Most Used Tags
Published Resources
regression-testing
Systematically compare LLM versions to identify regressions and ensure deterministic behavior.
code-review
Streamline your code review process with Claude's structured feedback and guided self-review.
agent-integration
Connect LLM agents to applications and APIs using various integration patterns.
database-design
Design efficient database schemas for new systems or revise existing ones with AI-specific considerations.
critic-judge-design
Design effective LLM Critic nodes by avoiding common pitfalls and ensuring reliable judgments.
problem-exploration
Systematically explore technical problems with multiple solutions to make informed decisions.
ai-system-design
Guide non-technical users to design AI systems from their ideas without needing technical knowledge.
agent-architecture
Framework for making architectural decisions in LLM agent projects.
memory-system
Design effective memory systems for agents to enhance user interactions.
harness-design
Design and improve the action space, observation format, and evaluation signals of LLM agents.
model-selection
Select the optimal model for LLM applications, balancing deployment options and fine-tuning needs.
prompt-change-management
Manage prompt changes in LLM systems to prevent regressions and ensure stability.
experiment-driven-development
Structured process for LLM development to prevent failures from assumptions.
build-reliable-agents
A collection of skills for building reliable LLM agents throughout their development lifecycle.
prompt-design
Optimize LLM prompts by designing from scratch or diagnosing existing ones for better outputs.
devops
Streamline application deployment with best practices for CI/CD and environment management.