hybrid-search-eval-author

testland/qa

SkillLoads cleanly

Evaluates hybrid retrieval pipelines (BM25 + vector + reranker) end-to-end: authors ground-truth judgment sets, computes nDCG@k and MRR over fused results,…

Scores
out of 100 · grade B+

2026-08-20

Works

40% of the score

100/100

Loads cleanly: valid frontmatter, required fields present, no dangling references.

Maintained

25% of the score

100/100

no commits in the last 12 weeks

Adopted

20% of the score

11/100

5 stars on the source repo.

Documented

15% of the score

90/100

1,358 words with worked examples.
Ships 3 bundled files.

Loads cleanly. Every structural check Claude Code needs to register this passed. Last commit yesterday.

Install

npx skills add testland/qa/hybrid-search-eval-author

What it says it does

Evaluates hybrid retrieval pipelines (BM25 + vector + reranker) end-to-end: authors ground-truth judgment sets, computes nDCG@k and MRR over fused results, measures the lift from Reciprocal Rank Fusion vs weighted fusion vs single-stage retrieval, and quantifies reranker (cross-encoder/Cohere/bge) impact. Use when a production system combines lexical and semantic retrieval and you need a numeric relevance baseline, fusion-strategy comparison, or evidence that a reranker is earning its latency cost.

Every number above came out of reading the file and its repository. Nothing is a judgement call, nothing is a model’s opinion, and nothing can be paid for. The full method is published. Source last committed 2026-08-18.

Also in testland/qa

Other artifacts published from the same repository.
Artifact	What the check found	Type	Reach	Last commit
idempotency-test-authortestland/qa	clean	Skill	5 stars	yesterday
flaky-test-quarantinetestland/qa	clean	Skill	5 stars	yesterday
appium-testingtestland/qa	clean	Skill	5 stars	yesterday
fast-check-testingtestland/qa	clean	Skill	5 stars	yesterday
negative-test-generatortestland/qa	clean	Skill	5 stars	yesterday
test-code-conventionstestland/qa	clean	Skill	5 stars	yesterday

Other research skills

Browse all

Same category, same type, ranked by score.
Artifact	What the check found	Category	Reach	Last commit
nextflow-developmentanthropics/knowledge-work-plugins	clean	Research	1,966 installs	today
single-cell-rna-qcanthropics/knowledge-work-plugins	clean	Research	1,995 installs	today
last30daysmvanhorn/last30days-skill	clean	Research	33,782 installs	today
scvi-toolsanthropics/knowledge-work-plugins	clean	Research	1,958 installs	today
plugin-creatoropenai/codex	clean	Research	112k stars	today
churn-preventioncoreyhaines31/marketingskills	clean	Research	92,159 installs	today

Put this measurement in your README

A badge carrying how many listings this index holds from the repository and how many pass every static structural check. It reads from this index every time somebody loads your page, so it changes when the measurement changes and there is nothing to keep up to date. Free, no account, and the value is not something you or we can set by hand.

[![SkillWorks](https://toolproof.kynth.studio/badge/skillworks/testland/qa.svg)](https://skillworks.kynth.studio/?q=testland%2Fqa)

Would rather not hotlink us? Every badge is also served in shields.io’s endpoint schema, so shields renders the image and your readers never talk to our domain:

Published by Toolproof, the masthead over this index and eight others. The method behind the number is at toolproof.kynth.studio/methodology, and the whole thing is readable as JSON with no key at /api.