arize-evaluator
🎯Skillfrom github/awesome-copilot
LLM-as-judge evaluator workflow on Arize — define versioned evaluators (template + classification choices + judge model + invocation params + span/trace/session granularity), create tasks that run them on real data via column mapping, and enable continuous monitoring via `ax tasks trigger-run`. Use for hallucination/faithfulness/correctness/relevance scoring of spans or experiments.
Same repository
github/awesome-copilot(315 items)
Installation
npx vibeindex add github/awesome-copilot --skill arize-evaluatornpx skills add github/awesome-copilot --skill arize-evaluator~/.claude/skills/arize-evaluator/SKILL.mdSKILL.md
More from this repository10
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Generates comprehensive Product Requirements Documents (PRDs) by systematically analyzing requirements and crafting detailed technical specifications
Expert technical writer guided by the Diataxis framework, creating tutorials, how-to guides, reference docs, and explanation pages for software documentation.
Generates Excalidraw diagrams from natural language descriptions, creating visual representations of processes, systems, relationships, and ideas.
A community-curated collection of custom agents, prompts, instructions, and skills to enhance GitHub Copilot across different domains, languages, and use cases.
Provides Spring Boot best practices covering project setup, dependency injection, REST API design, data access with JPA, security configuration, and testing strategies.
Creates optimized multi-stage Dockerfiles for any language or framework, separating builder and runtime stages to produce smaller, more secure container images.
Creates README.md files for projects.
Merges mature lessons from domain memory files into instruction files, consolidating knowledge with minimal redundancy across global, user, and workspace scopes.