hybrid-search-implementation

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

1.13x

Quality

66%

Does it follow best practices?

Impact

93%

1.13x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/llm-application-dev/skills/hybrid-search-implementation/SKILL.md

Evaluation results

90%

Internal Knowledge Base Search Engine

RRF fusion pipeline implementation

Criteria

Without context

With context

RRF constant k=60

100%

RRF formula correctness

100%

Candidate over-fetching

70%

100%

Parallel search execution

100%

Source field tracking

100%

Both scores retained

Handles single-source documents

100%

Includes keyword search

100%

Top-k truncation after fusion

100%

Descending score sort

100%

30%

Legal Document Search Infrastructure

PostgreSQL hybrid search schema

Criteria

Without context

With context

HNSW vector index

100%

vector_cosine_ops operator

100%

GIN full-text index

100%

GENERATED ALWAYS AS tsvector

100%

websearch_to_tsquery usage

100%

FULL OUTER JOIN for result combination

100%

RRF scoring in SQL

100%

pgvector extension

100%

JSONB metadata column

100%

CTE-based query structure

100%

90%

Research Paper Discovery Tool

Linear fusion and cross-encoder reranking

Criteria

Without context

With context

Min-max score normalization

100%

Alpha-weighted combination

100%

Cross-encoder model choice

100%

Reranking candidate over-fetching

Query-content pairs for reranker

100%

Rerank score descending sort

100%

Empty results handling

100%

Optional reranking toggle

100%

Missing-source score defaults to zero

100%

Normalization zero-range guard

100%

Repository: Dicklesworthstone/pi_agent_rust
Commit: 47823e3

Evaluated: 29 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Internal Knowledge Base Search Engine Legal Document Search Infrastructure Research Paper Discovery Tool

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.