
pfmea
Generate AIAG-VDA compliant Process FMEAs with proper Severity/Occurrence/Detection ratings, RPN calculations, and countermeasure recommendations. Covers MNMUK departments (Machine Shop, Damper, LVA, FML). USE WHEN user says 'PFMEA', 'FMEA', 'failure mode', 'risk analysis', 'RPN', 'severity occurrence detection', or 'process risk assessment'. Integrates with AutomotiveManufacturing, ControlPlan, and A3criticalthinking skills.
- Installs
- 42
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/robdtaylor/personal-ai-infrastructure --skill pfmea- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads pfmea automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Process FMEA (PFMEA)
When to Activate This Skill
- "Create a PFMEA for [process]"
- "What are the failure modes for [operation]?"
- "Calculate RPN for [risk scenario]"
- "Rate severity/occurrence/detection for [failure]"
- "Identify process risks"
- "FMEA analysis for [part/process]"
CRITICAL: Always Generate Content Directly
Every response to a PFMEA request MUST contain the actual PFMEA analysis inline — failure modes, S/O/D ratings, RPN/AP, controls, and actions written out in full. Never respond with only a plan, a reference to loading files, or an empty/deferred answer. Supplementary file reads (CLAUDE.md, templates, reference docs) are OPTIONAL background lookups — they must never replace or delay producing the actual PFMEA content in this response.
AIAG-VDA 7-Step Methodology
Step 1: Planning and Preparation
- Define scope and boundaries
- Identify team members (cross-functional)
- Gather documentation (process flow, control plan, drawings)
- Review lessons learned from similar processes
Step 2: Structure Analysis
- Define process steps from process flow diagram
- Create process tree (System > Sub-system > Process Element)
- Identify interfaces between steps
- Link to product characteristics
Step 3: Function Analysis
- Define function of each process step
- Identify product/process requirements
- Link to customer/engineering specifications
- Document special characteristics (CC/SC)
Step 4: Failure Analysis
- Identify failure modes (how can step fail to perform function?)
- Determine failure effects (consequences to customer/next operation)
- Identify failure causes (why would failure mode occur?)
- Chain: Cause → Failure Mode → Effect
Step 5: Risk Analysis
- Rate Severity (S) of effects: 1-10
- Rate Occurrence (O) of causes: 1-10
- Rate Detection (D) of controls: 1-10
- Calculate Action Priority (AP) or RPN
Step 6: Optimization
- Prioritize high-risk items
- Develop countermeasures (hierarchy: Eliminate > Substitute > Engineer > Admin > Detect)
- Assign responsibility and target dates
- Re-rate after countermeasures
Step 7: Results Documentation
- Document all analysis
- Track countermeasure completion
- Update Control Plan linkage
- Archive for lessons learned
Rating Scales (MNMUK Standard)
Severity (S) - Effect on Customer/Process
| Rating | Criteria | MNMUK Examples |
|---|---|---|
| 10 | Affects safety without warning | Brake component failure, no containment possible |
| 9 | Affects safety with warning | Safety critical dimension OOS, detectable at assembly |
| 8 | Product inoperable, 100% scrap | Part cannot be reworked, total loss |
| 7 | Product operable but degraded, customer dissatisfied | Performance below spec, customer complaint |
| 6 | Product operable, comfort/convenience affected | Cosmetic defect, minor fit issue |
| 5 | 50% of product may need rework | Significant rework required |
| 4 | Product requires sorting/rework | Sorting operation needed |
| 3 | Minor rework at station | In-station repair possible |
| 2 | Slight inconvenience | Minor adjustment |
| 1 | No effect | No discernible impact |
Occurrence (O) - Likelihood of Cause
| Rating | Failure Rate | Cpk Equivalent | MNMUK Examples |
|---|---|---|---|
| 10 | Very high: ≥100/1000 | <0.33 | New process, no controls |
| 9 | High: 50/1000 | ≥0.33 | Known problem process |
| 8 | High: 20/1000 | ≥0.51 | Similar process had failures |
| 7 | Moderately high: 10/1000 | ≥0.67 | Occasional failures observed |
| 6 | Moderate: 2/1000 | ≥0.83 | Infrequent failures |
| 5 | Moderately low: 0.5/1000 | ≥1.00 | Controlled process, some failures |
| 4 | Low: 0.1/1000 | ≥1.17 | Well-controlled process |
| 3 | Very low: 0.01/1000 | ≥1.33 | Capable and controlled |
| 2 | Remote: 0.001/1000 | ≥1.50 | Proven design and controls |
| 1 | Nearly impossible: ≤0.001/1000 | ≥1.67 | Failure eliminated by design |
Detection (D) - Ability to Detect Before Customer
| Rating | Detection Capability | MNMUK Examples |
|---|---|---|
| 10 | No detection possible | No inspection, no opportunity to detect |
| 9 | Unlikely to detect | Random sampling only, infrequent |
| 8 | Low: Visual inspection by operator | 100% visual check, variable attention |
| 7 | Very low: Double visual inspection | Two operators check |
| 6 | Low: Charting/SPC | Control charts, trend monitoring |
| 5 | Moderate: Attribute gaging | Go/No-go gaging |
| 4 | Moderately high: Variable gaging | Measurement with limit checking |
| 3 | High: Automated in-process test | Automatic measurement, alarm |
| 2 | Very high: Error-proofing | Poka-yoke prevents defect production |
| 1 | Almost certain: Error-proofing prevents cause | Design makes failure impossible |
Action Priority (AIAG-VDA Approach)
Instead of or in addition to RPN, use Action Priority:
| Priority | Criteria | Action Required |
|---|---|---|
| HIGH | S=9-10 (any O, D) OR S=7-8 with O≥4 AND D≥4 | Immediate action required |
| MEDIUM | S=5-8 with O≥4 OR D≥4 | Action recommended |
| LOW | All others | Monitor and document |
RPN Thresholds (MNMUK Standard)
| RPN Range | Priority | Required Action |
|---|---|---|
| ≥120 | Critical | Immediate countermeasure, cannot ship without action |
| 80-119 | High | Countermeasure required before PPAP |
| 40-79 | Medium | Countermeasure recommended |
| <40 | Low | Monitor, no immediate action |
Note: Any Severity ≥8 requires action regardless of RPN.
Countermeasure Hierarchy
When addressing failure modes, apply controls in this priority order:
- Eliminate - Design out the failure mode entirely
- Substitute - Replace with less hazardous process/material
- Engineer - Install physical safeguards, poka-yoke
- Admin - Procedures, training, work instructions
- Detect - Inspection, testing, monitoring
Special Characteristics
Critical Characteristics (CC)
- Safety or regulatory impact
- Marked with shield symbol or (CC)
- Requires enhanced controls
- Mandatory documentation
Significant Characteristics (SC)
- Fit, function, or durability impact
- Marked with diamond or (SC)
- Requires appropriate controls
- SPC typically required
Output Format Requirements
CRITICAL: Every PFMEA response MUST be complete. Never truncate or cut off mid-entry. Every failure mode listed MUST have:
- All causes fully documented
- S/O/D ratings for EVERY cause row
- RPN calculated for EVERY row
- Current controls listed
- Recommended actions specified
- After-action ratings included
If the full PFMEA would be very long, reduce the NUMBER of failure modes covered, but each one included MUST be 100% complete. Do not start a failure mode entry you cannot finish.
Output Format
When generating PFMEA content:
# PFMEA: [Part/Process Name]
**Part Number**: [P/N]
**Process**: [Description]
**FMEA Number**: PFMEA-[DEPT]-[SEQ]
**Revision**: [Rev] | **Date**: [YYYY-MM-DD]
**Team**: [Names/Roles]
## Process Step: [Step Name]
### Failure Mode 1: [Description]
**Function**: [What the step should do]
**Effect**: [What happens if it fails]
**Cause**: [Why it would fail]
| S | O | D | RPN | AP |
|---|---|---|-----|-----|
| X | X | X | XXX | H/M/L |
**Current Controls**:
- Prevention: [Current prevention measures]
- Detection: [Current detection measures]
**Recommended Actions**:
- [ ] [Action description] - Owner: [Name] - Due: [Date]
**After Action**:
| S | O | D | RPN | AP |
|---|---|---|-----|-----|
| X | X | X | XXX | H/M/L |
Department-Specific Guidance
Machine Shop
- Common failure modes: Dimensional OOS, surface finish, tool wear
- Focus on: Fixturing, program parameters, tool life management
- Key controls: First piece inspection, SPC, gage R&R
Damper Assembly
- Common failure modes: Leak, incorrect torque, missing component
- Focus on: Seal integrity, fastener torque, component presence
- Key controls: Leak test, torque verification, poka-yoke
LVA (Low Volume Assembly)
- Common failure modes: Wrong component, incorrect orientation, damage
- Focus on: Part identification, assembly sequence, handling
- Key controls: Visual verification, traveler documentation
FML (Final Manufacturing Line)
- Common failure modes: Test failure, labeling error, packaging damage
- Focus on: Final test parameters, traceability, packaging
- Key controls: Automated test, barcode verification, packaging audit
Integration with Related Skills
ControlPlan
PFMEA feeds directly into Control Plan:
- High S/O items require enhanced inspection
- Detection controls become Control Plan methods
- Special characteristics flow to Control Plan
Load: read ~/.claude/skills/Controlplan/SKILL.md
AutomotiveManufacturing
Work instructions should reflect PFMEA findings:
- High-risk steps highlighted
- Operator controls documented
- Quality checkpoints specified
Load: read ~/.claude/skills/Automotivemanufacturing/SKILL.md
A3criticalthinking
When PFMEA reveals issues:
- Use 5 Whys for root cause analysis
- Fishbone diagram for cause identification
- A3 format for countermeasure planning
Load: read ~/.claude/skills/A3criticalthinking/SKILL.md
Workflow Routing
| Trigger | What to do |
|---|---|
| "create a PFMEA for [process]" / "FMEA analysis for [part/process]" | Run the full AIAG-VDA 7-Step Methodology; emit the Output Format markdown with one Failure Mode block per row, S/O/D + RPN + AP for every cause, current controls, recommended actions, and after-action re-rating |
| "what are the failure modes for [operation]?" | Use Failure Analysis (Step 4) plus reference/common-failure-modes.md for the relevant department; chain Cause → Failure Mode → Effect for each candidate |
| "rate severity/occurrence/detection for [failure]" / "calculate RPN for [scenario]" | Apply the Rating Scales tables (S/O/D) and compute RPN + Action Priority per the Action Priority and RPN Thresholds tables; flag S≥8 as requiring action regardless of RPN |
| "identify process risks" / dept-specific PFMEA (Machine Shop, Damper, LVA, FML) | Apply the matching Department-Specific Guidance block for common failure modes, focus areas, and key controls before running Steps 1-7 |
| "what countermeasure / how do we fix this failure mode?" | Apply the Countermeasure Hierarchy (Eliminate > Substitute > Engineer > Admin > Detect) — never default to an added inspection when a higher-tier fix is feasible |
| "link PFMEA to control plan" / "special characteristics" | Use Special Characteristics (CC/SC) rules, then hand off to the ControlPlan skill per Integration with Related Skills |
| "PFMEA calibration session" / "team composition" / "review triggers" / advanced/edge-case PFMEA questions | read ~/.claude/skills/Pfmea/CLAUDE.md for team composition, rating calibration, control effectiveness matrix, and update triggers |
Examples
Example 1 — Full PFMEA for a machining operation
User: "Create a PFMEA for the damper rod OD turning operation on the CITIZEN Swiss lathe."
Output: AIAG-VDA 7-step PFMEA in the skill's Output Format — process step "Turn Rod OD to spec" with failure modes (oversize/undersize OD, poor surface finish, chatter marks), each with Function/Effect/Cause, S/O/D ratings, RPN, Action Priority, current prevention/detection controls, recommended actions with owner/due date, and after-action re-rating. Machine Shop department guidance applied (fixturing, tool wear, first-piece inspection per Department-Specific Guidance).
Example 2 — Rating a single failure mode
User: "Rate severity, occurrence, and detection for a missed damper gas charge — dampers ship without gas."
Output: S=8 (product inoperable) or S=9 if the application is safety-critical, per the Severity table. O rated against current process controls (e.g., O=6 for a manual charge station with no verification). D rated against current detection (e.g., D=7 if only an end-of-line function test is relied on). RPN calculated, Action Priority flagged HIGH (S≥8), and the Countermeasure Hierarchy applied to recommend an Engineer-tier fix (weight-check or pressure sensor poka-yoke) over adding another visual inspection.
Example 3 — Escalating a PFMEA finding into Control Plan and 8D
User: "Our LVA PFMEA shows wrong-component assembly at RPN 144. What next?"
Output: Flags RPN ≥120 as Critical per RPN Thresholds — immediate countermeasure required, cannot ship without action. Recommends an Eliminate/Engineer-tier fix (kitting with poka-yoke tray, component-presence sensor) over an Admin-tier fix (visual check procedure). Links the finding to the ControlPlan skill to convert the new detection control into a Control Plan line, and to A3criticalthinking for 5-Whys root cause analysis if the wrong-component issue has already occurred in production.
Supplementary Resources
For detailed guidance:
read ~/.claude/skills/Pfmea/CLAUDE.md
For templates:
ls ~/.claude/skills/Pfmea/templates/
For rating scales:
read ~/.claude/skills/Pfmea/reference/rating-scales.md
For common failure modes:
read ~/.claude/skills/Pfmea/reference/common-failure-modes.md
FAQ
What does the pfmea skill do?
Generate AIAG-VDA compliant Process FMEAs with proper Severity/Occurrence/Detection ratings, RPN calculations, and countermeasure recommendations. Covers MNMUK departments (Machine Shop, Damper, LVA, FML). USE WHEN user says 'PFMEA', 'FMEA', 'failure mode', 'risk analysis', 'RPN', 'severity occurrence detection', or 'process risk assessment'. Integrates with AutomotiveManufacturing, ControlPlan, and A3criticalthinking skills.
How do I install pfmea?
Run npx skills add https://github.com/robdtaylor/personal-ai-infrastructure --skill pfmea in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/pfmea/ (personal) or .claude/skills/pfmea/ (project).
Which AI agents can use pfmea?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is pfmea safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains pfmea?
It is published by robdtaylor in robdtaylor/personal-ai-infrastructure. It has 42 recorded installs.
More from robdtaylor/personal-ai-infrastructure
businessstrategy
robdtaylor/personal-ai-infrastructure
MBA-trained business strategist with full commercial awareness. USE WHEN user says 'business plan', 'financial analysis', 'P&L', 'cash flow', 'valuation', 'market analysis', 'competitive analysis', 'SWOT', 'business model', 'unit economics', 'fundraising', 'pitch deck', or needs strategic business guidance.
structuralfea
robdtaylor/personal-ai-infrastructure
Open source FEA structural analysis for damper and mechanical components. Generates CalculiX input files, guides mesh setup, provides material databases, interprets results. USE WHEN user says 'FEA', 'structural analysis', 'stress analysis', 'buckling', 'modal analysis', 'finite element', 'CalculiX', 'mesh', or needs to validate damper component designs.
shippinglogistics
robdtaylor/personal-ai-infrastructure
UK, US, and Canadian shipping, logistics, customs, duties, and tariff expert with automotive commodity code expertise. Covers import/export documentation, HS/HTS codes, rules of origin, FTAs, and landed cost calculations. USE WHEN user says 'shipping', 'customs', 'tariff', 'duty', 'import', 'export', 'HS code', 'HTS code', 'commodity code', 'landed cost', 'incoterms', 'customs broker', 'freight', 'logistics', 'rules of origin', 'CUSMA', 'USMCA', 'TCA', or needs help with international trade compliance.
supplychain
robdtaylor/personal-ai-infrastructure
Executive-level supply chain expertise for automotive manufacturing. Strategic purchasing, materials management, supplier development, and cost optimization aligned with IATF 16949 requirements. USE WHEN user says 'supply chain', 'purchasing', 'procurement', 'supplier', 'materials management', 'inventory', 'sourcing', 'vendor', 'BOM cost', 'PPV', 'should cost', 'make vs buy', 'RFQ', 'category management', or needs strategic guidance on automotive supply chain decisions. Integrates with AutomotiveManufacturing, A3CriticalThinking, and HoshinKanri skills.
automotivemanufacturing
robdtaylor/personal-ai-infrastructure
Expert guidance for writing automotive manufacturing business processes, work instructions, and standard operating procedures. Follows IATF 16949, ISO 9001, and APQP/PPAP standards. Covers assembly, machining, quality/inspection, and material handling. USE WHEN user says 'write work instruction', 'create business process', 'automotive SOP', 'manufacturing procedure', 'APQP documentation', 'process flow', or 'quality procedure'. Integrates with A3CriticalThinking for problem solving and SupplyChain for supplier requirements.
quoteestimator
robdtaylor/personal-ai-infrastructure
Rough cycle time and cost estimation for CNC machined parts. Uses MNMUK plant capabilities and standard estimating factors. USE WHEN user says 'quote', 'estimate', 'cycle time', 'how long', 'cost estimate', 'pricing', 'how much to make', or describes a part needing a rough quote.
Popular devops & cloud skills
microsoft-foundry
microsoft/azure-skills
Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, managed harness agent create, GitHub Copilot harness agent, create agent, update agent, add tool to agent, invoke agent, agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure
azure-diagnostics
microsoft/azure-skills
Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deployment failure, troubleshoot container apps, container app 503 or target port mismatch, troubleshoot functions, function telemetry missing or stopped after a config/connection-string change, troubleshoot AKS, VM RDP, Linux SSH, VM black screen, can't connect to VM, reset VM password, NSG or firewall blocking, kubectl cannot connect, kube-system/CoreDNS failures, pod pending, crashloop, node not ready, upgrade failures, analyze logs, KQL, insights, image pull failures, cold start issues, health probe failures, resource health, root cause of errors, troubleshoot event hubs, troubleshoot service bus, messaging SDK error, AMQP connection failure, message lock lost, lock renewal during long-running processing, service bus dead letter.
azure-prepare
microsoft/azure-skills
Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wants to use azd as the deployment tool, or the project already has an azure.yaml file. DO NOT USE FOR: non-azd deployments, Python App Service code-only deploys (use python-appservice-deploy), or cross-cloud migration (use azure-cloud-migrate). WHEN: prepare app for azd, create azure.yaml, set up azd infrastructure, modernize app for Azure with azd, deploy with azd, function app, timer trigger, service bus trigger, event-driven function, managed identity, generate Bicep, generate Terraform, create and deploy to Azure.
azure-ai
microsoft/azure-skills
Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.
azure-deploy
microsoft/azure-skills
Execute Azure deployments for ALREADY-PREPARED applications that have existing .azure/deployment-plan.md and infrastructure files. DO NOT use this skill when the user asks to CREATE a new application — use azure-prepare instead. This skill runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery. Requires .azure/deployment-plan.md from azure-prepare and validated status from azure-validate. WHEN: "run azd up", "run azd deploy", "execute deployment", "push to production", "push to cloud", "go live", "ship it", "bicep deploy", "terraform apply", "publish to Azure", "launch on Azure". DO NOT USE WHEN: "create and deploy", "build and deploy", "create a new app", "set up infrastructure", "create and deploy to Azure using Terraform" — use azure-prepare for these.
azure-validate
microsoft/azure-skills
Pre-deployment validation for Azure readiness. Run deep checks on configuration, infrastructure (Bicep or Terraform), RBAC role assignments, managed identity permissions, and prerequisites before deploying. WHEN: validate my app, check deployment readiness, run preflight checks, verify configuration, check if ready to deploy, validate azure.yaml, validate Bicep, test before deploying, troubleshoot deployment errors, validate Azure Functions, validate function app, validate serverless deployment, verify RBAC roles, check role assignments, review managed identity permissions, what-if analysis, validate Container Apps deployment.