ab-tasty
A/B Tasty integration. Manage data, records, and automate workflows. Use when the user wants to interact with A/B Tasty data.
Install with Tessl CLI
npx tessl i github:membranedev/application-skills --skill ab-tasty72
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
67%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 follows a good structure with explicit 'Use when' guidance, but suffers from generic, template-like language that doesn't convey A/B Tasty's specific capabilities (experiments, variations, targeting, feature flags). The actions described could apply to virtually any integration, reducing its usefulness for skill selection among many similar integrations.
Suggestions
Replace generic actions with A/B Tasty-specific capabilities like 'create and manage A/B tests, configure experiment variations, set up targeting rules, manage feature flags'
Add natural trigger terms users would say: 'A/B testing', 'experiments', 'variations', 'feature flags', 'split testing'
Make the 'Use when' clause more specific: 'Use when the user mentions A/B Tasty, A/B testing experiments, or wants to manage website variations and feature flags'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (A/B Tasty) and mentions general actions ('Manage data, records, and automate workflows'), but these actions are generic and not specific to A/B Tasty's actual capabilities like managing experiments, variations, or feature flags. | 2 / 3 |
Completeness | Explicitly answers both what ('Manage data, records, and automate workflows') and when ('Use when the user wants to interact with A/B Tasty data') with a clear trigger clause. | 3 / 3 |
Trigger Term Quality | Includes 'A/B Tasty' as a trigger term which users would say, but lacks natural variations like 'AB Tasty', 'A/B testing', 'experiments', 'feature flags', or 'variations' that users might commonly use. | 2 / 3 |
Distinctiveness Conflict Risk | The 'A/B Tasty' brand name provides some distinctiveness, but 'Manage data, records, and automate workflows' is extremely generic and could overlap with dozens of other integration skills using similar boilerplate language. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid, actionable CLI commands for A/B Tasty integration via Membrane, with good coverage of setup, connection, and action execution. However, it includes unnecessary introductory content about what A/B Tasty is, lacks validation checkpoints in workflows, and the 'Popular actions' section is misleadingly named since it only shows how to discover actions rather than listing common ones.
Suggestions
Remove the introductory paragraph explaining what A/B Tasty is - Claude already knows this and it wastes tokens
Add validation steps after key operations (e.g., 'Verify connection succeeded by running membrane connection list --json and confirming the new connectionId appears')
Either populate 'Popular actions' with actual common action IDs and their purposes, or rename the section to 'Discovering and running actions'
Remove or condense the empty 'A/B Tasty Overview' bullet list which provides no actionable information
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanation (e.g., 'A/B Tasty is a platform for experimentation and personalization...') that Claude already knows. The overview section with bullet points adds little value. However, the CLI commands and examples are reasonably efficient. | 2 / 3 |
Actionability | Provides fully executable CLI commands throughout with clear syntax. Commands are copy-paste ready with proper flags and JSON parameter examples. The proxy request section includes a helpful options table. | 3 / 3 |
Workflow Clarity | Steps are listed for setup and connection but lack explicit validation checkpoints. The workflow doesn't specify how to verify a connection succeeded or what to do if commands fail. Missing feedback loops for error recovery. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but everything is inline in one file. The 'Popular actions' section is oddly empty except for discovery commands. Could benefit from linking to external references for advanced proxy usage or troubleshooting. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- 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.