recommendation-engine
Build recommendation systems with collaborative filtering, matrix factorization, hybrid approaches. Use for product recommendations, personalization, or encountering cold start, sparsity, quality evaluation issues.
Install with Tessl CLI
npx tessl i github:secondsky/claude-skills --skill recommendation-engine86
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
85%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 description that clearly defines the skill's capabilities and when to use it. It excels at specificity and completeness with explicit 'Use for...' guidance. The main weakness is trigger term quality, which leans toward technical jargon that developers would use but may miss more casual user language for recommendation needs.
Suggestions
Add more natural user-facing trigger terms like 'suggest products', 'similar items', 'what to recommend', or 'personalized suggestions' alongside the technical terminology
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'collaborative filtering, matrix factorization, hybrid approaches' and specific use cases like 'product recommendations, personalization' plus technical challenges like 'cold start, sparsity, quality evaluation issues'. | 3 / 3 |
Completeness | Clearly answers both what ('Build recommendation systems with collaborative filtering, matrix factorization, hybrid approaches') and when ('Use for product recommendations, personalization, or encountering cold start, sparsity, quality evaluation issues') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'recommendation systems', 'product recommendations', 'personalization', but uses more technical jargon ('matrix factorization', 'cold start', 'sparsity') that users may not naturally say. Missing common variations like 'suggest products', 'what should I buy', 'similar items'. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on recommendation systems with distinct technical approaches and problem domains. Unlikely to conflict with general ML skills or other data processing skills due to specific terminology like 'collaborative filtering' and 'cold start'. | 3 / 3 |
Total | 11 / 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 skill with excellent actionability through complete, executable code examples and good progressive disclosure with clear reference file navigation. The workflow clarity is solid with explicit steps and fallback patterns. Minor verbosity in the comparison table and some redundancy between sections slightly reduces token efficiency.
Suggestions
Remove or condense the comparison table at the top - Claude understands these tradeoffs and the information is better demonstrated through the code examples that follow.
Consider consolidating the 'Quick Start' section with the earlier class implementations to reduce redundancy while maintaining the step-by-step guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good code examples, but includes some unnecessary elements like the comparison table that Claude already understands, and the 'Quick Start' section partially duplicates concepts shown in earlier code blocks. | 2 / 3 |
Actionability | Provides fully executable Python code throughout with concrete implementations for collaborative filtering, matrix factorization, hybrid recommenders, and known issues prevention. Code is copy-paste ready with clear imports and complete class definitions. | 3 / 3 |
Workflow Clarity | The 'Quick Start: Build a Recommender in 5 Steps' section provides clear sequencing with numbered steps. The 'Known Issues Prevention' section includes explicit validation patterns and fallback chains with error handling, demonstrating good feedback loops. | 3 / 3 |
Progressive Disclosure | Excellent structure with clear overview sections, detailed inline examples for common cases, and well-signaled one-level-deep references at the end ('When to Load References') pointing to specific files for deeper dives on each topic. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 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 |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 12 / 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.