early-stopping-callback
Early Stopping Callback - Auto-activating skill for ML Training. Triggers on: early stopping callback, early stopping callback Part of the ML Training skill category.
36
3%
Does it follow best practices?
Impact
99%
1.01xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./planned-skills/generated/07-ml-training/early-stopping-callback/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 extremely thin—it essentially just names the skill and its category without describing any concrete capabilities or providing meaningful trigger guidance. The trigger terms are duplicated rather than varied, and there is no actionable 'Use when...' clause. It would be very difficult for Claude to confidently select this skill from a pool of ML-related skills.
Suggestions
Add specific actions the skill performs, e.g., 'Implements early stopping callbacks to monitor validation metrics and halt training when performance stops improving, preventing overfitting and saving compute resources.'
Add an explicit 'Use when...' clause with varied trigger scenarios, e.g., 'Use when the user wants to stop training early, prevent overfitting, set patience parameters, monitor validation loss during training, or implement EarlyStopping in Keras/PyTorch.'
Expand trigger terms to include natural variations users would say: 'stop training early', 'prevent overfitting', 'patience', 'validation loss plateau', 'EarlyStopping', 'training convergence'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the concept 'Early Stopping Callback' but does not describe any concrete actions. There are no verbs indicating what the skill actually does (e.g., 'implements', 'monitors validation loss', 'halts training when metrics plateau'). | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond naming the concept, and the 'when' clause is essentially just the skill name repeated. There is no explicit 'Use when...' guidance with meaningful trigger scenarios. | 1 / 3 |
Trigger Term Quality | The trigger terms are just 'early stopping callback' repeated twice, providing no variation. Missing natural terms users might say like 'stop training early', 'prevent overfitting', 'patience parameter', 'validation loss monitoring', or 'EarlyStopping'. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'early stopping callback' is fairly specific to a particular ML training concept, which provides some distinctiveness. However, the lack of detail about what it does versus other ML training skills means it could overlap with general ML training or callback-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 a hollow template with no actual technical content about early stopping callbacks. It contains only meta-descriptions of what the skill would do without providing any implementation details, code examples, or concrete guidance. It fails on every dimension because it teaches Claude nothing it doesn't already know.
Suggestions
Add concrete, executable code examples for early stopping in PyTorch, TensorFlow/Keras, and sklearn (e.g., `tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=5, restore_best_weights=True)`).
Include a clear workflow: 1) Choose metric to monitor, 2) Set patience and delta parameters, 3) Integrate callback into training loop, 4) Verify callback triggered correctly by checking training logs.
Replace the meta-description sections (Purpose, When to Use, Capabilities, Example Triggers) with actual technical content covering key parameters (patience, min_delta, baseline, restore_best_weights) and common pitfalls.
Add a concise comparison table or decision guide for when to use different patience values or monitoring metrics based on the training scenario.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler and meta-description. It explains what the skill does in abstract terms without providing any actual technical content, code, or specific guidance about early stopping callbacks. Every section restates the same vague information. | 1 / 3 |
Actionability | There is zero concrete, executable guidance. No code examples, no specific parameters (patience, monitor metric, restore_best_weights), no commands, no library-specific implementations. It only describes rather than instructs. | 1 / 3 |
Workflow Clarity | No workflow steps are provided at all. Early stopping involves configuring callbacks, setting monitoring metrics, choosing patience values, and integrating with training loops—none of which are addressed. | 1 / 3 |
Progressive Disclosure | The content has section headers but they contain no substantive information. There are no references to detailed files, no examples, and no structured navigation to deeper content. The sections are just boilerplate. | 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.