feature-store-connector
Feature Store Connector - Auto-activating skill for ML Deployment. Triggers on: feature store connector, feature store connector Part of the ML Deployment skill category.
33
3%
Does it follow best practices?
Impact
84%
0.95xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./planned-skills/generated/08-ml-deployment/feature-store-connector/SKILL.mdQuality
Discovery
7%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 description is essentially a placeholder that names the skill but provides no substantive information about what it does or when to use it. It lacks concrete actions, meaningful trigger terms, and explicit usage guidance. The repeated trigger term and boilerplate structure suggest auto-generated content with no human refinement.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Connects to feature stores (Feast, Tecton, SageMaker Feature Store), retrieves feature vectors, registers new features, and manages feature serving endpoints.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user needs to retrieve features for model inference, register features, query a feature store, or integrate feature pipelines into ML deployment workflows.'
Include natural keyword variations users might say, such as 'feature retrieval', 'feature serving', 'online/offline features', 'Feast', 'feature pipeline', or specific feature store product names.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a domain ('Feature Store Connector') but describes no concrete actions. There are no verbs indicating what the skill actually does—no 'connects to', 'retrieves features from', 'syncs data', etc. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond naming itself, and the 'when' clause is just a redundant repetition of the skill name rather than explicit trigger guidance. Both what and when are very weak. | 1 / 3 |
Trigger Term Quality | The only trigger terms listed are 'feature store connector' repeated twice. There are no natural variations a user might say such as 'feature store', 'feature retrieval', 'feature serving', 'online features', or specific store names. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'feature store connector' is somewhat niche within ML, which provides some distinctiveness. However, the lack of specific actions or scope means it could overlap with other ML data pipeline or feature engineering skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an empty shell with no actionable content whatsoever. It reads as a boilerplate template where every section restates the skill name without providing any technical guidance, code examples, configuration patterns, or concrete instructions for connecting to feature stores. It would be entirely useless to Claude in performing any real task.
Suggestions
Add concrete, executable code examples showing how to connect to at least one feature store (e.g., Feast, Tecton, or SageMaker Feature Store) with actual Python code for reading/writing features.
Define a clear multi-step workflow for integrating a feature store into an ML serving pipeline, including validation steps (e.g., schema validation, feature freshness checks).
Replace the abstract 'Capabilities' and 'When to Use' sections with specific technical guidance—API patterns, configuration snippets, and common pitfalls.
Add references to detailed sub-documents for advanced topics (e.g., online vs. offline stores, feature versioning, monitoring feature drift) rather than keeping everything as vague bullet points.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler and meta-description. It explains what the skill does in abstract terms without providing any actual technical content. Every section restates the same vague idea—'feature store connector'—without adding substance. | 1 / 3 |
Actionability | There is zero concrete guidance—no code, no commands, no specific APIs, no configuration examples, no library references. The skill describes rather than instructs, offering only vague promises like 'provides step-by-step guidance' without actually delivering any. | 1 / 3 |
Workflow Clarity | No workflow, steps, or process is defined. There are no sequences, no validation checkpoints, and no error handling. The 'Capabilities' section claims step-by-step guidance but none is present. | 1 / 3 |
Progressive Disclosure | The content is a flat, monolithic block of placeholder text with no references to detailed materials, no links to related files, and no meaningful structural organization beyond generic headings. | 1 / 3 |
Total | 4 / 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 — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3076d78
- 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.