tensorflow-serving-setup

Tensorflow Serving Setup - Auto-activating skill for ML Deployment. Triggers on: tensorflow serving setup, tensorflow serving setup Part of the ML Deployment skill category.

1.01x

Quality

11%

Does it follow best practices?

Impact

97%

1.01x

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/tensorflow-serving-setup/SKILL.md

Evaluation results

93%

Deploy a Trained Keras Model for Production Inference

SavedModel export and Docker serving setup

Criteria

Without context

With context

SavedModel format

100%

Versioned subdirectory

100%

Official TF Serving image

100%

REST port 8501

100%

gRPC port 8500

100%

Restart policy

100%

Volume mount for models

100%

Step-by-step README

100%

REST prediction example

100%

Validation step present

14%

50%

Without context: $0.3103 · 1m 18s · 20 turns · 20 in / 4,389 out tokens

With context: $0.4130 · 1m 42s · 25 turns · 25 in / 4,751 out tokens

100%

Set Up a Shared TF Serving Instance for Multiple Production Models

Multi-model configuration with version policies

Criteria

Without context

With context

model_config_list format

100%

Both models registered

100%

Latest-only version policy

100%

Multi-version policy

100%

--model_config_file flag

100%

SavedModel stub creation

100%

Config file volume mount

100%

REST port 8501 exposed

100%

Per-model REST examples

100%

Step-by-step instructions

100%

Without context: $0.3963 · 1m 31s · 23 turns · 24 in / 5,241 out tokens

With context: $0.4387 · 1m 35s · 28 turns · 315 in / 5,262 out tokens

100%

Add Observability and Throughput Optimization to a TF Serving Deployment

Production monitoring and batching configuration

Criteria

Without context

With context

monitoring.config file

100%

--monitoring_config_file flag

100%

Prometheus endpoint documented

100%

Key metrics listed

100%

batching.config file

100%

--enable_batching flag

100%

--batching_parameters_file flag

100%

Config files volume-mounted

100%

Batching tuning guidance

100%

Ports preserved

100%

Step-by-step structure

100%

Without context: $0.2399 · 1m 1s · 15 turns · 16 in / 3,126 out tokens

With context: $0.4984 · 1m 44s · 30 turns · 28 in / 6,041 out tokens

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

Evaluated: 18 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Deploy a Trained Keras Model for Production Inference Set Up a Shared TF Serving Instance for Multiple Production Models Add Observability and Throughput Optimization to a TF Serving Deployment

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.