ab-testing-implementation
Implement and review MetaMask Mobile A/B tests using the canonical repository standard. Use for any task that adds or modifies A/B test flags, variant configs, useABTest usage, analytics payloads, or A/B-test-related tests and docs.
81
76%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/ab-testing-implementation/SKILL.mdQuality
Discovery
100%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 is a strong skill description that clearly defines its scope (MetaMask Mobile A/B testing), lists specific concrete actions and artifacts it covers, and provides explicit trigger guidance via a 'Use for' clause. The domain-specific terminology makes it highly distinctive and unlikely to conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: implementing A/B tests, reviewing them, adding/modifying A/B test flags, variant configs, useABTest usage, analytics payloads, and A/B-test-related tests and docs. | 3 / 3 |
Completeness | Clearly answers both 'what' (implement and review MetaMask Mobile A/B tests using canonical repository standard) and 'when' (explicit 'Use for any task that adds or modifies A/B test flags, variant configs, useABTest usage, analytics payloads, or A/B-test-related tests and docs'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'A/B test', 'A/B test flags', 'variant configs', 'useABTest', 'analytics payloads', 'MetaMask Mobile'. These cover both conceptual and code-level terms a developer would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped specifically to MetaMask Mobile A/B testing with domain-specific terms like 'useABTest', 'variant configs', and 'A/B test flags'. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
52%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is admirably concise and avoids over-explaining, but it delegates nearly all actionable content to an external document without providing any inline summary of the workflow, key steps, or examples. It functions more as a pointer than a skill. The compliance script is a good concrete artifact, but the lack of any workflow description or validation checkpoints in the skill itself significantly limits its standalone usefulness.
Suggestions
Add a brief inline summary (3-5 numbered steps) of the A/B testing workflow from docs/ab-testing.md so Claude has immediate context without needing to read the external file first.
Include at least one concrete example of a typical A/B test flag addition or useABTest usage pattern to make the skill actionable on its own.
Add explicit validation checkpoints (e.g., 'run compliance check before committing', 'verify analytics payload matches schema') to improve workflow clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean — no unnecessary explanation, no concept definitions Claude already knows. Every line serves a purpose: points to the SSOT doc, lists what to follow, and provides the compliance command. | 3 / 3 |
Actionability | The compliance check command is concrete and executable, but the actual workflow, analytics rules, testing policy, and required response sections are all delegated to an external doc with no inline examples or concrete guidance. Claude must read another file to know what to do. | 2 / 3 |
Workflow Clarity | No workflow steps are described in the skill itself — it simply says 'follow docs/ab-testing.md' without any sequencing, validation checkpoints, or error recovery. For a multi-step process (adding flags, configs, analytics, tests), this is insufficient. | 1 / 3 |
Progressive Disclosure | It correctly points to a single external SSOT document and a compliance script, which is good structure. However, it provides no overview or summary of what the workflow entails, making it hard to navigate without reading the external file. A brief inline summary of the key steps would improve discoverability. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- MetaMask/metamask-mobile
- Commit
bee9b14
- 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.