Name: redis-search
Rating: 74.4 (1 reviews)
Author: redis

redis-search

Redis Search guidance covering FT.CREATE schema design, field type selection (TEXT, TAG, NUMERIC, GEO, GEOSHAPE, VECTOR, JSON path), DIALECT 2 query syntax, FT.SEARCH / FT.AGGREGATE / FT.HYBRID command selection, vector similarity with HNSW or FLAT, hybrid retrieval combining lexical and vector ranking, RAG pipelines, zero-downtime index updates via aliases, and debugging with FT.PROFILE and FT.EXPLAIN. Use when defining a search index on Hash or JSON documents, writing FT.SEARCH queries with filters, sorting, aggregation, or vector KNN, tuning HNSW parameters, building a RAG retrieval pipeline, or troubleshooting slow or empty search results.

Quality

93%

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

Quality

Content

86%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.

A tightly written, highly actionable reference skill with excellent progressive disclosure: a lean overview pointing to a rich, verified bundle of one-level-deep reference files. The only meaningful gap is the absence of explicit validation checkpoints in the operational/destructive index-management workflows.

Suggestions

Add an explicit validation step to the zero-downtime index-update workflow (e.g. verify FT.INFO on the new index and run a sample FT.SEARCH before FT.ALIASUPDATE) to convert the alias-swap pattern into a checkpointed feedback loop.

In the Operations section, note a verify/rollback action after FT.DROPINDEX or FT.ALIASUPDATE so destructive index changes carry an explicit checkpoint.

Tighten the few inline explanatory asides (e.g. the 'classic mistake' note) into the field-types reference to push conciseness toward a fully lean overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no preamble on what Redis/vectors/RAG are), with every code block and table earning its place; a few inline explanatory sentences ('The classic mistake is TEXT for a category...') and inline version gates keep it just shy of the fully lean 5 anchor.	4 / 5
Actionability	Multiple copy-paste-ready Redis commands (FT.CREATE, FT.SEARCH, FT.AGGREGATE, FT.HYBRID, KNN vector queries) plus decision tables for command/field-type/algorithm selection cover the common cases with executable guidance.	5 / 5
Workflow Clarity	Decision workflows (command selection, field-type choice, hybrid retrieval patterns) are clearly sequenced and the debugging section supplies a feedback loop via FT.PROFILE/FT.EXPLAIN, but the destructive index operations (FT.DROPINDEX, zero-downtime alias swap) lack explicit validate-before-proceed checkpoints.	4 / 5
Progressive Disclosure	SKILL.md is a well-signaled overview with one-level-deep references to 19 topic files plus 3 client files, all verified to exist in ./references/, each linked inline at the relevant section and supplemented by an external-links References block — easy to navigate.	5 / 5
	Total	18 / 20 Passed

Description

100%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.

An excellent description that explicitly states both capabilities and concrete trigger conditions using third-person voice, with comprehensive natural keywords and a clear Redis-Search-specific niche. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'FT.CREATE schema design, field type selection (TEXT, TAG, NUMERIC, GEO, GEOSHAPE, VECTOR, JSON path)', 'DIALECT 2 query syntax', 'vector similarity with HNSW or FLAT', 'zero-downtime index updates via aliases', 'debugging with FT.PROFILE and FT.EXPLAIN' — giving comprehensive coverage rather than the 'minor gaps' that define a 4.	5 / 5
Completeness	Both 'what' (the full capability catalog in the first sentence) and 'when' (an explicit, concrete 'Use when...' clause with multiple trigger scenarios) are clearly and explicitly answered with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Natural trigger phrases a user would actually say are present throughout the 'Use when' clause: 'defining a search index on Hash or JSON documents', 'writing FT.SEARCH queries with filters, sorting, aggregation, or vector KNN', 'tuning HNSW parameters', 'building a RAG retrieval pipeline', 'troubleshooting slow or empty search results'.	5 / 5
Distinctiveness Conflict Risk	Redis-specific command names (FT.CREATE, FT.SEARCH, FT.AGGREGATE, FT.HYBRID, HNSW/FLAT) carve a clear niche with minimal conflict risk against other skills; it would not trigger for the wrong skill.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 6 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: redis/agent-skills
Path: skills/redis-search/SKILL.md
Commit: 172fb9e

Reviewed: 4 days 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.