a-b-test-config-creator
A B Test Config Creator - Auto-activating skill for ML Deployment. Triggers on: a b test config creator, a b test config creator Part of the ML Deployment skill category.
36
Quality
3%
Does it follow best practices?
Impact
100%
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/a-b-test-config-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 placeholder that provides almost no useful information for skill selection. It only states the skill name and category without explaining what actions it performs, what inputs it accepts, or when Claude should choose it. The trigger terms are redundant repetitions of the skill name rather than natural user language.
Suggestions
Add specific actions the skill performs, e.g., 'Creates A/B test configuration files with variant definitions, traffic allocation percentages, and success metrics for ML model deployments.'
Include a 'Use when...' clause with natural trigger terms like 'A/B test', 'split test', 'experiment setup', 'traffic splitting', 'model comparison', or 'canary deployment'.
Specify the output format or integration context, e.g., 'Generates YAML/JSON configs compatible with ML deployment pipelines' to distinguish from other experimentation tools.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only names the skill ('A B Test Config Creator') without describing any concrete actions. There are no verbs explaining what the skill actually does - no mention of creating configs, defining variants, setting traffic splits, or any other specific capabilities. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond the name, and provides no 'when should Claude use it' guidance. The 'Triggers on' section just repeats the skill name rather than providing meaningful trigger scenarios. | 1 / 3 |
Trigger Term Quality | The trigger terms listed are just the skill name repeated twice ('a b test config creator'). Missing natural user phrases like 'A/B test', 'split test', 'experiment config', 'feature flag', 'traffic allocation', or 'variant testing'. | 1 / 3 |
Distinctiveness Conflict Risk | The skill name 'A B Test Config Creator' provides some specificity to the A/B testing domain, but without describing actual capabilities, it could overlap with other ML/experimentation skills. The 'ML Deployment' category helps somewhat with context. | 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 with no actionable content. It describes what an A/B test config creator skill would do in vague marketing language but provides zero actual guidance, code examples, configuration schemas, or workflows. The content fails every dimension of the rubric by being simultaneously verbose and empty of useful information.
Suggestions
Add concrete A/B test configuration examples with actual JSON/YAML schemas showing traffic splits, variant definitions, and metric configurations
Provide executable code snippets for creating and validating A/B test configs in common ML serving frameworks (e.g., KServe, Seldon, or cloud-specific tools)
Define a clear workflow: 1) Define variants 2) Configure traffic split 3) Set success metrics 4) Validate config 5) Deploy with rollback plan
Remove all generic boilerplate ('provides automated assistance', 'follows best practices') and replace with specific, actionable instructions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is padded with generic boilerplate that explains nothing Claude doesn't already know. Phrases like 'provides automated assistance' and 'follows industry best practices' are meaningless filler with no actual information. | 1 / 3 |
Actionability | There is zero concrete guidance - no code, no commands, no specific steps, no configuration examples. The skill describes what it does in abstract terms but never shows how to actually create an A/B test config. | 1 / 3 |
Workflow Clarity | No workflow is defined whatsoever. For a config creator skill, there should be clear steps for creating, validating, and deploying A/B test configurations, but none are provided. | 1 / 3 |
Progressive Disclosure | The content is a flat, uninformative structure with no useful organization. There are no references to detailed materials, examples, or schemas that would help with actual implementation. | 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.