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

55%

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

Quality

Content

32%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 body is structured into clear sections but is almost entirely generic boilerplate with no executable guidance, no sequenced workflow, and a broken reference to a non-existent resources file. It fails to provide the concrete hybrid-search patterns its description promises.

Suggestions

Replace the generic "Instructions" boilerplate with concrete, actionable hybrid-search steps — e.g. specific library calls (vector index + BM25), fusion strategies (RRF, weighted), and a copy-paste-ready code example.

Add a sequenced workflow with explicit validation checkpoints: build/refresh each index, run both retrievers, fuse and re-rank, then verify recall@k against a held-out query set.

Create the referenced resources/implementation-playbook.md (or fix the path) so the "open for detailed patterns" instruction resolves to a real file.

Dimension	Reasoning	Score
Conciseness	The body is lean but dominated by generic boilerplate ("Apply relevant best practices and validate outcomes") that adds little beyond what Claude knows, matching anchor 3; it is not a 2 (not padded/verbose) nor a 4 (the empty directives are more than minor over-explanation).	3 / 5
Actionability	No code, commands, or concrete patterns are given — only high-level hints like "Clarify goals, constraints, and required inputs", matching anchor 2; it is not a 1 (it names a file to open and specific use-cases) nor a 3 (no executable steps or examples).	2 / 5
Workflow Clarity	There is no sequenced multi-step process and no validation checkpoints; the flat generic directive list matches anchor 2 (steps poorly defined, validation absent); not a 1 (section structure exists) nor a 3 (no actual step sequence is listed).	2 / 5
Progressive Disclosure	Structure is minimal and the single reference ("resources/implementation-playbook.md") is dangling — no resources/ directory exists — so navigation fails, matching anchor 2 (minimal structure); not a 3 because the broken reference undermines the one-level-deep pattern rather than merely being unclear.	2 / 5
	Total	9 / 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.

The description clearly answers both what the skill does and when to use it, with concrete, natural trigger phrases and a distinct retrieval niche. Its main weakness is specificity and synonym coverage — only one action is named and common terms like "hybrid search" are missing.

Dimension	Reasoning	Score
Specificity	"Combine vector and keyword search for improved retrieval" names the domain and one concrete action (combining two search methods), matching anchor 3; it is not a 2 (the action is specific, not minimal) nor a 4 (only one action, not several).	3 / 5
Completeness	It explicitly states both what ("Combine vector and keyword search for improved retrieval") and when ("Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall") with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	"RAG systems", "search engines", and "vector and keyword search" are natural user phrases with good coverage, matching anchor 4; it is not a 5 because common synonyms like "hybrid search", "semantic search", or "BM25" are absent.	4 / 5
Distinctiveness Conflict Risk	The hybrid-retrieval niche is clearly distinct with specific triggers, matching anchor 4; it is not a 5 due to minor overlap with adjacent pure-vector or pure-keyword search skills.	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: rmyndharis/antigravity-skills
Path: skills/hybrid-search-implementation/SKILL.md
Commit: 3eff4af

Reviewed: 1 day 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.