GitHub
llm-judge-patterns
Comprehensive guide to using LLMs as judges for automated evaluation including prompt patterns, calibration, bias reduction, and multi-judge ensembles
Skills IA Recherche
Découvrez les skills Recherche, comparez leurs dépôts et consultez leurs instructions.
Catégories: Recherche
Recherche Effacer les filtres
Explorer
GitHub
architecture-review
Structured process for reviewing and validating architectural decisions before implementation to catch issues early.
GitHub
schema-management
Strategies for managing data structures, versioning, and evolutions across databases and event streams.
GitHub
repo-map-ssot
Single source of truth for repository structure and entry points, including key directories, domain boundaries, shared code, integrations, and build/deploy references
GitHub
lineage-and-provenance
See the main Data Lineage skill for comprehensive coverage of data lineage tracking and provenance.
GitHub
db-migration-generator
Generator สำหรับสร้าง database migration files พร้อม up/down scripts, validation และ rollback safety
GitHub
ground-truth-management
Comprehensive guide to creating, managing, and maintaining ground truth datasets for AI evaluation including annotation, quality control, and versioning
GitHub
bulkhead-patterns
Resource isolation strategies to prevent cascading failures and limit blast radius in distributed systems
GitHub
event-sourcing
Implementing event sourcing pattern for maintaining application state as a sequence of immutable events.
GitHub
data-quality-checks-and-validation
Implementing comprehensive data quality checks across the data pipeline to ensure accuracy, completeness, and reliability.
GitHub
retry-timeout-backoff-strategies
Comprehensive guide to implementing robust retry logic, timeout handling, and backoff algorithms for resilient distributed systems
GitHub
ai-risk-assessment
Identifying, assessing, and mitigating risks in AI systems including bias, safety, privacy, security, and ethical concerns.
GitHub
agent-self-correction
Protocols for the agent to autonomously detect failures, analyze root causes, and attempt recovery strategies before requesting user intervention.
GitHub
endpoint-generator
Generator สำหรับสร้าง API endpoint พร้อม controller, service, repository, validation, tests และ documentation โดยอัตโนมัติ
GitHub
security-baseline-controls
Minimum security controls every service must implement: authentication/authorization, input validation, secrets management, security headers, dependency security, audit logging, and operational guardrails
GitHub
prompt-library-minimal
คลัง prompts แบบ minimal ที่ใช้ token น้อยที่สุดแต่ได้ผลลัพธ์ดี พร้อม templates และ best practices
GitHub
proposal-sow-delivery-management
Comprehensive guide to professional services delivery including proposal writing, SOW creation, pricing strategies, scope management, and client delivery
GitHub
ai-model-registry
Centralized management of machine learning models throughout their lifecycle, including versioning, metadata, and production deployment.
GitHub
tech-stack-selection
Systematic approach to choosing technologies, frameworks, and tools based on requirements, team capabilities, and long-term sustainability.
GitHub
llm-token-optimization
See the main LLM Cost Optimization skill for comprehensive coverage of token economics and optimization strategies.
GitHub
grpc-integration
Comprehensive guide to gRPC for high-performance microservices communication with Protocol Buffers.
GitHub
architecture-decision-records-adr
Documenting significant architectural decisions with context, consequences, and rationale for future reference.
GitHub
where-to-find-what
A quick lookup guide for navigating a repository: where to find endpoints, business logic, models, tests, configs, docs, scripts, plus search patterns and commands
GitHub
roadmap-planning
Comprehensive guide to creating, communicating, and maintaining technical and product roadmaps for strategic alignment and stakeholder communication
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.