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 with 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' ('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', '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 'analytics payloads'. 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 extremely concise and correctly delegates to a single source of truth, but it delegates almost everything — leaving the SKILL.md body as little more than a pointer with a compliance command. The lack of any inline workflow steps, concrete implementation examples, or validation checkpoints means Claude must fully rely on the referenced document, which cannot be verified from the bundle. The skill would benefit from at minimum a brief workflow summary and a concrete code example.
Suggestions
Add a brief inline workflow summary (3-5 numbered steps) covering the key phases of A/B test implementation so Claude has actionable guidance even before reading docs/ab-testing.md.
Include at least one concrete code example showing canonical useABTest usage or variant config structure to make the skill immediately actionable.
Add a validation/feedback loop step (e.g., 'Run compliance check → if failures, fix flagged issues → re-run') to provide explicit error recovery guidance for this multi-step process.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean — no unnecessary explanation, no concept definitions Claude already knows. Every line serves a purpose: pointing to the SSOT doc, listing what to follow, and providing the compliance command. | 3 / 3 |
Actionability | The skill provides one concrete executable command (the compliance check script), but all actual workflow steps, analytics rules, and testing policy are delegated entirely to `docs/ab-testing.md`. The skill itself contains no executable code examples for implementation, variant configs, or useABTest usage patterns. | 2 / 3 |
Workflow Clarity | No workflow steps are defined in the skill body itself — it simply says 'follow docs/ab-testing.md for workflow.' There are no sequenced steps, no validation checkpoints, and no feedback loops for error recovery. For a skill involving potentially destructive flag changes and multi-step processes, this is insufficient. | 1 / 3 |
Progressive Disclosure | The skill correctly points to `docs/ab-testing.md` as the SSOT and references a compliance script, which is good structure. However, no bundle files were provided to verify these references exist, and the skill doesn't clearly signal what's in the referenced doc (e.g., section summaries or navigation hints). It's essentially a thin pointer with minimal navigational guidance. | 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
dedb5dd
- 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.