Loading...
Loading...
Found 131 Skills
Use when asked to compare multiple ML models, perform cross-validation, evaluate metrics, or select the best model for a classification/regression task.
Use when "HuggingFace Transformers", "pre-trained models", "pipeline API", or asking about "text generation", "text classification", "question answering", "NER", "fine-tuning transformers", "AutoModel", "Trainer API"
Image processing, object detection, segmentation, and vision models. Use for image classification, object detection, or visual analysis tasks.
Run ML model inference (YOLO, YOLOv8, CLIP, SAM, Detectron2, etc.) on FiftyOne datasets. Use when running models, applying detection, classification, segmentation, embeddings, or any model prediction task. Also use for end-to-end workflows that include importing data then running inference.
Analyzes and processes images using Claude's vision capabilities. Supports OCR, image classification, diagram comparison, chart analysis, visual Q&A, and more. Use when users need to understand, extract, or analyze visual content.
Write comprehensive literature reviews for medical imaging AI research. Use when writing survey papers, systematic reviews, or literature analyses on topics like segmentation, detection, classification in CT, MRI, X-ray, ultrasound, or pathology imaging. Triggers on requests for "review paper", "survey", "literature review", "综述", "systematic review", or mentions of writing academic reviews on deep learning for medical imaging.
Proof-driven exploitation with 4-level evidence system, bypass exhaustion protocol, mandatory evidence checklists, and strict EXPLOITED/POTENTIAL/FALSE_POSITIVE classification.
Manage PR crises using classification, golden hour response, crisis statement templates (3C framework), and reputation recovery planning. Use this skill when the user faces negative media coverage, a viral complaint, product safety issues, executive misconduct, or any situation threatening brand reputation — even if they say 'we're getting destroyed on social media', 'draft a response to this article', 'how do we handle this PR disaster', or 'prepare for potential backlash'.
Analyze Huawei Ascend NPU profiling data to discover hidden performance anomalies and produce a detailed model architecture report reverse-engineered from profiling. Trigger on Ascend profiling traces, NPU bottlenecks, device idle gaps, host-device issues, kernel_details.csv / trace_view.json / op_summary / communication.json. Also trigger on "profiling", "step time", "device bubble", "underfeed", "host bound", "device bound", "AICPU", "wait anchor", "kernel gap", "Ascend performance", "model architecture", "layer structure", "forward pass", "model structure". Runs anomaly discovery (bubble detection, wait-anchor, AICPU exposure) alongside model architecture analysis (layer classification, per-layer sub-structure, communication pipeline). Outputs a separate Markdown architecture report alongside anomaly analysis.
Source code security audit using backward taint analysis, slot type classification, render context verification, and 3-phase parallel review producing an exploitation queue.
Production incident response automation. Reads logs, checks recent deploys, identifies root cause, suggests fixes, drafts incident comms, creates post-mortem templates. Severity classification (SEV1-4), escalation paths, status page updates. Generates incident-report.md with timeline, root cause, impact assessment, remediation steps, and prevention measures.
DORA (EU 2022/2554) digital operational resilience compliance automation for financial entities. Assesses readiness against all 5 DORA pillars, classifies ICT incidents, validates third-party risk management, and generates resilience testing plans. Use for DORA compliance assessments, ICT risk management, incident classification, third-party ICT oversight, and digital operational resilience testing.