Evaluate corpus retrieval quality with Hit@5, MRR, and nDCG metrics.
npx skills add https://github.com/nicholasglazer/gnosis-mcp --skill eval-nicholasglazer
Please help me install this Agent Skill. Skill: eval Source: https://github.com/nicholasglazer/gnosis-mcp/tree/main/skills/eval Command: npx skills add https://github.com/nicholasglazer/gnosis-mcp --skill eval-nicholasglazer
Measures retrieval quality on your corpus by evaluating against golden queries, providing interpretable results and regression tracking after ingestion or config changes.
Run the evaluation to generate current metrics and compare them to your saved baseline.
High-intent search queries and answers about installing and using this skill.
Measure retrieval quality by running an evaluation against golden queries to generate Hit@5, MRR, and nDCG metrics. This validates search accuracy and tracks regressions after ingest or configuration changes.
Track search regressions by comparing current evaluation metrics against a saved baseline. This highlights performance drops and provides actionable tuning pointers when numbers look off after ingesting new data.
Calculate Hit@5 and MRR by running a retrieval evaluation wrapper over your corpus using golden queries. This generates interpretable results that you can save as a baseline for future regression comparison.
Yes, this retrieval evaluation requires integration with gnosis-mcp eval. It acts as a thin wrapper around gnosis-mcp to perform quick quality checks and validate search accuracy on your corpus.
Run an evaluation to validate search accuracy after each corpus ingest or configuration change. This ensures your retrieval quality has not regressed from its saved baseline metrics.
arbgjrIndexes external reference documents into a searchable corpus for RAG workflows.
Chachamaru127Verify builds, recover from errors, and apply review fixes across CI pipelines.
Exia-thdProfile web applications and generate k6/Artillery load testing scripts.
floflo777Evaluate RAG systems using retrieval, generation, and latency metrics.
