tensorflow-savedmodel-creator

Tensorflow Savedmodel Creator - Auto-activating skill for ML Deployment. Triggers on: tensorflow savedmodel creator, tensorflow savedmodel creator Part of the ML Deployment skill category.

1.02x

Quality

Does it follow best practices?

Impact

97%

1.02x

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-savedmodel-creator/SKILL.md

Evaluation results

93%

Prepare a Fraud Detection Model for Production Serving

SavedModel export with serving signatures

Criteria

Without context

With context

SavedModel format used

100%

Explicit serving signature

80%

66%

Typed input spec (TensorSpec)

70%

80%

Named serving key

70%

100%

Variable batch size

100%

Post-save validation

100%

Step-by-step structure

100%

serving_notes.md present

100%

Without context: $0.4173 · 2m 17s · 21 turns · 21 in / 5,679 out tokens

With context: $0.6700 · 2m 52s · 35 turns · 293 in / 7,734 out tokens

100%

Audit a Model Export Pipeline for Deployment Readiness

SavedModel validation and directory structure

Criteria

Without context

With context

SavedModel format

100%

saved_model.pb check

100%

variables/ subdirectory check

100%

Reloadability test

100%

Serving signature check

100%

Serving signature defined on export

50%

100%

Structured validation output

100%

Checklist covers format

100%

Checklist covers signatures

100%

Step-by-step guidance

100%

Without context: $0.5944 · 3m 28s · 23 turns · 23 in / 10,592 out tokens

With context: $0.7015 · 3m 18s · 31 turns · 64 in / 10,310 out tokens

98%

-1%

Design an MLOps Deployment Pipeline for a Computer Vision Model

MLOps deployment pipeline with monitoring

Criteria

Without context

With context

SavedModel export step

100%

Serving signature in export

90%

80%

Model versioning addressed

100%

TF Serving configuration

100%

Monitoring plan present

100%

monitoring_config.json has 4+ targets

100%

Production optimization applied

100%

TFLite path for edge

100%

Step-by-step pipeline structure

100%

Success criteria per stage

100%

Production-readiness signals

100%

Without context: $0.5502 · 3m 8s · 19 turns · 19 in / 11,739 out tokens

With context: $1.1289 · 5m 5s · 41 turns · 488 in / 16,120 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

Prepare a Fraud Detection Model for Production Serving Audit a Model Export Pipeline for Deployment Readiness Design an MLOps Deployment Pipeline for a Computer Vision Model

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.