Results for “deadlock-detection”

Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.

Investigates slow responses, tool failures, and guardrail rejections by querying agent trace logs and performance metrics.

Investigates hard, flaky, or performance failures through a six-phase feedback-loop-first debugging process; use when quick targeted debugging is insufficient.

Detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using the Resemble AI platform.

Find the earliest decisive failure in an agent run trace and propose an evidence-backed targeted repair. Load when a run failed, results are wrong, or the user asks what went wrong in an agent session. Also triggers on "localize the fault", "first incorrect step", "debug this run", "trace attribution", "why did the agent fail", or after run-trace captures errors. Pairs with debug-and-fix for code defects and dynamic-routing for plan faults.

Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and production deployment with ONNX/TensorRT. Includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection frameworks. Use when building detection pipelines, training custom models, optimizing inference, or deploying vision systems.

AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.

Systematic debugging workflow for errors and bugs. Use when debugging errors, investigating bugs, troubleshooting issues, or when something isn't working as expected. Integrates Sentry MCP for production error context, Firecrawl for researching fix patterns, and Sequential Thinking for complex multi-step diagnosis.