“classification”的搜索结果

Detects 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 detector 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-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.

中文简介正在准备中。当前显示原文说明。

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.

中文简介正在准备中。当前显示原文说明。

Detects 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 detector 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-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.

中文简介正在准备中。当前显示原文说明。

Build text and data classification systems with training and evaluation. TRIGGERS - Use when user needs help with ai-classification-system related tasks.

中文简介正在准备中。当前显示原文说明。

Prioritizes rare-disease variants from trio/quad WES/WGS with de novo (DeNovoGear, Triodenovo), compound-heterozygous phasing (WhatsHap), mosaic VAF tiering, phenotype-driven ranking (Exomiser, Phen2Gene, AMELIE), ClinGen gene-disease validity gating, and ACMG SF v3.2 secondary findings reporting. Use when running diagnostic exome / genome pipelines, identifying candidate Mendelian disease genes, screening for incidental findings, or auditing VUS reclassification cycles. The ACMG/AMP classification framework (PVS1 decision tree, Pejaver PP3/BP4 calibration, Tavtigian point system) is in clinical-databases/acmg-classification.

中文简介正在准备中。当前显示原文说明。

Prioritizes rare-disease variants from trio/quad WES/WGS with de novo (DeNovoGear, Triodenovo), compound-heterozygous phasing (WhatsHap), mosaic VAF tiering, phenotype-driven ranking (Exomiser, Phen2Gene, AMELIE), ClinGen gene-disease validity gating, and ACMG SF v3.2 secondary findings reporting. Use when running diagnostic exome / genome pipelines, identifying candidate Mendelian disease genes, screening for incidental findings, or auditing VUS reclassification cycles. The ACMG/AMP classification framework (PVS1 decision tree, Pejaver PP3/BP4 calibration, Tavtigian point system) is in clinical-databases/acmg-classification.

中文简介正在准备中。当前显示原文说明。

Semantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classification, similarity matching. NOT for counting objects, fine-grained classification (celebrities, car models), spatial reasoning, or compositional queries. Activate on "CLIP", "embeddings", "image similarity", "semantic search", "zero-shot classification", "image-text matching".

中文简介正在准备中。当前显示原文说明。

Codified expertise for customs documentation, tariff classification, duty optimization, restricted party screening, and regulatory compliance across multiple jurisdictions. Informed by trade compliance specialists with 15+ years experience. Includes HS classification logic, Incoterms application, FTA utilization, and penalty mitigation. Use when handling customs clearance, tariff classification, trade compliance, import/export documentation, or duty optimization.

中文简介正在准备中。当前显示原文说明。

Detects 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 detector 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-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.

中文简介正在准备中。当前显示原文说明。

协助进出口商品关税归类、通关文件审查和制裁对象匹配核查，涵盖美国、欧盟、英国及亚太地区的贸易实务，并整理关税优惠条件及海关问询应对。

• 根据商品规格研究关税归类
• 审查商业发票与原产地证明
• 核查自由贸易协定优惠条件

Send a single request to DeepSeek for summarization, information extraction, or simple classification. Receive the response and token usage as JSON for further processing, with structured status information when the API is unavailable.

中文简介正在准备中。当前显示英语简介。

• Summarizing text in a single request
• Extracting information from text
• Classifying text into simple categories

Analyze time series with aeon, a Python toolkit for data that changes over time. Supports classification, regression, clustering, forecasting, anomaly detection, and pattern search, with guidance on preprocessing, algorithm selection, and evaluation.

中文简介正在准备中。当前显示英语简介。

• Classify time series and predict continuous outcomes
• Group time series with similar patterns
• Forecast future values

Prepare Apache Airflow provider releases by classifying pending changes, inspecting pull request diffs for compatibility risks, and applying version bumps and changelog entries. Use existing breeze tooling to regenerate release documentation and consult the release manager on uncertain decisions.

中文简介正在准备中。当前显示英语简介。

• Prepare documentation for a regular provider release cycle
• Classify changes for a selected set of providers
• Review breaking changes and choose version bumps

Screen AI application inputs and historical logs for prompt injection, where malicious instructions try to redirect the model. Combine pattern matching, text structure scoring, and a DeBERTa classifier to flag suspicious content and produce JSON results.

中文简介正在准备中。当前显示英语简介。

• Screening chatbot and AI agent inputs
• Checking external text used in retrieval-based AI applications
• Auditing historical interaction logs for injection attempts

Adapt a knowledge collection's schema, the rules defining page types and relationships. Review untyped pages, propose new types, update classification settings, and apply those types to existing pages after previewing the changes and checking consistency.

中文简介正在准备中。当前显示英语简介。

• Adding page types for researchers and papers
• Classifying existing pages that have no type
• Proposing new types from stored content

Recommend where new gbrain pages belong using the active schema pack, a configuration defining page types and storage paths. It also checks existing pages for missing or undeclared types and highlights cases requiring a classification decision.

中文简介正在准备中。当前显示英语简介。

• Choose a storage path before creating a brain page
• Check filing rules before a bulk import
• Apply classification settings for a specific source

Assess detected security events by checking false positives, assigning incident types and severity levels, and identifying escalation routes. Guide initial response and forensic evidence collection, including records of who collected, held, and transferred each evidence item.

中文简介正在准备中。当前显示英语简介。

• Classifying security alerts during initial response
• Checking false positives before escalation
• Planning evidence collection and custody records

Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.

中文简介正在准备中。当前显示英语简介。

• Fine-tuning an embedding model for domain-specific search
• Training a model to rerank search results
• Training SPLADE or ColBERT retrieval models

Build safety checks for LLM prompts and responses using Meta's LlamaGuard. This skill covers content classification, batch moderation, serving a moderation API, and connecting checks to NeMo Guardrails.

中文简介正在准备中。当前显示英语简介。

• Screening user prompts before sending them to an LLM
• Checking generated responses before displaying them
• Building an API for content safety checks

Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.

中文简介正在准备中。当前显示英语简介。

• Fine-tuning an embedding model for domain-specific search
• Training a model to rerank search results
• Training SPLADE or ColBERT retrieval models

Run an audit, separate findings that can be fixed automatically from those needing manual work, and apply eligible fixes with tests and separate commits. Use severity filters, a finding limit, or a classification-only dry run.

中文简介正在准备中。当前显示英语简介。

• Fixing audit findings with test verification
• Prioritizing findings by severity
• Limiting how many findings are fixed

Research employment questions about overtime, breaks, leave, worker classification, and final pay for a specific state or country. Receive an answer with cited legal sources, notes on recent changes, and issues requiring professional judgment.

中文简介正在准备中。当前显示英语简介。

• Checking overtime and break rules for a specific state
• Reviewing whether a role qualifies for an overtime exemption
• Checking final-pay deadlines and unused leave payouts

Build an AI system register for EU AI Act reviews. Track owners, deployment status, EU connections, and each system’s role and risk category through a guided discussion, preserving classification reasons and dates for future review.

中文简介正在准备中。当前显示英语简介。

• Register AI systems used or planned across an organization
• Review each system’s role and risk category
• Find systems approaching their next review date

Create an AI impact assessment in your team's format. Gather system details through conversation, analyze risks and applicable regulatory classifications, check consistency with internal policy, and document recommendations, safeguards, and conditions for deployment.

中文简介正在准备中。当前显示英语简介。

• Assessing an AI system before deployment
• Preparing an assessment after conditional triage
• Reviewing pilot or production AI risks