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.
76
66%
Does it follow best practices?
Impact
95%
1.17xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/llm-application-dev/skills/hybrid-search-implementation/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that clearly communicates the skill's purpose and when to use it. The 'Use when' clause with multiple trigger scenarios is well-constructed. The main weakness is that the 'what' portion could be more specific about the concrete actions the skill enables beyond the high-level 'combine vector and keyword search.'
Suggestions
Add more specific concrete actions to the capability description, e.g., 'Combine vector and keyword search with score fusion, reranking, and weight tuning for improved retrieval.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (hybrid search combining vector and keyword) and the general action (improved retrieval), but doesn't list specific concrete actions like 'rerank results', 'configure BM25 weights', 'build embedding pipelines', etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (combine vector and keyword search for improved retrieval) and 'when' (implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall) with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'vector search', 'keyword search', 'RAG systems', 'search engines', 'recall' — these are terms users would naturally use when seeking this capability. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of 'vector and keyword search' plus 'hybrid' retrieval creates a clear niche that is distinct from pure vector search skills, pure keyword/full-text search skills, or general RAG skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable code templates for hybrid search across multiple backends, which is its primary strength. However, it is severely over-long and monolithic—four complete class implementations are inlined without any progressive disclosure or external file references. The content would benefit enormously from being restructured into a concise overview with pointers to separate template files, and from adding explicit validation/error-handling guidance.
Suggestions
Extract the four templates into separate files (e.g., templates/rrf.py, templates/postgres_hybrid.py, templates/elasticsearch_hybrid.py, templates/rag_pipeline.py) and reference them from a concise SKILL.md overview.
Remove the 'When to Use This Skill' section and the 'Core Concepts' explanatory text—Claude already understands these concepts; keep only the architecture diagram and fusion methods table.
Add explicit validation steps and error handling guidance (e.g., what to do when one search backend returns empty results, how to verify fusion quality, fallback strategies).
Trim the Best Practices section to a compact checklist rather than Do's/Don'ts with explanations Claude can infer.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines, with four large template implementations that are largely boilerplate code. The 'When to Use This Skill' and 'Core Concepts' sections explain things Claude already knows. The Elasticsearch and PostgreSQL templates could be dramatically condensed or split into separate reference files. | 1 / 3 |
Actionability | All four templates provide fully executable, copy-paste ready Python code with proper type hints, imports, and complete method implementations. The code covers multiple real-world backends (PostgreSQL, Elasticsearch, custom pipeline) with concrete, working examples. | 3 / 3 |
Workflow Clarity | Template 4 (HybridRAGPipeline) shows a clear multi-step pipeline (embed → parallel search → fuse → rerank), but there are no validation checkpoints, error handling, or feedback loops for when searches return unexpected results. The steps are implicit in code rather than explicitly documented. | 2 / 3 |
Progressive Disclosure | All content is monolithically inlined in a single file with no references to supporting files. Four large templates (~300+ lines of code) should be split into separate reference files, with the SKILL.md providing a concise overview and links. No bundle files exist to support this content. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (565 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- wshobson/agents
- Commit
34632bc
- Reviewed
Table of Contents
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.