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.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/llm-application-dev/skills/hybrid-search-implementation/SKILL.md

Quality

Content

55%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The SKILL.md body is a clean, well-structured overview that appropriately offloads detailed templates to a real one-level-deep reference file. Its weaknesses are the lack of any executable code or explicit implementation workflow with validation checkpoints in the body itself.

Suggestions

Include at least one minimal executable fusion snippet (e.g., a short RRF implementation) directly in the body so the skill is actionable before opening the reference.

Add a short numbered implementation workflow (retrieve candidates -> fuse -> optional rerank -> evaluate) with a validation/evaluation checkpoint (e.g., compare recall against a held-out set).

Tighten the Do's/Don'ts bullets by dropping the trailing justifications that restate the obvious, or move them into details.md.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding about what RAG or vector search is; minor justifications on the Do's/Don'ts bullets ('Handles exact matches better') are slightly trimmable, keeping it just below 5.	4 / 5
Actionability	The body names fusion methods in a comparison table and gives recommendations, but contains no executable code or commands—all concrete templates are deferred to references/details.md, leaving execution incomplete without the reference.	3 / 5
Workflow Clarity	The architecture diagram gives a rough data-flow sequence (Query -> Vector+Keyword -> Fusion -> Results) but no explicit implementation steps and no validation checkpoints; steps are poorly defined.	2 / 5
Progressive Disclosure	A well-organized 56-line overview that clearly signals a single one-level-deep reference (references/details.md, which exists and contains no nested references); not a 5 because the four templates in details.md are pointed to generically rather than via labeled sub-references.	4 / 5
	Total	13 / 20 Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description with an explicit 'Use when' clause and concrete trigger scenarios. Its main limitation is specificity: it describes one combined action rather than enumerating several concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('Combine vector and keyword search for improved retrieval') but does not list several specific actions, so it sits at the 'domain + 1-2 actions, not comprehensive' anchor rather than 4.	3 / 5
Completeness	Explicitly answers both what ('Combine vector and keyword search for improved retrieval') and when with three concrete trigger phrases via the 'Use when...' clause.	5 / 5
Trigger Term Quality	Natural terms users would say ('RAG systems', 'search engines', 'vector and keyword search') give good coverage; not a 5 because synonyms/exhaustive variations are missing.	4 / 5
Distinctiveness Conflict Risk	Hybrid vector+keyword search is a distinct niche, but the 'RAG systems' trigger creates minor overlap risk with general RAG/vector-search skills, keeping it just below 5.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: wshobson/agents
Path: plugins/llm-application-dev/skills/hybrid-search-implementation/SKILL.md
Commit: d6837ae

Reviewed: about 11 hours ago

Table of Contents

Discovery Implementation Validation

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.