Cdisc Submission Compliance logo

Cdisc Submission Compliance

Organization
Amazon-Quick
cdisc-submission-compliance

Apply Clinical Data Interchange Standards Consortium (CDISC) decision frameworks for regulatory submission compliance across the Study Data Tabulation Model (SDTM), the Analysis Data Model (ADaM), define.xml, and controlled terminology. Use when asked to 'check SDTM compliance', 'map data to an SDTM domain', 'decide what goes in SUPPQUAL', 'plan define.xml value-level metadata', 'triage Pinnacle 21 findings', 'prioritize data queries', 'compare FDA and PMDA submission requirements', or any CDISC submission data standards question

Overview

PublisherAmazon-Quick
RepositoryAmazon-Quick-official-catalog
Skill namecdisc-submission-compliance
Stars
50
Forks
4
Bundled files
8
LicenseMIT-0
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 Amazon-Quick on GitHub. Read the source before you install it.

Installation

Install the Cdisc Submission Compliance 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/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/healthcare/cdisc-submission-compliance
  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/Amazon-Quick/Amazon-Quick-official-catalog.git /tmp/Amazon-Quick-official-catalog
mkdir -p .claude/skills
cp -r /tmp/Amazon-Quick-official-catalog/skills/healthcare/cdisc-submission-compliance .claude/skills/cdisc-submission-compliance
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cdisc Submission Compliance 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 Cdisc Submission Compliance 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 Cdisc Submission Compliance 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.

Overview

Provides expert reasoning for Clinical Data Interchange Standards Consortium (CDISC) data standards used in regulatory submissions. It answers questions about Study Data Tabulation Model (SDTM) and Analysis Data Model (ADaM) implementation, controlled terminology, define.xml content, Supplemental Qualifiers (SUPPQUAL) decisions, agency submission differences, data query prioritization, and Pinnacle 21 triage. Use it when a data manager, statistical programmer, or standards lead needs a defensible recommendation grounded in a specific criterion, threshold, or rule. The decision frameworks live in reference files that the agent reads on demand and applies as internal reasoning; the response carries only the conclusion and its evidence.

Workflow

<Workflow - Assess CDISC Compliance description="Classify a CDISC submission question, apply the matching decision framework from the reference files, and return a defensible recommendation." tools=[file_read] triggers=["User asks about SDTM or ADaM compliance", "User asks how to map data to an SDTM domain or SUPPQUAL", "User asks about define.xml, controlled terminology, agency requirements, data query priority, or Pinnacle 21 findings"]

  1. [Decide] Is the request within scope per Rule 7? If it concerns pre-clinical data, non-regulatory use, or eCTD assembly mechanics, state that it is out of scope and stop. If in scope, continue.

  2. [Decide] Classify the question and select the reference file(s) to read:

    • SDTM domain selection (tumor, medication, pre-existing conditions, questionnaires): references/domain-mapping.md
    • Whether a field belongs in SUPPQUAL, the parent domain, or a custom domain: references/suppqual.md
    • ADaM rules, define.xml value-level metadata, or minimum SDTM version: references/adam-define.md
    • Agency submission format differences or controlled terminology version policy: references/agency-requirements.md
    • Data query prioritization or Pinnacle 21 finding triage: references/query-and-p21-triage.md
    • Study day calculation or ADaM date imputation: references/date-handling.md
    • Reviewing datasets for compliance gaps or ranking mistakes by severity: references/common-mistakes.md Validate: at least one reference file is selected and it matches the question topic. If fails: ask the user one clarifying question about the data or decision at hand.
  3. [Agent] Read the selected reference file(s) with file_read. Validate: file content loaded and non-empty. If fails: report which file could not be read and answer only from what loaded, noting the gap.

  4. [Decide] If the question requires the target agency and it was not given (per Rule 6), state the assumption you are applying (default to FDA) and note that PMDA or other agencies may differ, then continue.

  5. [Think] Apply the matching framework internally. Walk the decision branch or check the thresholds, then reach a single conclusion and identify the specific criterion, rule ID, threshold, or version that supports it.

  6. [Decide] Is this an escalation case per Rule 8 (ambiguous dual-domain mapping, missing controlled terminology, or agency feedback conflicting with the Implementation Guide)? If yes, give your best reasoned view and name the human decision owner who must confirm.

  7. [Agent] Compose the response per the Response Format in . Do not paste the reference tables or trees; cite the evidence in prose. Include the Rule 2 disclaimer when the recommendation carries regulatory risk. Validate: the response leads with the recommendation, cites at least one specific standard, criterion, or rule ID, and reproduces no framework verbatim. If fails: rewrite until it does.

</Workflow - Assess CDISC Compliance>

<Template - Response Format>

  • Lead with the direct recommendation or classification in three sentences or fewer.
  • Structure as: recommendation, then justification citing the specific criterion, threshold, rule ID, or version, then caveats.
  • Use a short table for comparisons and bullet points for criteria lists.
  • Omit background the user already knows; they asked the question.
  • Target 200 to 400 words unless the user requests exhaustive detail.
  • Add the Rule 2 disclaimer when the recommendation carries regulatory risk. </Template - Response Format>
  • references/domain-mapping.md: SDTM domain selection for the non-obvious cases (tumor data, medications, pre-existing conditions, questionnaires).
  • references/suppqual.md: SUPPQUAL anti-pattern checklist, red flags, and formatting rules.
  • references/adam-define.md: ADaM rules, define.xml value-level metadata, and minimum SDTM versions by agency.
  • references/agency-requirements.md: FDA versus PMDA submission differences and controlled terminology rules.
  • references/query-and-p21-triage.md: query prioritization by clinical impact and Pinnacle 21 triage with top rules.
  • references/date-handling.md: study day calculation and ADaM date imputation rules.
  • references/common-mistakes.md: severity-ranked common compliance mistakes with corrections.

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 Cdisc Submission Compliance AI skill do?

Apply Clinical Data Interchange Standards Consortium (CDISC) decision frameworks for regulatory submission compliance across the Study Data Tabulation Model (SDTM), the Analysis Data Model (ADaM), define.xml, and controlled terminology. Use when asked to 'check SDTM compliance', 'map data to an SDTM domain', 'decide what goes in SUPPQUAL', 'plan define.xml value-level metadata', 'triage Pinnacle 21 findings', 'prioritize data queries', 'compare FDA and PMDA submission requirements', or any CDISC submission data standards question

Why use Cdisc Submission Compliance on TypingMind?

Because you install it once and use it with any model. Cdisc Submission Compliance 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 Cdisc Submission Compliance in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/healthcare/cdisc-submission-compliance. 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 Cdisc Submission Compliance?

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 Cdisc Submission Compliance?

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

Is the Cdisc Submission Compliance AI skill free?

Yes. It is published on GitHub by Amazon-Quick under the MIT-0 license. 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 👇