Back to Skills

conduct-gxp-audit

pjt222
Updated 2 days ago
4 views
17
2
17
View on GitHub
Metadata

About

This Claude Skill automates GxP compliance audits for computerized systems, handling the full audit lifecycle from planning to follow-up. It classifies findings, generates CAPAs, and creates reports for internal, supplier, or for-cause audits. Developers can use it for pre-inspection readiness and compliance reviews of validated systems.

Quick Install

Claude Code

Recommended
Primary
npx skills add pjt222/agent-almanac -a claude-code
Plugin CommandAlternative
/plugin add https://github.com/pjt222/agent-almanac
Git CloneAlternative
git clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/conduct-gxp-audit

Copy and paste this command in Claude Code to install this skill

Documentation

Conduct GxP Audit

Plan + execute GxP audit of computerized systems, data integrity practices, or regulated procs.

Use When

  • Scheduled internal audit of validated computerized system
  • Supplier/vendor qualification audit for GxP-relevant software
  • Pre-inspection readiness assessment before regulatory audit
  • For-cause audit triggered by deviation, complaint, or data integrity concern
  • Periodic review of validated system's compliance posture

In

  • Required: Audit scope (system, proc, or site to audit)
  • Required: Applicable regs (21 CFR Part 11, EU Annex 11, GMP, GLP, GCP)
  • Required: Prev audit reports + open CAPA items
  • Optional: System valid. docs (URS, VP, IQ/OQ/PQ, traceability matrix)
  • Optional: SOPs, training records, change control logs
  • Optional: Specific risk areas / concerns triggering audit

Do

Step 1: Develop Audit Plan

# Audit Plan
## Document ID: AP-[SYS]-[YYYY]-[NNN]

### 1. Objective
[State the purpose: scheduled, for-cause, supplier qualification, pre-inspection]

### 2. Scope
- **System/Process**: [Name and version]
- **Regulations**: [21 CFR Part 11, EU Annex 11, ICH Q7, etc.]
- **Period**: [Date range of records under review]
- **Exclusions**: [Any areas explicitly out of scope]

### 3. Audit Criteria
| Area | Regulatory Reference | Key Requirements |
|------|---------------------|------------------|
| Electronic records | 21 CFR 11.10 | Controls for closed systems |
| Audit trail | 21 CFR 11.10(e) | Secure, computer-generated, time-stamped |
| Electronic signatures | 21 CFR 11.50 | Manifestation, legally binding |
| Access controls | EU Annex 11, §12 | Role-based, documented |
| Data integrity | MHRA guidance | ALCOA+ principles |
| Change control | ICH Q10 | Documented, assessed, approved |

### 4. Schedule
| Date | Time | Activity | Participants |
|------|------|----------|-------------|
| Day 1 AM | 09:00 | Opening meeting | All |
| Day 1 AM | 10:00 | Document review | Auditor + QA |
| Day 1 PM | 13:00 | System walkthrough | Auditor + IT + System Owner |
| Day 2 AM | 09:00 | Interviews + evidence collection | Auditor + Users |
| Day 2 PM | 14:00 | Finding consolidation | Auditor |
| Day 2 PM | 16:00 | Closing meeting | All |

### 5. Audit Team
| Role | Name | Responsibility |
|------|------|---------------|
| Lead Auditor | [Name] | Plan, execute, report |
| Subject Matter Expert | [Name] | Technical assessment |
| Auditee Representative | [Name] | Facilitate access and information |

Audit plan approved by QA mgmt + communicated to auditee ≥ 2 weeks before audit. If err: Reschedule if auditee can't provide req'd docs or personnel.

Step 2: Conduct Opening Meeting

Agenda:

  1. Introduce audit team + roles
  2. Confirm scope, schedule, logistics
  3. Explain finding classification (critical/major/minor)
  4. Confirm confidentiality
  5. ID auditee escorts + doc custodians
  6. Address questions

Opening meeting doc'd w/ attendance record. If err: Key personnel unavail → reschedule affected audit activities.

Step 3: Collect + Review Evidence

Review docs + records vs. audit criteria:

3a. Validation Documentation Review

  • URS exists + approved
  • Valid. plan matches system category + risk
  • IQ/OQ/PQ protocols executed w/ results doc'd
  • Traceability matrix links req's to test results
  • Deviations doc'd + resolved
  • Valid. summary report approved

3b. Operational Controls Review

  • SOPs current + approved
  • Training records show competence all users
  • Change control records complete (req, assessment, approval, valid.)
  • Incident/deviation reports handled per SOP
  • Periodic review conducted on schedule

3c. Data Integrity Assessment

  • Audit trail enabled + not user-modifiable
  • Electronic sigs meet reg req's
  • Backup + recovery docs'd + tested
  • Access controls enforce role-based perms
  • Data: attributable, legible, contemporaneous, original, accurate (ALCOA+)

3d. System Configuration Review

  • Prod config matches validated state
  • User accounts reviewed — no shared accounts, inactive disabled
  • System clocks sync'd + accurate
  • Security patches applied per approved change control

Evidence collected as screenshots, doc copies, interview notes w/ timestamps. If err: Can't verify → record "unable to verify" as observation + reason.

Step 4: Classify Findings

Classify each finding by severity:

ClassificationDefinitionResponse Required
CriticalDirect impact on product quality, patient safety, or data integrity. Systematic failure of a key control.Immediate containment + CAPA within 15 business days
MajorSignificant departure from GxP requirements. Potential to impact data integrity if uncorrected.CAPA within 30 business days
MinorIsolated deviation from procedure. No direct impact on data integrity or product quality.Correction within 60 business days
ObservationOpportunity for improvement. Not a regulatory requirement.Optional — tracked for trend analysis

Doc each finding:

## Finding F-[NNN]
**Classification:** [Critical / Major / Minor / Observation]
**Area:** [Audit trail / Access control / Change control / etc.]
**Reference:** [Regulatory clause, e.g., 21 CFR 11.10(e)]

**Observation:**
[Objective description of what was found]

**Evidence:**
[Document ID, screenshot reference, interview notes]

**Regulatory Expectation:**
[What the regulation requires]

**Risk:**
[Impact on data integrity, product quality, or patient safety]

Every finding has classification, evidence, reg ref. If err: Classification disputed → escalate to audit program manager for adjudication.

Step 5: Conduct Closing Meeting

Agenda:

  1. Present findings summary (no new findings should be raised)
  2. Review finding classifications
  3. Discuss prelim CAPA expectations + timelines
  4. Confirm next steps + report timeline
  5. Acknowledge auditee cooperation

Closing meeting doc'd w/ attendance. Auditee acknowledges findings (acknowledgement ≠ agreement). If err: Auditee disputes finding → doc disagreement + escalate per SOP.

Step 6: Write Audit Report

# Audit Report
## Document ID: AR-[SYS]-[YYYY]-[NNN]

### 1. Executive Summary
An audit of [System/Process] was conducted on [dates] against [regulations].
[N] findings were identified: [n] critical, [n] major, [n] minor, [n] observations.

### 2. Scope and Methodology
[Summarize audit plan scope, criteria, and methods used]

### 3. Findings Summary
| Finding ID | Classification | Area | Brief Description |
|-----------|---------------|------|-------------------|
| F-001 | Major | Audit trail | Audit trail disabled for batch record module |
| F-002 | Minor | Training | Two users missing annual GxP training |
| F-003 | Observation | Documentation | SOP formatting inconsistencies |

### 4. Detailed Findings
[Include full finding details from Step 4 for each finding]

### 5. Positive Observations
[Document areas of good practice observed during the audit]

### 6. Conclusion
The overall compliance status is assessed as [Satisfactory / Needs Improvement / Unsatisfactory].

### 7. Distribution
| Recipient | Role |
|-----------|------|
| [Name] | System Owner |
| [Name] | QA Director |
| [Name] | IT Manager |

### Approval
| Role | Name | Signature | Date |
|------|------|-----------|------|
| Lead Auditor | | | |
| QA Director | | | |

Report issued within 15 business days of closing meeting. If err: Delayed beyond 15 days → notify stakeholders + doc reason.

Step 7: Track CAPA + Verify Effectiveness

Each finding requiring CAPA:

## CAPA Tracking
| Finding ID | CAPA ID | Root Cause | Corrective Action | Due Date | Status | Effectiveness Check |
|-----------|---------|------------|-------------------|----------|--------|-------------------|
| F-001 | CAPA-2025-042 | Configuration oversight during upgrade | Enable audit trail, verify all modules | 2025-04-15 | Open | Scheduled 2025-07-15 |
| F-002 | CAPA-2025-043 | Training matrix not updated | Complete training, update tracking | 2025-05-01 | Open | Scheduled 2025-08-01 |

CAPAs assigned, tracked, effectiveness verified per defined timeline. If err: Unresolved CAPAs escalate to QA mgmt + flag in next audit cycle.

Check

  • Audit plan approved + communicated pre-audit
  • Opening + closing meetings doc'd w/ attendance
  • Evidence collected w/ timestamps + source refs
  • Every finding has classification, evidence, reg ref
  • Audit report issued within 15 business days
  • CAPAs assigned w/ due dates for all critical + major findings
  • Prev audit CAPAs verified for closure effectiveness

Traps

  • Scope creep: Expanding scope during exec w/o formal agreement → incomplete coverage + disputes.
  • Opinion-based findings: Findings must ref specific reg req's, not personal preferences.
  • Adversarial tone: Audits = collaborative quality improvement, not interrogations.
  • Ignore positives: Reporting only findings w/o acknowledging good practices undermines trust.
  • No effectiveness check: Closing CAPA w/o verifying fix actually works = recurring regulatory citation.

  • perform-csv-assessment — full CSV lifecycle assessment (URS through validation summary)
  • setup-gxp-r-project — project structure for validated R environments
  • implement-audit-trail — audit trail impl for electronic records
  • write-validation-documentation — IQ/OQ/PQ protocol + report writing
  • security-audit-codebase — security-focused code audit (complementary perspective)

GitHub Repository

pjt222/agent-almanac
Path: i18n/caveman-ultra/skills/conduct-gxp-audit
0
agentsagentskillsai-assisted-developmentclaude-codeskillsteams

Related Skills

content-collections

Meta

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

View skill

polymarket

Meta

This skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.

View skill

creating-opencode-plugins

Meta

This skill helps developers create OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It provides the plugin structure, event API specifications, and implementation patterns for JavaScript/TypeScript modules. Use it when you need to intercept, monitor, or extend the OpenCode AI assistant's lifecycle with custom event-driven logic.

View skill

sglang

Meta

SGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.

View skill