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.

Quality

71%

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 ./plugins/recommendation-engine/skills/recommendation-engine/SKILL.md

Quality

Content

60%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 well-structured with a clear quick-start workflow and properly signaled reference files, but it is padded with explanatory problem statements and contains code examples with internal inconsistencies and imports of non-existent modules that reduce executability.

Suggestions

Fix the inline code inconsistencies: set self.user_item_matrix in CollaborativeFilter.fit, add a score() method or align Hybrid.recommend to use recommend_for_user, and define or stub ContentBasedFilter.

Resolve the Quick Start imports: either point them at the actual reference file modules (e.g. from references.collaborative_filtering import ...) or note that these are illustrative package names to be created.

Trim the "Problem" exposition in each Known Issues section to one line, keeping the "Solution" code, to reduce tokens spent on concepts Claude already knows.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-oriented content, but the seven "Known Issues Prevention" sections each open with a "Problem" paragraph explaining concepts Claude already knows (e.g. popularity bias, filter bubbles) that could be trimmed.	3 / 5
Actionability	Substantial concrete code, but several examples are not directly executable: CollaborativeFilter.recommend_for_user references an unset self.user_item_matrix, Hybrid calls a non-existent self.collab.score, and the Quick Start imports modules (recommendation_engine, evaluation_metrics) that are not provided.	3 / 5
Workflow Clarity	The numbered "Build a Recommender in 5 Steps" Quick Start gives a clear prepare-train-recommend-evaluate-cold-start sequence with the evaluation step acting as a checkpoint; minor feedback-loop gap (no retrain-if-poor path).	4 / 5
Progressive Disclosure	Good structure with a dedicated "When to Load References" section mapping four real one-level-deep reference files (all present in ./references/); a fair amount of detailed known-issues content is inlined rather than split out.	4 / 5
	Total	14 / 20 Passed

Description

83%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 is specific, uses third person, and cleanly answers both what the skill does and when to invoke it with concrete trigger phrases. Trigger-term coverage is strong though a few natural synonyms are absent.

Dimension	Reasoning	Score
Specificity	Names concrete approaches ("collaborative filtering, matrix factorization, hybrid approaches") under the action "Build recommendation systems", listing several specific techniques with only minor coverage gaps.	4 / 5
Completeness	Explicitly 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 concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user-facing terms ("product recommendations, personalization, cold start, sparsity, quality evaluation") with good coverage, though a few synonyms (e.g. "recommender system") are missing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear, specialized niche (recommendation engines with named CF/MF techniques) with distinct triggers, with only minor overlap risk against general ML skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: secondsky/claude-skills
Path: plugins/recommendation-engine/skills/recommendation-engine/SKILL.md
Commit: 84802a4

Reviewed: 3 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.