recommendation-system
Deploy production recommendation systems with feature stores, caching, A/B testing. Use for personalization APIs, low latency serving, or encountering cache invalidation, experiment tracking, quality monitoring issues.
Install with Tessl CLI
npx tessl i github:secondsky/claude-skills --skill recommendation-system91
Does it follow best practices?
Validation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its scope around production recommendation system deployment. It effectively combines the 'what' (deploying recommendation systems with specific infrastructure components) with explicit 'when' triggers covering both proactive use cases and problem scenarios. The technical terminology is appropriately specific without being obscure jargon.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Deploy production recommendation systems with feature stores, caching, A/B testing' clearly names the domain and specific technical components involved. | 3 / 3 |
Completeness | Clearly answers both what ('Deploy production recommendation systems with feature stores, caching, A/B testing') and when ('Use for personalization APIs, low latency serving, or encountering cache invalidation, experiment tracking, quality monitoring issues'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'recommendation systems', 'feature stores', 'caching', 'A/B testing', 'personalization APIs', 'low latency serving', 'cache invalidation', 'experiment tracking', 'quality monitoring'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific niche combining recommendation systems with production deployment concerns (feature stores, A/B testing, cache invalidation); unlikely to conflict with general ML or generic deployment skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, production-focused skill with excellent actionability and clear workflows. The code examples are executable and address real-world concerns like cold start, cache invalidation, and A/B testing. Minor verbosity in the 'When to Use' section and some pattern repetition prevent a perfect conciseness score, but overall this skill provides substantial value for building recommendation systems.
Suggestions
Remove or condense the 'When to Use This Skill' section since it largely duplicates information already in the skill description metadata
Consider moving the Common Patterns section content into the Core Components section to reduce repetition of similar concepts
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy - the 'When to Use This Skill' section largely duplicates the description, and some patterns (like RecommendationService) repeat concepts already shown. The architecture diagram and tables add value but the overall length (~400 lines) could be tightened. | 2 / 3 |
Actionability | Excellent executable code throughout - the Quick Start provides copy-paste ready bash commands and Python code, all code examples are complete and runnable, and specific solutions are provided for each known issue with concrete implementations. | 3 / 3 |
Workflow Clarity | The Quick Start has clear numbered steps, the RecommendationService pattern shows explicit sequencing (1. Check cache, 2. Get features, etc.), and the Known Issues section provides clear problem-solution pairs with validation approaches like cache invalidation triggers and monitoring alerts. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from Quick Start to Architecture to Components to Known Issues. The 'When to Load References' section provides clear one-level-deep pointers to detailed reference files with specific use cases for each. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 13 / 16 Passed | |
- Reviewed
Table of Contents
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.