Victoria Duan
Community@victoriakaey
Existence is in beta, updates pending
Agent Skills by Victoria Duan
Showing 17 vetted skills indexed across 2 GitHub repositories.
build-reliable-agents
Design and operate reliable LLM agents with deterministic validation and rollback protocols.
prompt-design
Diagnose structural prompt failures and redesign prompts for reliable LLM outputs.
memory-system
Design memory systems for agents to persist and retrieve information across sessions.
regression-testing
Compare LLM system outputs across versions to locate regression sources.
devops
Automate end-to-end deployment planning and execution across environments.
database-design
Design query-first PostgreSQL schemas with pgvector for AI storage.
ai-system-design
Guide product idea clarification and AI system architecture design.
experiment-driven-development
Coordinate LLM development cycles with evidence-driven changes and traceable commits.
code-review
Review code for correctness, security, performance, and maintainability with severity-based reports.
prompt-change-management
Automate prompt change documentation, validation, and rollback protocols for LLM systems.
problem-exploration
Structures exhaustive option listing and trade-off analysis for complex technical problems before committing to a solution.
agent-architecture
Guide engineers in selecting agent architectures and decision patterns.
harness-design
Define tool space, observation format, and evaluation signals for LLM agent harnesses.
critic-judge-design
Design Critic/Judge nodes with input schemas and structured verdicts.
model-selection
Compare LLM deployment paths and models across cost, latency, privacy, and capability.
agent-integration
Integrate stateful LLM agents with webhooks, SSE, and message queues.
reflect
Analyze user-described events and emotional patterns using therapeutic frameworks.