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
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 essentially a title and category label with no substantive content. It lacks concrete actions, meaningful trigger terms, and explicit guidance on when to use the skill. It would be nearly impossible for Claude to reliably select this skill from a pool of ML-related skills based on this description alone.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Exports TensorFlow models to SavedModel format, configures serving signatures, converts checkpoints to deployable artifacts.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user needs to export a TensorFlow model, create a SavedModel, prepare a model for TF Serving, or convert a .h5/checkpoint to .pb format.'
Replace the duplicated trigger term with diverse natural keywords users might say, such as 'export model', 'tf.saved_model', 'serving signature', 'deploy tensorflow model', '.pb file'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain ('ML Deployment') and mentions 'TensorFlow SavedModel Creator' but does not describe any concrete actions. There are no verbs describing what the skill actually does (e.g., 'exports models', 'converts checkpoints', 'serializes graphs'). | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no explanation of capabilities and no explicit 'Use when...' clause with meaningful trigger guidance. | 1 / 3 |
Trigger Term Quality | The trigger terms are just the skill name repeated twice ('tensorflow savedmodel creator'). There are no natural user keywords like 'export model', 'save tensorflow model', 'savedmodel format', '.pb files', 'serving', or 'deploy tensorflow'. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'TensorFlow SavedModel' is fairly specific to a particular framework and format, which provides some distinctiveness. However, the vague 'ML Deployment' category and lack of concrete actions could cause overlap with other ML-related 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 entirely auto-generated boilerplate with no actual technical content. It contains no code examples, no concrete instructions, no workflow steps, and no real guidance on creating TensorFlow SavedModels. Every section is generic filler that could apply to any skill by swapping the name.
Suggestions
Add executable Python code showing how to create and export a TensorFlow SavedModel (e.g., tf.saved_model.save(model, 'path/to/saved_model'))
Define a clear workflow: 1) Build/load model, 2) Define serving signatures, 3) Export SavedModel, 4) Validate with saved_model_cli, 5) Test inference
Include concrete examples of serving signatures, input/output specs, and validation commands (e.g., `saved_model_cli show --dir ./saved_model --all`)
Remove all generic boilerplate sections (Purpose, When to Use, Example Triggers) and replace with actionable technical content specific to SavedModel creation
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler and boilerplate. It explains nothing Claude doesn't already know, repeats the skill name excessively, and provides zero technical substance about TensorFlow SavedModel creation. | 1 / 3 |
Actionability | There is no concrete code, no commands, no executable guidance whatsoever. The content only describes what the skill supposedly does in vague, abstract terms without any actual instructions on how to create a TensorFlow SavedModel. | 1 / 3 |
Workflow Clarity | No workflow steps are defined. Claims to provide 'step-by-step guidance' but includes zero actual steps. There are no validation checkpoints, no sequencing, and no process description. | 1 / 3 |
Progressive Disclosure | The content is a monolithic block of generic placeholder text with no references to detailed materials, no links to examples or API references, and no meaningful structural organization beyond boilerplate 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.