Radiology Dissemination logo

Radiology Dissemination

CommunityPopular
huang-sir1
radiology-dissemination

Create traceable posters, conference abstracts, summaries and media; not papers, decks or figures.

Overview

Publisherhuang-sir1
Repositoryradiology-skills
Skill nameradiology-dissemination
Stars
2K
Forks
20
Bundled files
8
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.

  • 8 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 Dissemination 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-dissemination
  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-dissemination .claude/skills/radiology-dissemination
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Radiology Dissemination 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 Dissemination 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 Dissemination 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 Dissemination

Use this skill to translate a frozen research evidence base into an audience-specific communication product without inflating its scientific maturity. It owns the communication decision, audience action, claim-source trace, release risks and channel adaptation. It does not own the underlying analysis, manuscript, standalone scientific figure, slide deck or institutional release authority.

Non-negotiable boundaries

  • Audience action before format. Name who should understand, discuss, decide or do what after receiving the product. Awareness is not an action unless the user explicitly wants awareness.
  • One evidence base, multiple honest summaries. Every material sentence resolves through a claim-source ledger to a frozen artifact and evidence state. Simpler wording may reduce detail; it may not increase certainty, causality, generalisability, clinical utility or deployment status.
  • Plan is not product. Record PLAN_ONLY, DRAFT_TEXT, CREATE_ARTIFACT or AUDIT. A content plan is not an abstract submission, poster file, published brief, press release or social post. Create or publish an artifact only when explicitly requested and authorized.
  • Current venue and channel rules are live facts. Verify word limits, formats, deadlines, embargoes, disclosures, copyright grants and accessibility requirements from the named current source. Otherwise mark LIVE_RULE_UNVERIFIED and do not claim release readiness.
  • Privacy and rights are independent gates. PHI removal, participant consent/governance, copyright ownership, license scope, attribution and venue reuse permission each require evidence. A citation is not reuse permission; a PowerPoint crop or black box is not de-identification.
  • Public communication is not medical advice. Explain population-level evidence and uncertainty; do not diagnose, recommend an examination or change an individual patient's care.
  • No promotional laundering. Citation counts, statistical significance, regulatory status, preliminary findings or market interest do not by themselves establish patient benefit.

Input passport

Before drafting, record in the dissemination brief:

  • mode, artifact scope, audience, literacy/language needs and intended action;
  • venue/channel, deadline, length/format, review chain, embargo and disclosure rules;
  • project/material version, evidence maturity, Claim IDs and source-owner approvals;
  • population, setting, comparator, denominators, uncertainty, limitations and unresolved findings;
  • image provenance, modality/sequence/view, orientation/laterality, transformations and caption state;
  • PHI/consent/governance, copyright/license/attribution and accessibility state;
  • whether the deliverable is internal, participant-facing, clinical, public, policy or media-facing.

If the evidence base is not frozen, retain SOURCE_LOCK_MISSING; produce only a bounded planning brief and return the missing inputs to the scientific owner.

Route by mode

NeedModeReadPrimary output
Scientific meeting posterconference-postermodes-and-audience-actions.md, rights-privacy-accessibility.mdposter content architecture, claim/image ledger and production brief
Meeting or congress abstractconference-abstractmodes-and-audience-actions.md, then verify the current callstructured abstract draft and compliance gaps
Plain-language research summaryplain-language-summarymodes-and-audience-actions.mdstand-alone question/findings/limits summary
Participant, patient or public explanationpatient-public-explanationboth references aboveactionable explanation with safety and uncertainty boundary
Evidence brief for clinicians or service leadersclinical-evidence-briefmodes-and-audience-actions.mddecision-context evidence brief, not a guideline
Policy briefpolicy-briefmodes-and-audience-actions.mdproblem/options/evidence/implementation brief
Press release or social-media packagepress-socialboth references above and live embargo/channel rulesbounded media copy, caveats, links and release gate
Correct, reissue, withdraw or update an already released derivativederivative-lifecyclemodes-and-audience-actions.md (correction/contact route and released-wording archive), then the same release gatesaffected-derivative ledger, corrected artifact plan and release/withdrawal plan

Use the source registry to choose authoritative guidance and verify every entry marked LIVE_VERIFICATION_REQUIRED. Do not load every reference for a narrow request.

STOP gates

Return an explicit STOP state before external release when any applies:

  • STOP_SOURCE: a material claim lacks a resolvable source, denominator, uncertainty or owner;
  • STOP_CLAIM: wording exceeds the frozen evidence state or hides a negative/discordant result;
  • STOP_PHI: pixels, metadata, filenames, notes, hidden content or linked files may expose PHI;
  • STOP_RIGHTS: ownership, permission, license, attribution or participant image reuse is unresolved;
  • STOP_EMBARGO: journal, meeting, sponsor or institutional publicity timing is unresolved;
  • STOP_ACCESSIBILITY: the intended public channel lacks a reasonable accessible alternative;
  • STOP_AUTHORITY: institutional, sponsor, patient-communications, policy or media approval is absent;
  • STOP_SAFETY: copy could reasonably be read as individual clinical advice or autonomous use.

A STOP blocks release, not safe internal analysis or a clearly labelled repair plan.

Workflow and output contract

  1. Lock the passport, artifact scope and intended audience action.
  2. Build the claim-source ledger; preserve source wording, evidence state, population, effect/accuracy, uncertainty, limitations and permitted reuse.
  3. Choose the mode-specific information order. Keep results, interpretation, recommendation and proposed action distinct.
  4. Adapt language, numbers and images without changing scientific meaning. Explain absolute risk, prevalence and false-positive/false-negative consequences when relevant.
  5. Run scientific, privacy, rights, accessibility, venue and release-authority gates separately.
  6. Return: Scope and audience, Evidence/claim ledger, Draft or production brief, Radiology image ledger, Risk and STOP ledger, Live-rule verification, and Release status.

Release status is one of PLAN_COMPLETE, DRAFT_FOR_SCIENTIFIC_REVIEW, READY_FOR_AUTHORIZED_PRODUCTION, READY_FOR_AUTHORIZED_RELEASE, or STOP. For a derivative already released, the same gates govern correction, reissue, withdrawal or update: preserve the released wording/version archive and a correction/contact route, and record the affected-derivative ledger and release/withdrawal plan before any external action.

Handoffs and non-ownership

  • Slide decks and PPTX, including talks and proposal defences → radiology-paper2ppt.
  • Standalone scientific figures and quantitative plots → radiology-figure; tables → radiology-table; manuscript sections → radiology-writing.
  • Scientific reporting checklist selection → radiology-reporting; evidence synthesis and its conclusions → radiology-systematic-review; corpus retrieval → radiology-search.
  • Disease pathway/reference-standard truth → radiology-clinical-domain; image measurement and acquisition validity → radiology-acquisition-qc; data/consent/governance → radiology-data / radiology-ethics.
  • Final press, policy, patient-facing or institutional release remains with the authorized human communications, clinical, legal, sponsor or policy owner. This skill cannot submit or publish.

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 Dissemination AI skill do?

Create traceable posters, conference abstracts, summaries and media; not papers, decks or figures.

Why use Radiology Dissemination on TypingMind?

Because you install it once and use it with any model. Radiology Dissemination 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 Dissemination 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-dissemination. 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 Dissemination?

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 Dissemination?

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

Is the Radiology Dissemination 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 👇