model-serving-inference
Comprehensive guide to deploying and serving LLM models including optimization, batching, caching, and production infrastructure
探索开发、内容、数据与办公效率等 AI 技能。先比较用途和仓库热度,再查看技能说明与来源。
Comprehensive guide to deploying and serving LLM models including optimization, batching, caching, and production infrastructure
Comprehensive guide to access audits, periodic reviews, anomaly detection, and segregation of duties for compliance and security.
Policy และ automation สำหรับ data retention, archival และ deletion ตาม compliance requirements
Comprehensive guide to effective prompt engineering patterns including few-shot, chain-of-thought, ReAct, and advanced prompting techniques
Comprehensive guide to detecting Personally Identifiable Information (PII) across systems, databases, and logs using regex patterns, NER models, and automated scanning tools.
กลยุทธ์การ retrieve context ให้ AI อย่างมีประสิทธิภาพ - เลือกอะไร ไม่เลือกอะไร และจัดลำดับอย่างไร
Comprehensive guide to API versioning approaches for maintaining backward compatibility.
Patterns for distributing configuration and secrets to services safely and consistently across environments (env vars, config files, secret managers, K8s External Secrets, and change process)
Comprehensive guide to incident severity classification and response requirements
Techniques and tools for understanding how machine learning models make decisions and explaining those decisions to stakeholders.
The master skill for analyzing, designing, and standardizing the creation of new AI skills (Skill 72).
Organization-wide REST/GraphQL API conventions: URL and naming rules, versioning, pagination/filtering, status codes, authentication headers, and compatibility guidance
Policy สำหรับ automated security scanning ใน CI/CD pipeline รวม dependency audit, SAST, และ secret detection
See the main Incident Triage skill for comprehensive triage workflows and procedures.
Comprehensive guide to consumer-driven contract testing with Pact, bi-directional contracts, and integration with CI/CD pipelines
Comprehensive guide to offline and online evaluation strategies including A/B testing, shadow mode, canary deployments, and bridging offline-online metrics
Standardized local development environment setup ensuring consistency across team members and reducing "works on my machine" issues.
Comprehensive guide to Agile Scrum methodology including roles, ceremonies, artifacts, sprint planning, and best practices for iterative software development
See the main Model Explainability skill for comprehensive coverage of confidence scoring and calibration.
Protecting personal and sensitive data throughout the machine learning lifecycle, from training to inference.
Implementing fast feedback loops with hot reload, live reload, and rapid iteration to maximize developer productivity.
Architecture and implementation strategies for consumption-based billing models in SaaS products.
SSOT blueprint for creating consistent services: folder structure, required endpoints, dependency conventions, interface contracts, docs/testing/security/observability requirements
Design patterns for building autonomous AI agents that can reason, plan, and execute tasks.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。