MRL, scientific validity, clinical validity/validation, clinical utility, regulatory status, quality-system readiness, interoperability and commercial adoption are not interchangeable. Use evidence-backed exit criteria for each axis.
  • Market interest is not adoption. Interviews, letters, clicks, citations, pilots and investor interest are different signals. None alone proves willingness to pay, procurement, reimbursement, sustained use or patient benefit.
  • Rights before value claims. Map employment/sponsor obligations, foreground/background IP, software and model licenses, training/validation data rights, annotation rights, consent/governance, open-source obligations, vendor dependencies and collaboration agreements. Do not infer ownership.
  • Current facts are live. Patent status, legal rules, assignees, licensing terms, regulatory classification, reimbursement, competitors, prices and market size require LIVE_VERIFICATION_REQUIRED with jurisdiction, source and access date.
  • No confidential fabrication. Never invent dates, contributors, disclosures, performance, customers, costs, regulatory status, patent families or market evidence.

Input passport

Use innovation-disclosure-passport.md to record:

  • asset/invention version, concise problem/solution and intended use;
  • contributors, affiliations, employment, funding, sponsor and collaboration context;
  • conception/development evidence, dated records and public/planned disclosures;
  • code, algorithms, model weights, data, labels/masks, documentation, hardware and know-how;
  • scientific/technical evidence, comparator, failure modes and unresolved reproduction;
  • TRL/MRL and separate clinical, regulatory, quality, interoperability and deployment states;
  • third-party/open-source/data/model licenses and access/consent/governance constraints;
  • prior-art/landscape objective, concepts, synonyms, CPC/IPC classes, jurisdictions and dates;
  • target users, workflow, payer/procurer, alternatives, benefits, burdens and adoption assumptions;
  • confidentiality tier, authorized recipients and institutional TTO/legal contacts.

Do not send confidential material to an external search, model, partner or public tool unless the user has authority and the channel is approved for that material.

Route by mode

NeedModeMain output
Prepare an institutional invention disclosuredisclosure-triageevidence-backed disclosure passport, contributor/dependency questions and TTO handoff
Map prior art and patent activitypatent-landscapereproducible search protocol, family-level landscape and legal-opinion boundary
Assess technical/manufacturing maturityreadiness-assessmentevidence/exit-criteria matrix across TRL, MRL and separate medical-product axes
Test clinical/customer value assumptionsvalue-propositionuser/workflow/problem/alternative/benefit hypothesis and evidence gaps
Map IP, data, model, partnership or license constraintsrights-and-partnershipdependency/rights matrix and questions for authorized owners
Prepare safe external-facing materialnonconfidential-summaryreviewed non-confidential problem/solution/evidence/status summary
Prepare a diligence or transfer decisiondiligence-handoffclaim-source evidence map, red flags, open questions and TTO/regulatory/quality handoffs

Read transfer-modes-and-evidence-gates.md for readiness/value decisions and patent-readiness-and-diligence.md for patent and diligence controls. Consult source-registry.md and recheck every dynamic source.

STOP gates

  • STOP_PUBLIC_DISCLOSURE: protectable/confidential material could be released before TTO/IP review;
  • STOP_CONFIDENTIAL_CHANNEL: proposed tool, repository, email or partner channel is not approved;
  • STOP_RIGHTS: material data/code/model/contract rights or sponsor obligations are unresolved;
  • STOP_IDENTITY: contributor, inventorship or ownership facts are disputed or missing;
  • STOP_EVIDENCE: claimed performance/readiness/value lacks a source artifact and exit criterion;
  • STOP_LEGAL_OPINION: user requests patentability, validity, FTO, ownership or contract advice;
  • STOP_REGULATED_CLAIM: medical-device, clinical, quality or marketing claims lack qualified review;
  • STOP_MARKET_FACT: current competitor, price, market-size, reimbursement or deal fact is unverified;
  • STOP_PHI: patient/image data, DICOM headers, burned-in text or linked artifacts may expose PHI.

STOP blocks the unsafe release or conclusion, not a bounded internal gap analysis.

Radiology-specific diligence

  • Define intended input/output, modality, anatomy, acquisition/reconstruction, DICOM objects, PACS/RIS/worklist integration, latency, failure/fallback and human oversight.
  • Separate algorithm/model IP from training data, labels/masks, pretrained weights, third-party code, scanner/vendor components, deployment stack and tacit clinical/engineering know-how.
  • Trace dataset permissions across centers, consent/waiver, data-use agreements, de-identification, secondary use, commercial use, cross-border transfer and model/derived-artifact clauses.
  • Preserve measurement validity: protocol/scanner shift, QIBA/phantom/test-retest evidence, reference-standard quality and external/local validation remain scientific gates.
  • Distinguish a research prototype from a maintainable product: cybersecurity, logging, versioning, monitoring, update/change control, service support and rollback require owners and evidence.
  • A radiology AI model with high AUC or a prospective pilot is not automatically patentable, regulatory-authorized, reimbursable, interoperable, manufacturable or adoptable.

Workflow and output contract

  1. Freeze the passport, confidentiality tier and decision being supported.
  2. Build a claim-source ledger inside diligence-evidence-map.md: claim, exact artifact, status, owner, date, restrictions and unresolved verification.
  3. Choose the mode. Search patent literature at family/claim/classification level where authorized; include non-patent literature and record query/date/database/coverage.
  4. Score no maturity level without evidence and explicit exit criteria. Record the chosen framework and any medical-imaging adaptation.
  5. Separate evidence from hypotheses in the value proposition. Test workflow burden, alternative, decision maker, buyer/payer, resource effect and adoption barrier.
  6. Run confidentiality, IP/rights, scientific, clinical, regulatory/quality, interoperability, operational and market gates independently.
  7. For external material use nonconfidential-summary.md and obtain the authorized TTO/legal/communications release decision.

Return Decision and scope, Disclosure passport, Evidence/claim map, Landscape or readiness method, Rights/dependency matrix, Value hypotheses, Red flags and STOP ledger, Qualified-owner handoffs, and Decision status.

Decision status is INTERNAL_TRIAGE, READY_FOR_TTO_REVIEW, READY_FOR_QUALIFIED_DILIGENCE, READY_FOR_AUTHORIZED_NONCONFIDENTIAL_USE, or STOP—never “patentable”, “FTO clear” or “investment ready”.

Handoffs and non-ownership

  • Patentability, FTO, validity, inventorship, ownership, filing and contracts → institutional TTO and qualified patent/legal counsel.
  • Intended use, clinical validation/utility, human factors and deployment → radiology-translation; formal regulatory and QMS decisions → qualified regulatory/quality owners.
  • Imaging acquisition/measurement → radiology-acquisition-qc; disease pathway → radiology-clinical-domain; data/consent/governance → radiology-data / radiology-ethics.
  • Underlying study design/statistics → radiology-design / radiology-stats; grant proposal → radiology-grant; manuscript → radiology-writing.
  • Public adaptation of an authorized non-confidential source → radiology-dissemination; this skill prepares the source but does not publish or market it.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Radiology Innovation Transfer AI skill do?

Assess disclosure, prior-art handoff, rights and transfer readiness; not patentability, FTO or legal advice.

Why use Radiology Innovation Transfer on TypingMind?

Because you install it once and use it with any model. Radiology Innovation Transfer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Radiology Innovation Transfer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/huang-sir1/radiology-skills/tree/main/radiology-skills/skills/radiology-innovation-transfer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Radiology Innovation Transfer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Radiology Innovation Transfer?

As many as you like. As long as a model supports skills, you can use Radiology Innovation Transfer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Radiology Innovation Transfer AI skill free?

It is published on GitHub by huang-sir1. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇