ab-tasty
A/B Tasty integration. Manage data, records, and automate workflows. Use when the user wants to interact with A/B Tasty data.
68
61%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/ab-tasty/SKILL.mdQuality
Discovery
57%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description benefits from naming the specific product (A/B Tasty) and including an explicit 'Use when' clause, but it is severely lacking in specificity of capabilities. The actions described are boilerplate integration language that could apply to any SaaS tool, providing no insight into what A/B Tasty-specific operations are supported.
Suggestions
Replace generic phrases like 'manage data, records, and automate workflows' with specific A/B Tasty actions such as 'create and manage experiments, configure variations, analyze test results, manage feature flags'.
Add natural trigger term variations users might say, such as 'AB Tasty', 'A/B testing', 'split testing', 'experiments', 'feature flags', 'variations'.
Expand the 'Use when' clause with more specific scenarios, e.g., 'Use when the user mentions A/B Tasty, AB Tasty, or wants to manage A/B testing experiments, variations, or feature flags.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'manage data, records, and automate workflows' without listing any concrete actions specific to A/B Tasty. These are generic phrases that could apply to almost any integration. | 1 / 3 |
Completeness | It does answer both 'what' (manage data, records, automate workflows) and 'when' (when the user wants to interact with A/B Tasty data) with an explicit 'Use when' clause, even though both parts are vague in substance. | 3 / 3 |
Trigger Term Quality | It includes 'A/B Tasty' as a key trigger term which is specific to the product, but lacks natural variations users might say (e.g., 'AB Tasty', 'A/B testing', 'experiments', 'feature flags', 'variations', 'campaigns') and doesn't mention specific A/B Tasty concepts. | 2 / 3 |
Distinctiveness Conflict Risk | The 'A/B Tasty' product name provides some distinctiveness, but 'manage data, records, and automate workflows' is so generic it could overlap with dozens of other integration skills. It could also conflict with other A/B testing tools. | 2 / 3 |
Total | 8 / 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.
The skill provides solid, actionable CLI commands for integrating with A/B Tasty via Membrane, with good coverage of the full workflow from installation to running actions. Its main weaknesses are unnecessary introductory content explaining what A/B Tasty is, a shallow overview section that adds no value, and missing explicit validation/error-recovery steps in the workflow.
Suggestions
Remove or drastically shorten the opening paragraph explaining what A/B Tasty is — Claude already knows this. Start directly with the CLI workflow.
Either flesh out the Overview section (Campaign, Variation, etc.) with actionable details about how they map to Membrane actions, or remove it entirely.
Add explicit validation checkpoints, e.g., verify connection status after `membrane connect`, and include error recovery guidance (what to do if authentication fails or connection drops).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The opening paragraph explaining what A/B Tasty is (experimentation, personalization, A/B tests, etc.) is unnecessary context Claude already knows. The overview section listing Campaign/Variation/Account/User/Test adds little value without explanation. However, the CLI commands and workflow sections are reasonably efficient. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste-ready CLI commands for every step: installation, authentication, connecting, searching actions, creating actions, and running actions with parameters. Each command includes concrete flags and placeholders. | 3 / 3 |
Workflow Clarity | The workflow follows a logical sequence (install → authenticate → connect → discover → create/run), and the action creation section includes a polling loop with state checking. However, there are no explicit validation checkpoints or error recovery steps for the overall workflow — e.g., no guidance on what to do if connection fails, or how to verify a connection is active before running actions. | 2 / 3 |
Progressive Disclosure | The content is reasonably structured with clear headers, but it's somewhat monolithic — all content is inline in a single file. The overview section (Campaign/Variation/Account/User/Test) is underdeveloped and doesn't link to anything. The external docs link is provided but there's no structured navigation to deeper reference material. | 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 | |
- Repository
- membranedev/application-skills
- Commit
56d7336
- 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.