Name: redis-semantic-cache
Rating: 70.39999999999999 (1 reviews)
Author: redis

redis-semantic-cache

Redis LangCache guidance for semantic caching of LLM responses on Redis Cloud — calling search/set via the SDK or REST API, tuning the similarity threshold, separating caches per task type, and filtering with custom attributes. Use when caching LLM completions or RAG answers to cut API cost and latency, building a cache-aside layer in front of OpenAI / Anthropic / etc., tuning hit rate vs precision, or splitting one app's LLM workloads into multiple LangCache caches.

Quality

85%

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

78%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 well-structured, actionable skill body with clean code examples and excellent progressive disclosure via two real reference files. Small improvements are available in tightening redundant explanation and replacing placeholder/ellipsis code with complete executable snippets.

Suggestions

Trim the opening 'Stores prompts as embeddings...' sentence and the 'When to apply' list, since the description already covers the trigger conditions — keep the body focused on how-to detail Claude doesn't already have.

Replace the `llm.generate(...)` placeholder and `server_url=...`/`api_key=...` ellipses with a concrete, copy-paste-ready pattern (e.g., a minimal OpenAI call) so the cache-aside example is fully executable end-to-end.

Make the threshold-tuning feedback loop explicit as a validate→adjust step (e.g., 'check hit rate and relevance, then raise/lower threshold by 0.05 and re-measure') to strengthen the workflow checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and product-scoped, but the opening explanation of how semantic caching works and the 'When to apply' list (which overlaps the description's Use-when clause) are minor over-explanation that could be trimmed, fitting the 4 anchor better than 5.	4 / 5
Actionability	Provides executable cache-aside Python code, named REST endpoints, and a threshold tuning table, but uses a `llm.generate` placeholder and `server_url=...` ellipses that leave minor gaps, matching the 4 anchor rather than fully copy-paste-ready 5.	4 / 5
Workflow Clarity	The cache-aside flow is a clear numbered sequence with a spot-checking feedback note for threshold tuning, but the validation checkpoint is implicit rather than a structured validate-fix-retry loop, fitting the 4 anchor; the operation is not destructive/batch so the 3-cap does not apply.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview pointing to two one-level-deep, clearly signaled references (langcache-usage.md and best-practices.md) that exist as real files with the detailed content, matching the 5 anchor for clear navigation and appropriate content split.	5 / 5
	Total	17 / 20 Passed

Description

92%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, specific description that clearly communicates both capabilities and trigger conditions with concrete actions and natural phrasing. The only minor gap is trigger-term synonym coverage, which is good but not exhaustive.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'calling search/set via the SDK or REST API, tuning the similarity threshold, separating caches per task type, and filtering with custom attributes' — giving comprehensive coverage of the skill's capabilities, matching the 5 anchor rather than 4 (no meaningful gaps).	5 / 5
Completeness	Explicitly states what it does (semantic caching of LLM responses on Redis Cloud with specific operations) and gives a concrete 'Use when...' clause with multiple trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Natural phrases users would say appear ('caching LLM completions or RAG answers', 'cut API cost and latency', 'cache-aside layer', 'hit rate vs precision') but coverage stops short of exhaustive synonyms, fitting the 4 anchor better than 5.	4 / 5
Distinctiveness Conflict Risk	'Redis LangCache' and 'semantic caching of LLM responses on Redis Cloud' carve a clear niche with distinct triggers and minimal overlap with other skills, matching the 5 anchor.	5 / 5
	Total	19 / 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: redis/agent-skills
Path: skills/redis-semantic-cache/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.