Route LLM evaluation-method requests to matching local workflow files.
npx skills add https://github.com/jscraik/Agent-Skills --skill evals-router
Please help me install this Agent Skill. Skill: evals-router Source: https://github.com/jscraik/Agent-Skills/tree/main/utilities/evals-router Command: npx skills add https://github.com/jscraik/Agent-Skills --skill evals-router
This Skill streamlines the process of directing complex LLM evaluation tasks to the most appropriate specialized workflow, ensuring efficient and accurate problem-solving.
eval-audit workflow.Use the evals-router skill to audit our LLM eval pipeline and tell us what is missing before we trust the scores.
High-intent search queries and answers about installing and using this skill.
Route LLM evaluation tasks by matching user goals and available artifacts to specific local workflow files, providing prerequisite and trust-boundary guidance for accurate execution.
Audit an LLM evaluation setup by directing requests to the eval-audit workflow, which identifies missing components and validates trust boundaries before relying on evaluation scores.
RAG evaluation and synthetic eval data generation are supported workflows, triggered by matching your specific evaluation goals and available artifacts to the corresponding local workflow files.
LLM evaluator validation and judge prompt design are handled by routing your specific request to dedicated workflows, ensuring explicit prerequisite checks and trust-boundary guidance are applied.
Existing artifacts are required to validate an LLM evaluation pipeline, as the routing mechanism matches your available artifacts to the narrowest, most trustworthy workflow for immediate action.
Automated routing for LLM evaluation relies on matching user goals and artifacts to predefined workflows, meaning it cannot process tasks outside its supported scope of eval design, auditing, and review tooling.
Corvalis-LLCOutline a skill workflow from drafting to evaluation with SKILL.md structure.
oimiragieoEvaluate agent performance, rule compliance, and workflow quality across task datasets.
iani-kuliAudit LLM evaluation pipelines and prioritize systemic issues in error analysis and judge design.
Alex1980AlexQuantify search and RAG output quality using standardized retrieval metrics.