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.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/recommendation-system/skills/recommendation-system/SKILL.md

Quality

Content

67%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 content is highly actionable with executable code and clear references, but suffers from redundancy across sections and inlines more detail than an overview SKILL.md should. Tightening repeated caching/monitoring examples and pushing deeper material into the existing reference files would improve it.

Suggestions

Consolidate the repeated caching and monitoring code (appearing in Quick Start, Core Components, Known Issues #2/#3/#5/#6, and Common Patterns) into a single authoritative example, referencing it elsewhere.

Move the detailed Known Issues Prevention solutions into the corresponding reference files, keeping only the problem statement and a pointer in SKILL.md.

Replace undefined stubs (fetch_from_db, generate_personalized_recs, get_candidates) with minimal working implementations or explicit notes that they are intentionally abstracted.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining basic concepts, but caching and monitoring logic is repeated across Quick Start, Core Components, multiple Known Issues, and Common Patterns, so it could be tightened noticeably by consolidating.	3 / 5
Actionability	Most code is concrete and copy-paste ready (Quick Start, TieredCache, sample-size calc), but a few examples rely on undefined stubs like fetch_from_db and generate_personalized_recs, leaving minor gaps.	4 / 5
Workflow Clarity	The 5-step Quick Start is clearly sequenced with a curl verification step, and Known Issues follow a consistent problem/solution pattern; minor validation gaps exist for the broader multi-step production workflow.	4 / 5
Progressive Disclosure	The 'When to Load References' section clearly signals four real, one-level-deep reference files each with a described purpose, but a large amount of detail (Known Issues, Common Patterns) is inlined in SKILL.md that could live in those references.	4 / 5
	Total	15 / 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 strong: it concisely states both the capability and explicit use-case triggers, with mostly natural trigger terms and a clear niche. The main weakness is that several trigger terms are technical rather than the phrasings a user would naturally say.

Suggestions

Add user-natural trigger phrases such as 'recommendations', 'recommender system', or 'what to show users' alongside the technical terms.

Consider including a file-format or surface trigger (e.g., 'recommendation API', '.py serving') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Deploy production recommendation systems with feature stores, caching, A/B testing'), matching the anchor that lists several specific actions with minor gaps rather than the fully comprehensive level 5.	4 / 5
Completeness	Explicitly 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') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage with natural phrases ('personalization APIs', 'low latency serving', 'cache invalidation', 'experiment tracking', 'quality monitoring'), but the terms lean technical and omit common user-level synonyms like 'recommendations' or 'recsys'.	4 / 5
Distinctiveness Conflict Risk	Clear niche (production recommendation systems) with distinct triggers and minimal conflict risk, though generic terms like 'caching' and 'A/B testing' create minor overlap with adjacent 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-system/skills/recommendation-system/SKILL.md
Commit: 84802a4

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.