- Home
- Skills
- Legal & Compliance
- Medical & Pharma AI Compliance Gate
Works with the AI Agents you already use
Medical & Pharma AI Compliance Gate
Audit AI-assisted medical and pharma content for compliance-readiness before it enters formal MLR review or journal submission. It checks claim substantiation and on-label scope, reference integrity (the acute AI risk: fabricated or misrepresented citations), fair balance and safety, AI-use disclosure, ICMJE authorship and GPP, COI and funding, data integrity and patient privacy, and adverse-event flags — then returns a PASS / REVISE / BLOCK verdict with the must-fix list. A readiness pre-check built for the regulated reality of medical communications — not a replacement for formal review.
$29
Medical & Pharma AI Compliance Gate
Example session with this skill installed
"Check this AI-drafted congress abstract before it goes to MLR."
- Read your context and instructions
- Compiled the medical & pharma
A BLOCK verdict: the "significantly outperformed" wording exceeds what a single-arm result supports (soften to the data); two citations verify but the third can't be confirmed and may be fabricated (verify against the primary source before use); AI assistance and medical-writing support aren't disclosed (add per GPP/ICMJE). A prioritized must-fix list, ending "BLOCK until the citation is verified and the claim is on-label" — with the reminder that this is a pre-check, not formal MLR sign-off.
Connects securely to your tools. The creator never sees your data.
About this skill
This catches the issues that get medical content rejected at MLR or by a journal — before it goes to formal review — so AI-assisted drafts don't bounce or ship something unsupportable.
It is a readiness pre-check (not a replacement for formal MLR, qualified medical/regulatory review, or human accountability) and it defers to your applicable codes and SOPs (FDA/OPDP, ABPI, EMA, IFPMA, ICMJE, GPP 2022).
It checks:
- Claim substantiation & on-label scope — nothing stronger than its evidence, nothing off-label
- Reference integrity — the acute AI risk: fabricated citations, or real ones that don't actually support the claim (verified or flagged for primary-source check, never passed blind)
- Fair balance & safety information
- AI-use disclosure & human accountability (AI is never an author)
- ICMJE authorship & GPP 2022 publication practice — no ghost/guest authorship, writing support disclosed
- COI & funding disclosure
- Data integrity & patient privacy (no fabricated data, no PHI)
- Adverse-event flags routed to pharmacovigilance
- Permissions and promotional-vs-non-promotional classification
You get a PASS / REVISE / BLOCK verdict with the must-fix list — what a reviewer would catch, caught early.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Legal & Compliance.
A readiness pre-check only — not legal, regulatory, or medical advice, and not a substitute for MLR, qualified medical/regulatory review, or human accountability. It can't independently verify a citation's content without access to the source, so it flags what to verify. Codes and SOPs vary by region and company and change; defer to them.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
2 uses
Times used to date
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 months ago
Permissions
No special permissions declared or detected