Results for “classification”

Reads one export transaction, order or shipment description and returns a DRAFT export review pack: parties to screen with a screening checklist, an item classification worksheet, a red-flag review, licence-determination questions and open items. Use when the user asks to "prepare the export review for this order", "pre-check this shipment for export control", "who do we need to screen on this deal", "build the classification worksheet for this item" or "assemble the trade-compliance file for this technology transfer". Do not use for vendor security or due-diligence screening of a supplier's questionnaire answers; use vendor-risk-screening-brief instead. Never classifies, screens, clears, decides licence need or releases a shipment; trade compliance does. Drafts for human review; never approves, authorises or signs off.

The English summary is being prepared. Showing the original description.

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.

The English summary is being prepared. Showing the original description.

Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.

The English summary is being prepared. Showing the original description.

Implement Amazon Macie to automatically discover, classify, and protect sensitive data in S3 buckets using machine learning and pattern matching for PII, financial data, and credentials Tespit.

The English summary is being prepared. Showing the original description.

tespit etme (s) prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The tespit etme (or) analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-...

The English summary is being prepared. Showing the original description.

Detects command-and-control (C2) communications tunneled through DNS protocol including DNS tunneling tools (Iodine, dnscat2, dns2tcp, Cobalt Strike DNS beacon), domain generation algorithms (DGA), encoded payload delivery via TXT/CNAME records, and DNS beaconing patterns. Covers Shannon entropy analysis of query subdomains, statistical anomaly detection, ML-based DGA classification, passive DNS correlation, and Zeek/Suricata signature development. Activates for requests involving DNS-based C2 detection, DNS tunnel identification, suspicious DNS traffic investigation, or DGA domain classification.

The English summary is being prepared. Showing the original description.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

The English summary is being prepared. Showing the original description.

End-to-end shotgun metagenomics workflow from FASTQ to taxonomic and functional profiles, orchestrating controls/host depletion, Kraken2+Bracken classification, MetaPhlAn marker profiling, and HUMAnN functional profiling. Covers the controls-first ordering, why Kraken2 read counts are not abundances and MetaPhlAn cell fractions do not equal Bracken read fractions, and the consistent-pipeline framing. Use when profiling shotgun metagenomic samples end to end, or chaining classification, abundance, and function. For resistome see metagenomics/amr-detection; for strains see metagenomics/strain-tracking; for assembly see genome-assembly/metagenome-assembly.

The English summary is being prepared. Showing the original description.

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.

The English summary is being prepared. Showing the original description.

Claude API (platform.claude.com) のプロンプトエンジニアリング・評価リファレンス。 prompt engineering, XML タグ, few-shot, system prompts, モデル別プロンプティング（Fable 5.1 / Fable 5 / Opus 5.5 / Opus 5 / Sonnet 5.5 / Sonnet 5 / Haiku 5.5）。 evals, grading（LLM-graded 等）, jailbreak・prompt leak 対策, hallucination 低減, classification, ticket routing, commerce agent 等ユースケース実装。

The English summary is being prepared. Showing the original description.

Use this skill when a crash has been incorrectly classified as DOT-recordable when it shouldn't be. Covers the § 390.5 criteria, common misclassifications, and challenge process.

The English summary is being prepared. Showing the original description.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

The English summary is being prepared. Showing the original description.

Detects command-and-control (C2) communications tunneled through DNS protocol including DNS tunneling tools (Iodine, dnscat2, dns2tcp, Cobalt Strike DNS beacon), domain generation algorithms (DGA), encoded payload delivery via TXT/CNAME records, and DNS beaconing patterns. Covers Shannon entropy analysis of query subdomains, statistical anomaly detection, ML-based DGA classification, passive DNS correlation, and Zeek/Suricata signature development. Activates for requests involving DNS-based C2 detection, DNS tunnel identification, suspicious DNS traffic investigation, or DGA domain classification.

The English summary is being prepared. Showing the original description.

Inventory existing tests and identify gaps. Link requirements, business rules, risks, and bugs to stable test identifiers and executable evidence, maintaining a test registry that shows what is covered and what still needs verification.

• Inventory existing tests and identify gaps
• Link bug fixes to regression evidence
• Check client and server behavior against one shared contract

Research United States patents and trademarks using official USPTO records. Find patents, check application and trademark status, review examination documents and ownership transfer records, and keep search logs so findings can be checked and reproduced.

• Search patents by company, inventor, date, or classification
• Check patent application status and examination records
• Retrieve trademark status and documents

Build clinical decision support for electronic medical records, covering drug interactions, dose validation, clinical risk scores, and alerts. Provides patterns for testable checking functions, severity-based interface behavior, and safety tests that detect missed warnings.

• Implementing drug interaction and allergy checks
• Validating doses using patient factors
• Implementing NEWS2 and other clinical scores

Review healthcare applications for exposure of patient and staff information. Classify sensitive data, design access restrictions for individual database rows, record data access and changes, and check common leaks through logs, URLs, and browser storage.

• Review code that handles patient records
• Design access restrictions between healthcare facilities
• Record access to and changes in sensitive data

Generate model responses in defined formats for data extraction and classification. Use JSON schemas, Pydantic data models, regular expressions, or fixed choices to produce structured results that other programs can parse and validate.

• Extracting company or product details from text
• Classifying reviews into predefined labels
• Turning profile text into structured fields

Classify images using written labels without additional training data, or find images that match a text query. This skill provides CLIP workflows for image-text similarity, batch processing, and storing searchable image representations in vector databases.

• Classify photos using written category labels
• Find images by describing their content
• Compare images with candidate descriptions

Control local language model output with patterns and grammar rules to generate structured JSON, formatted dates, and fixed classification labels. The skill also covers reusable Python functions and workflows that combine multiple generation steps.

• Generate JSON that follows a defined schema
• Keep dates and email addresses in a specified format
• Classify text using a fixed set of labels

Maintain Paperclip Storybook examples by comparing them with shipped interfaces and the feature map. Update fixtures, classifications, and catalog references while preserving stable links and clearly identifying current examples, prototypes, historical work, and cases needing review.

• Reconciling Storybook examples after interface changes
• Updating mock data and API responses
• Classifying prototypes and historical examples

Select, inspect, validate, and report Paperclip evaluations for Runner protocol behavior or complete product workflows. Interpret results with evidence, source revisions, costs, and failure categories, and refresh reports from retained evidence without new provider calls.

• Choosing between Runner and Product E2E evaluations
• Inspecting evaluation catalogs without credentials
• Interpreting failures using evidence and execution records

Browse World Monitor's curated news feeds by topic or language, with duplicate stories removed. Review headlines, sources, publication dates, threat labels, and alert flags, then summarize selected headlines or translate them through the connected tools.

• Scanning current headlines across topics
• Reviewing technology or finance news by language
• Summarizing or translating selected headlines

Help DeerFlow maintainers investigate GitHub issues and review pull requests, or proposed code changes. It prepares or posts evidence-based comments with fix strategies, risks, and validation guidance, and compares competing proposals for the same issue.

• Draft issue replies with fixes and validation steps
• Post evidence-based pull request review findings
• Review batches of issues and pull requests