SkillVaultskills Browse all 500 skills

Search · Version 1.1.0 · Reviewed 2026-08-02

Multilingual Search Advisor

Make a defensible decision about language analyzer selection and cross-lingual retrieval with evidence, explicit trade-offs, and a verification plan.

4 method steps 4 documented failure modes 4 diagnostic checks 7 quality gates

Designs multilingual search across language detection, analyzers, morphology, transliteration, cross-lingual embeddings, synonyms, and evaluation.

₹99 one-time

Get this skill archive

What this skill helps you do

  • Language analyzer selection
  • Cross-lingual retrieval
  • Multilingual evaluation

How Multilingual Search Advisor works

You provide

Index config, analyzers, and queries that return the wrong thing

It inspects

Recall before ranking for language analyzer selection

It decides

A cross-lingual retrieval change scoped to the failing query class

You verify

Recall@k and NDCG re-measured on a judged query set

What it checks first

Multilingual Search Advisor designs multilingual search across language detection, analyzers, morphology, transliteration, cross-lingual embeddings, synonyms, and evaluation. Use it when the work involves Language analyzer selection, Cross-lingual retrieval, Multilingual evaluation.

  1. Whether relevance failures are recall problems or ranking problems, since the fixes are unrelated.
  2. Query analysis and index analysis symmetry, because a mismatch silently breaks exact matching.
  3. Whether rare tokens such as identifiers and codes are preserved rather than stemmed away.
  4. Click and abandonment data, which reveals relevance failures no offline metric captures.

Failure modes it recognizes

  • Aggressive stemming or lowercasing destroying exact matches on part numbers and error codes.
  • A relevance tweak that improves head queries while breaking the long tail nobody measures.
  • Synonym expansion introducing false positives that outrank the exact match.
  • Analyzer changes applied at query time but not reindexed, so the two sides disagree.

Answers it will reject

  • Tuning ranking weights before confirming the correct document is retrieved at all.
  • Judging relevance from a handful of favorite queries rather than a sampled distribution.
  • Boosting recency or popularity globally, which buries precise matches for specific queries.

Decision rules it applies

  • Fix recall before ranking; a document that is not retrieved cannot be ranked.
  • Keep query-time and index-time analysis identical, and reindex when either changes.
  • Evaluate on a judged set that includes head, torso, and tail queries.

Evidence it asks for

  • Measure recall@k and NDCG on a labeled query set before and after each change.
  • Track zero-result and reformulation rates as leading indicators of relevance failure.
  • Inspect the analyzed form of both the query and the document when a match fails.

The method inside

  1. Map the artifact, actors, boundaries, and invariants relevant to language analyzer selection.
  2. Trace concrete failure or abuse paths for cross-lingual retrieval; do not report checklist items without a mechanism.
  3. Prioritize multilingual evaluation findings by impact, likelihood, confidence, and cost of correction.
  4. Recommend the smallest defensible change, then define how an independent reviewer can verify it.

Deliverables

  • Language analyzer selection assessment
  • Cross-lingual retrieval decision and action plan
  • Multilingual evaluation verification checklist

Evidence requirements

  • Functional and quality requirements
  • Scale, latency, consistency, cost, and compliance constraints
  • Current topology and alternatives considered

Quality gates

  • Every material claim traces to supplied evidence or is labeled as a hypothesis.
  • The response follows the declared deliverable contract.
  • No execution, access, measurement, or verification is invented.
  • Secrets and personal data are redacted rather than repeated.
  • The user receives a concrete independent verification step.
  • The relevant failure modes in this domain were considered rather than only the reported symptom.
  • No listed anti-pattern was recommended as a solution.

Example task

Input

Users search in Hindi and English, often mixing scripts in one query. How should our search pipeline handle this?

Expected output

Detect language per token rather than per query, normalize transliteration variants, retain original terms for exact matching, and add multilingual semantic retrieval as a candidate source validated on mixed-script judged queries...

Boundaries and compatibility

Ideal for

  • Language analyzer selection: produce a decision or artifact grounded in supplied evidence.
  • Cross-lingual retrieval: produce a decision or artifact grounded in supplied evidence.
  • Multilingual evaluation: produce a decision or artifact grounded in supplied evidence.

Out of scope

  • Producing a generic reference architecture without requirements
  • Hiding material trade-offs behind best-practice language

Agent compatibility

  • GitHub Copilot custom agents
  • Claude Agent Skills / SKILL.md
  • Any instruction-following chat model

Tool policy: Advisory by default. No tools are assumed. If the host provides tools, use read-only evidence gathering unless the user explicitly approves a scoped write or execution action.