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.
36
Quality
3%
Does it follow best practices?
Impact
97%
1.02xAverage 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/tensorflow-savedmodel-creator/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 severely underdeveloped, essentially just restating the skill name without explaining capabilities or providing usage guidance. It lacks concrete actions, natural trigger terms, and explicit 'when to use' instructions. The redundant trigger terms and reliance on category labels instead of substantive description make it nearly useless for skill selection.
Suggestions
Add specific actions the skill performs, e.g., 'Converts TensorFlow/Keras models to SavedModel format, configures serving signatures, optimizes for deployment'
Include a 'Use when...' clause with natural trigger terms like 'export model', 'save tensorflow model', 'deploy keras model', 'serving signature', '.pb format'
Expand trigger terms to include variations users would naturally say: 'tf model export', 'model serialization', 'tensorflow serving', 'production model'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only names the tool 'Tensorflow Savedmodel Creator' without describing any concrete actions. There are no verbs or specific capabilities listed - it doesn't explain what creating a SavedModel involves or what operations are supported. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond the name, and 'when should Claude use it' is only implied through the category label 'ML Deployment'. There is no explicit 'Use when...' clause or trigger guidance. | 1 / 3 |
Trigger Term Quality | The trigger terms are redundant ('tensorflow savedmodel creator' listed twice) and overly specific. Missing natural variations users might say like 'save model', 'export tensorflow model', 'deploy tf model', '.pb files', or 'model serialization'. | 1 / 3 |
Distinctiveness Conflict Risk | The TensorFlow SavedModel focus is somewhat specific and wouldn't conflict with general document or code skills. However, it could overlap with other ML/model export skills due to lack of clear boundaries on when to use this vs other model serialization approaches. | 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 essentially a placeholder template with no substantive content. It describes what a TensorFlow SavedModel Creator skill would do but provides zero actual guidance, code examples, or actionable instructions for creating SavedModels. The entire content is meta-description about the skill rather than the skill itself.
Suggestions
Add executable Python code showing how to create a TensorFlow SavedModel (e.g., `tf.saved_model.save(model, 'path/to/saved_model')`)
Include a concrete workflow with steps: model preparation, signature definition, saving, and validation/testing the saved model
Provide specific examples of common SavedModel patterns (serving signatures, custom functions, preprocessing layers)
Remove all boilerplate meta-description and replace with actual technical content that teaches the task
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is padded with generic boilerplate that explains nothing specific about TensorFlow SavedModel creation. Phrases like 'provides automated assistance' and 'follows industry best practices' are filler that Claude already understands. | 1 / 3 |
Actionability | No concrete code, commands, or specific instructions are provided. The skill describes what it does abstractly ('provides step-by-step guidance') but never actually provides any guidance, examples, or executable content. | 1 / 3 |
Workflow Clarity | No workflow is defined. There are no steps, no sequence, and no validation checkpoints for creating TensorFlow SavedModels. The content only describes trigger phrases, not how to accomplish the task. | 1 / 3 |
Progressive Disclosure | The content is a monolithic block of meta-description with no actual technical content to organize. There are no references to detailed materials, examples, or related documentation. | 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
f17dd51
- 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.