bigquery-ml-model-creator
Bigquery Ml Model Creator - Auto-activating skill for GCP Skills. Triggers on: bigquery ml model creator, bigquery ml model creator Part of the GCP Skills skill category.
32
0%
Does it follow best practices?
Impact
89%
0.98xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./planned-skills/generated/14-gcp-skills/bigquery-ml-model-creator/SKILL.mdQuality
Discovery
0%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 placeholder that restates the skill name without providing any meaningful information about capabilities, use cases, or trigger conditions. It fails on all dimensions: no concrete actions, no natural trigger terms, no 'what/when' guidance, and no distinctiveness from other GCP or ML skills.
Suggestions
Add specific actions the skill performs, e.g., 'Creates and trains machine learning models in BigQuery using CREATE MODEL statements, evaluates model performance, and generates predictions on BigQuery datasets.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user wants to build ML models in BigQuery, mentions BQML, CREATE MODEL, training data in BigQuery, or needs predictions from BigQuery tables.'
Remove the duplicate trigger term and expand with natural variations users would say, such as 'BigQuery ML', 'BQML', 'train a model in BigQuery', 'ML predictions', 'BigQuery machine learning'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions. It only states the skill name 'Bigquery Ml Model Creator' and that it's 'auto-activating' as part of 'GCP Skills', but never describes what it actually does (e.g., create ML models, train models, evaluate predictions). | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is meaningfully answered. There is no 'Use when...' clause, and the description only restates the skill name without explaining capabilities or trigger conditions. | 1 / 3 |
Trigger Term Quality | The trigger terms are just the skill name repeated twice ('bigquery ml model creator, bigquery ml model creator'). There are no natural user keywords like 'machine learning', 'train model', 'BigQuery ML', 'BQML', 'CREATE MODEL', or 'predictions'. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it could overlap with any GCP or BigQuery-related skill. Without specifying what ML model creation entails or distinguishing it from other BigQuery or ML skills, conflict risk is high. | 1 / 3 |
Total | 4 / 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 an empty placeholder that provides no actual guidance on BigQuery ML model creation. It contains only auto-generated boilerplate sections with no executable code, no concrete steps, and no domain-specific knowledge. It would be entirely useless to Claude in performing any BigQuery ML task.
Suggestions
Add concrete BigQuery ML SQL examples such as CREATE MODEL statements with different model types (linear_reg, logistic_reg, kmeans, etc.) and their key OPTIONS.
Define a clear workflow: 1) Prepare training data query, 2) CREATE MODEL with appropriate options, 3) Evaluate with ML.EVALUATE, 4) Predict with ML.PREDICT, including validation checkpoints.
Remove all boilerplate sections (Example Triggers, When to Use, Capabilities) that provide no actionable information and replace with actual technical content.
Add concrete examples showing common patterns like feature engineering in the training query, model hyperparameter tuning, and model export to Vertex AI.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler with no substantive information. It explains what the skill does in abstract terms without providing any actual guidance, code, or concrete details about BigQuery ML model creation. | 1 / 3 |
Actionability | There is zero actionable content—no SQL examples, no BigQuery ML CREATE MODEL syntax, no concrete commands or configurations. Every section is vague and descriptive rather than instructive. | 1 / 3 |
Workflow Clarity | No workflow is defined at all. There are no steps, no sequence, and no validation checkpoints for creating BigQuery ML models, which is inherently a multi-step process (data prep, model creation, evaluation, prediction). | 1 / 3 |
Progressive Disclosure | The content is a flat, shallow placeholder with no meaningful structure. There are no references to detailed guides, no links to examples or API references, and the sections contain only boilerplate text. | 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
c8a915c
- 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.