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.

0.95x

Quality

Does it follow best practices?

Impact

84%

0.95x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./planned-skills/generated/08-ml-deployment/feature-store-connector/SKILL.md

Evaluation results

75%

-11%

Connecting a Churn Prediction Model to a Feature Store

Production-ready feature store integration

Criteria

Without context

With context

Step-by-step setup doc

100%

Setup doc covers materialisation

100%

Environment-based config

100%

30%

Error handling in client

40%

Production logging

Entity key usage

100%

Validate script exists

100%

Validate prints outcome

100%

All four features defined

100%

Feature store YAML present

100%

FastAPI endpoint returns prediction

100%

Without context: $0.9973 · 4m 22s · 48 turns · 52 in / 13,294 out tokens

With context: $0.7552 · 3m 18s · 39 turns · 40 in / 9,446 out tokens

82%

Batch Scoring Pipeline for Weekly Credit Risk Reports

MLOps pipeline feature retrieval

Criteria

Without context

With context

Numbered README steps

100%

Env var credentials

100%

CLI argument for IDs

100%

Feature store connection step

100%

Batch feature retrieval

100%

Error handling in pipeline

Logging not print

Unit tests with mocks

100%

Tests cover multiple IDs

100%

Output CSV written

100%

Requirements file present

100%

Without context: $0.6940 · 2m 56s · 30 turns · 31 in / 11,293 out tokens

With context: $0.9073 · 3m 32s · 41 turns · 73 in / 13,576 out tokens

97%

-1%

Hardening a Feature Store Connector Against Schema Drift

Feature store output validation

Criteria

Without context

With context

Numbered setup guide

100%

Schema config file

100%

Validation in retrieval

100%

Typed schema exception

80%

70%

Dtype mismatch detected

100%

Missing feature detected

100%

Env var auth

100%

Boto3 mocked in tests

100%

Test: success case

100%

Test: dtype mismatch case

100%

Test: missing feature case

100%

Without context: $0.8687 · 3m 22s · 38 turns · 39 in / 12,622 out tokens

With context: $0.6811 · 2m 32s · 33 turns · 31 in / 9,857 out tokens

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: f17dd51

Evaluated: 17 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Connecting a Churn Prediction Model to a Feature Store Batch Scoring Pipeline for Weekly Credit Risk Reports Hardening a Feature Store Connector Against Schema Drift

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.