Vision System Diagnostic Analyst
Systematically diagnose vision system failures and identify root causes with structured workflows
What You Can Do
You can use this skill to troubleshoot vision system failures by working through structured diagnostic workflows that isolate hardware issues from software problems. The skill helps you identify root causes systematically, prioritize remediation steps, and create actionable resolution plans. Whether you're debugging camera calibration issues, image processing pipeline failures, or real-time performance degradation, this skill guides you through evidence-based diagnosis to resolution.
Features
navigate branching decision paths to isolate failure modes
distinguish hardware failures from software issues with targeted tests
match observed failures to likely culprits using domain knowledge
analyze benchmarks and compare against baseline thresholds
create reproducible test sequences for validation
organize fixes by impact and effort
record diagnosis results, evidence, and next steps
Example Output
Example 1: Camera Calibration Diagnostic Report
SYMPTOM: Distorted output images in real-time stereo vision system
DIAGNOSTIC TREE:
├─ Optical issue?
│ ├─ Lens contamination? → Visual inspection, clean, retest
│ └─ Focus drift? → Measure focal length, recalibrate
├─ Hardware failure?
│ ├─ Sensor defect? → Hot pixel map analysis
│ └─ Cable/connection? → Check impedance, reseat connectors
└─ Software issue?
├─ Calibration matrix stale? → Re-run calibration routine
└─ Processing pipeline bug? → Unit test image transforms
ROOT CAUSE: Calibration matrix expired (last updated 6 months ago)
REMEDIATION: Re-run calibration with reference checkerboard pattern
PRIORITY: High | EFFORT: 30 minutes | EXPECTED OUTCOME: Image distortion corrected
Example 2: Performance Degradation Analysis
METRIC ANALYSIS:
Frame rate: 24 fps (expected: 30 fps) → -20% degradation
Latency: 45ms (expected: 33ms) → +36% degradation
Memory: 2.1 GB (expected: 1.8 GB) → +17% growth
LIKELY CAUSES (ranked by probability):
1. GPU memory leak in preprocessing stage (80% confidence)
2. Background process contention (15% confidence)
3. Network I/O blocking main thread (5% confidence)
RECOMMENDED TESTS:
□ Profile GPU memory allocation over 100 frames
□ Monitor system resource usage during capture
□ Enable network tracing to identify I/O bottlenecks
What's Included
- SKILL.md: Full diagnostic analyst instructions and workflows
- Diagnostic Decision Tree template: Branching logic for symptom investigation
- Hardware vs. Software checklist: Tests to differentiate failure categories
- Root-Cause Analysis worksheet: Structured template for findings documentation
- Remediation Priority Matrix: Framework for ranking fixes by impact and effort
- Performance Metric Baseline table: Reference values for common vision system parameters
- Test Plan Generator: Automated sequence creation for validation
Who It's For
- Computer vision engineers — debug image processing pipelines and camera integration issues
- Robotics technicians — troubleshoot real-time vision systems in autonomous platforms
- Quality assurance engineers — systematically validate vision system performance and reliability
- Systems integrators — diagnose multi-component vision system failures
- Technical support specialists — provide structured guidance to customers experiencing vision system problems
Best For
- Camera calibration troubleshooting — fixing distortion, focus, and intrinsic parameter issues
- Image processing pipeline failures — identifying which stage in your processing chain is broken
- Real-time vision system outages — rapid diagnosis when cameras stop feeding frames
- Performance degradation investigation — analyzing frame rate drops and latency increases
- Hardware-software integration debugging — determining whether failures are in hardware, drivers, or application code
You might also like
You'll develop systematic approaches to injectable formulation design, from API selection through sterilization strategy. Claude helps you troubleshoot failed batches by analyzing root causes, recommends regulatory pathways (505(b)(2), ANDA, NDA), and provides science-backed solutions for stability, compatibility, and manufacturability challenges.
This skill helps you systematically assess integration needs across your systems, design architecture patterns that scale with your organization, and identify technical and operational risks before implementation. You'll receive architecture recommendations aligned to your business constraints, clear integration roadmaps, and risk mitigation strategies that reduce deployment surprises. Get structured decision records suitable for architecture review boards and engineering teams.
You can conduct comprehensive hazard analyses for chemical processes using industry-standard methodologies like HAZOP and LOPA. The skill helps you assess risks quantitatively, identify control gaps, design engineered safeguards, and generate formal documentation for regulatory compliance and process safety management.
Claude analyzes your code diffs and generates standardized commit messages that follow the Conventional Commits specification. The skill automatically determines the correct commit type, scope, and description based on the changes you've made, ensuring your messages are parseable by automation tools while remaining human-readable for code reviewers.
You can transform raw text into structured, labeled datasets for machine learning, analysis, and research. This skill performs named entity recognition, sentiment classification, part-of-speech tagging, and dependency parsing—generating consistent, validated annotations at scale. Use it to prepare corpora, extract entities, classify documents, or perform linguistic analysis without manual annotation.
This skill helps you systematically analyze service mesh architectures, identify inter-service communication failures, and design optimal routing and security policies. You'll receive step-by-step troubleshooting guidance tailored to your mesh platform (Istio, Linkerd, Consul), configuration validation reports, and architectural recommendations that reduce latency, improve observability, and tighten security posture.
This skill automates the creation of production-ready deployment validation checklists, infrastructure-as-code templates, and incident response runbooks tailored to your ML stack. You get comprehensive pre-deployment checks covering model validation, data pipeline integrity, infrastructure readiness, and monitoring setup—all customized for your specific models and cloud provider. The skill generates executable runbooks that teams can follow during incidents, including rollback procedures, failover strategies, and diagnostic commands.
Rapidly analyze firmware logs and diagnose hardware issues that cause device failures, connectivity problems, and performance degradation. You'll identify root causes from stack traces, crash dumps, and sensor data, then generate specific optimization recommendations. This skill transforms raw device logs into actionable debugging plans that reduce time-to-resolution from hours to minutes.