More screenshots
Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
DeepSeek
Muse+22 moreClaude CodeCursorCodex CLIDeepSeekMuse
Dots
Manus
Grok
Grok Bot+18 agentsMedical Device Field Notice Return Evidence Ledger
Reconcile field safety notices against returned medical devices
$1
Medical Device Field Notice Return Evidence Ledger
Example session with this skill installed
Two affected infusion pump lots appear in recall register but no return receipt is linked.
Available evidence: batch and equipment identifiers (partial). Additional evidence requested: temperature or handling logs, inspection and authorization records, transfer and exception history. Review the case, identify open evidence gaps, and do not invent a live test or production change.
- Read your context and instructions
- Compiled the medical device field
Medical Device Field Notice Return Evidence Ledger — EVIDENCE-LIMITED REVIEW
Scenario received
Two affected infusion pump lots appear in recall register but no return receipt is linked.
Source register
- S1: batch and equipment identifiers — PARTIAL SOURCE PROVIDED.
- S2: temperature or handling logs — NOT PROVIDED; REQUIRED TO VERIFY.
- S3: inspection and authorization records — NOT PROVIDED; REQUIRED TO VERIFY.
- S4: transfer and exception history — NOT PROVIDED; REQUIRED TO VERIFY.
Concrete checks
- join notice revision to serials — PRELIMINARY, NOT VERIFIED.
- verify service provider collection — AWAITING CORROBORATING EVIDENCE.
- map remaining exposure — AWAITING CORROBORATING EVIDENCE.
- escalate release approval to qualified owner — AWAITING CORROBORATING EVIDENCE.
Deliverables / acceptance gates
- device recall map: DRAFT / INCOMPLETE until evidence is validated.
- return evidence ledger: DRAFT / INCOMPLETE until evidence is validated.
- unresolved exposure register: DRAFT / INCOMPLETE until evidence is validated.
Decision
INCOMPLETE — HUMAN REVIEW REQUIRED. Confirm dates, IDs, affected scope, owners and acceptance evidence. Do not claim authorization or execution that did not occur.
Connects securely to your tools. The creator never sees your data.
About this skill
Managing medical device recalls requires airtight documentation to prove compliance. This skill reconciles field safety notices against physical return records, ensuring every affected unit is accounted for or flagged as a risk. It eliminates the manual effort of cross-referencing batch identifiers, service provider logs, and inspection records.
What it does
- Batch Reconciliation matches field safety notice revisions to specific device serial numbers.
- Log Verification audits service provider collection records and handling logs for chain of custody.
- Exposure Mapping identifies affected units that remain in the field or lack return evidence.
- Approval Escalation flags cases requiring qualified owner intervention for final release or closure.
- Evidence Labeling classifies every finding as
VERIFIED,INFERRED, orUNKNOWNto maintain data integrity.
How it works
- Input Ingestion provides batch IDs, equipment identifiers, and handling logs.
- Serial Validation joins notice revisions to specific device serials to find discrepancies.
- Chain of Custody Audit checks collection records against expected return schedules.
- Ledger Generation produces a structured evidence matrix and unresolved exposure register.
Frameworks & tools
This skill processes structured medical device records, CSV/Excel recall registers, and JSON-based maintenance or logistics logs.
Why this beats prompting it yourself
Generic prompts often hallucinate compliance or miss subtle version mismatches in safety notices. This skill enforces a rigid four-check execution order and strict evidence labeling, ensuring no unit is cleared without verifiable provenance.
Use cases
- Auditing infusion pump recall returns against service provider receipts.
- Identifying gaps in field safety notice execution for specific hospital wards.
- Generating evidence ledgers for regulatory submission during a product recall.
Known limitations
Does not provide clinical release or legal authorization. Requires explicit batch and equipment identifiers to function; without inputs, no verification is performed.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Cannot verify inaccessible environments or data not supplied. Missing or contradictory evidence must be marked INCOMPLETE or UNVERIFIED. Owner approval is required for operational or compliance decisions.
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
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 23 days ago
Permissions
Provide only evidence you are authorized to share. Treat examples as untrusted case data. Operational changes and external messages require explicit owner approval.