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

41%

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 ./skills/hybrid-search-implementation/SKILL.md

The canonical home for this skill is hybrid-search-implementation in rmyndharis/antigravity-skills

Quality

Content

18%Scale 1-5

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

This skill is essentially a stub with no actionable content. It correctly identifies when hybrid search should be used but provides zero implementation guidance — no code examples, no algorithms (e.g., RRF, weighted scoring), no library recommendations, and no concrete workflow. The Instructions section consists entirely of generic boilerplate that could apply to any skill, and the referenced playbook file is not provided in the bundle.

Suggestions

Add concrete code examples showing hybrid search implementation (e.g., combining vector similarity scores with BM25 keyword scores using Reciprocal Rank Fusion or weighted linear combination)

Include specific library/tool recommendations (e.g., pgvector + tsvector in PostgreSQL, or Elasticsearch with knn_search + match queries) with executable code snippets

Replace the generic Instructions bullets with a concrete workflow: 1) Set up vector index, 2) Set up keyword index, 3) Execute both searches, 4) Combine scores using RRF, 5) Validate results with test queries

Either provide the referenced `resources/implementation-playbook.md` bundle file or inline the essential patterns directly in the SKILL.md

Dimension	Reasoning	Score
Conciseness	The 'Use this skill when' and 'Do not use this skill when' sections are reasonable but the Instructions section is entirely generic boilerplate ('Clarify goals, constraints, and required inputs', 'Apply relevant best practices') that adds no value specific to hybrid search. The content is short but wastes tokens on non-informative filler.	3 / 5
Actionability	There is zero concrete guidance on how to implement hybrid search — no code, no commands, no specific algorithms, no scoring formulas, no library recommendations. The instructions are entirely abstract platitudes like 'Apply relevant best practices and validate outcomes' which provide no executable direction.	1 / 5
Workflow Clarity	There is no workflow, no sequenced steps, and no validation checkpoints. The four bullet points in Instructions are generic meta-instructions that don't describe any process for implementing hybrid search.	1 / 5
Progressive Disclosure	The skill references `resources/implementation-playbook.md` for detailed patterns, which is a reasonable structure, but no bundle files are provided so the reference is unverifiable. The SKILL.md itself contains essentially no substantive content to serve as an overview — it's an empty shell pointing to a file that may not exist.	2 / 5
	Total	7 / 20 Passed

Description

65%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.

The description clearly communicates the domain (hybrid search) and provides explicit 'when' guidance with relevant trigger scenarios. However, it lacks specificity in concrete actions—it says 'combine' but doesn't describe what that entails (e.g., scoring, reranking, weight tuning, indexing). Adding more concrete capabilities and a few additional trigger synonyms would strengthen it.

Suggestions

Add specific concrete actions such as 'configure scoring weights, implement reciprocal rank fusion, set up BM25 + embedding pipelines' to improve specificity.

Include additional trigger synonyms like 'semantic search,' 'full-text search,' 'BM25,' 'embedding retrieval,' or 'hybrid retrieval' to improve keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (hybrid search combining vector and keyword) but provides no concrete actions beyond 'combine.' No specifics about what operations are performed—e.g., indexing, scoring, reranking, configuring weights—are mentioned.	2 / 5
Completeness	Has both 'what' (combine vector and keyword search for improved retrieval) and 'when' (implementing RAG systems, building search engines, insufficient recall). The 'what' is somewhat thin, and the 'when' could be more specific with additional trigger phrases, but both are present and explicit.	4 / 5
Trigger Term Quality	Includes several natural keywords users would say: 'vector search,' 'keyword search,' 'RAG systems,' 'search engines,' and 'recall.' Missing some common synonyms like 'semantic search,' 'full-text search,' 'BM25,' 'embedding search,' or 'hybrid retrieval.'	4 / 5
Distinctiveness Conflict Risk	The combination of 'vector and keyword search' and 'hybrid' retrieval is fairly distinctive. There's minor overlap risk with a pure vector search skill or a pure keyword search skill, but the hybrid framing and RAG mention help distinguish it.	4 / 5
	Total	14 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/hybrid-search-implementation/SKILL.md
Commit: 0159794

Reviewed: about 12 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.