Lab Result Deviation Evidence Packet
Organize laboratory-result deviation records into a traceable evidence packet with Claude.
Secure checkout via Stripe
Works with the AI tools you already use
See it in action
You say
Organize a deviation packet for Assay L1 (98-102%). Original result L2 was 94.1%. Audit trail L3 shows reintegration. Retest L4 passed at 99.8%. Analyst suspects a pipette error.
Your agent does
1. Packet decision
Decision: PARTIAL LABORATORY-RESULT DEVIATION EVIDENCE PACKET AVAILABLE.
7. Gaps and conflicts
G1 — Assignable cause: Pipette hypothesis lacks supporting evidence. G2 — Audit trail: Reintegration needs reconstruction and rationale. G4 — Retest governance: Authorization missing.
What you get
About this skill
The problem
Laboratory deviation records are often scattered across disparate instrument logs, worksheets, and audit trails. Manually organizing this evidence into a traceable investigation packet is time-consuming and prone to overlooking critical data integrity gaps.
What it does
- Builds a structured source register from specifications, raw instrument data, and analyst notes.
- Maps sample identities across chain-of-custody, receipt, and preparation records to identify discrepancies.
- Separates original observations from recalculated results, retests, and resamples to preserve data integrity.
- Chronologically links analytical controls, system-suitability results, and equipment alarms to specific results.
- Flags gaps such as unsupported hypotheses, missing audit trails, and unauthorized retests for technical review.
Why this beats prompting it yourself
This skill enforces strict regulatory-style boundaries, ensuring that hypotheses are never conflated with confirmed causes. It maintains a neutral stance that prevents the agent from making unauthorized validity decisions or disposition claims that could compromise a quality investigation.
Use cases
- Preparing a source-indexed packet for internal quality assurance or technical review.
- Reconstructing a data trail when audit logs show reintegration or reprocessing.
- Organizing evidence when a laboratory hypothesis is presented as a confirmed root cause.
- Mapping batch impact across shared instruments, materials, and analysts.
Known limitations
Requires all records to be supplied via file or Read tool. Cannot determine result validity, assign root cause, or assess public health risks.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean today
- 30-day refund guarantee
- One-time purchase, yours forever
- Secure checkout via Stripe
Creator
109 skills on Agensi
Frequently Asked Questions
Popular in AI Agents & LLM Ops
agentic-workflow
A risk-aware, evidence-based engineering lifecycle protocol for robust agentic task execution and safety.
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.

prompt-engineer
Professional prompt engineering patterns for building robust, secure, and production-ready LLM applications.
codex-grade-coding
Turn your AI agent into a senior engineer with strict task classification and verification-driven coding protocols.