i18n-expert
This skill should be used when setting up, auditing, or enforcing internationalization/localization in UI codebases (React/TS, i18next or similar, JSON locales), including installing/configuring the i18n framework, replacing hard-coded strings, ensuring en-US/zh-CN coverage, mapping error codes to localized messages, and validating key parity, pluralization, and formatting.
91
88%
Does it follow best practices?
Impact
98%
1.00xAverage score across 3 eval scenarios
Passed
No known issues
Quality
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 well-crafted skill description that clearly defines its scope (i18n/l10n for React/TS UI codebases), lists specific concrete actions, and explicitly states when it should be used. The description uses proper third-person voice and includes excellent trigger terms that users would naturally use when needing this functionality.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'installing/configuring the i18n framework, replacing hard-coded strings, ensuring en-US/zh-CN coverage, mapping error codes to localized messages, and validating key parity, pluralization, and formatting.' | 3 / 3 |
Completeness | Explicitly answers both what ('installing/configuring the i18n framework, replacing hard-coded strings...') AND when ('when setting up, auditing, or enforcing internationalization/localization in UI codebases') with clear trigger conditions. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'internationalization', 'localization', 'i18n', 'React/TS', 'i18next', 'JSON locales', 'hard-coded strings', 'en-US/zh-CN', 'pluralization' - good coverage of both technical terms and common variations. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on i18n/l10n in UI codebases with React/TS stack - unlikely to conflict with general coding skills or other document processing skills due to specific domain focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured i18n skill with strong actionability and workflow clarity. The 8-step workflow with explicit validation checkpoints is excellent for a complex, multi-step process. Main weaknesses are some unnecessary explanation of concepts Claude knows (Core Capabilities section) and inline content that could benefit from progressive disclosure to separate reference files.
Suggestions
Remove or significantly trim the 'Core Capabilities' section - Claude already knows what i18n libraries do; focus on project-specific decisions instead
Move 'Architecture Guidance', 'Performance Notes', and 'Failure Modes' to a separate REFERENCE.md file with clear links, keeping only the most critical points inline
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some sections that could be tightened (e.g., 'Core Capabilities' lists things Claude already knows, 'Architecture Guidance' repeats some concepts). The workflow steps are appropriately detailed without excessive padding. | 2 / 3 |
Actionability | Provides concrete, executable commands (rg searches, python scripts, json validation), specific patterns like `t('namespace.key')` and `_one/_other` for plurals, and clear code examples. The guidance is copy-paste ready and specific to the task. | 3 / 3 |
Workflow Clarity | Excellent 8-step workflow with explicit validation checkpoints (step 3 audit, step 8 validate), clear feedback loop ('Re-run the audit until missing/parity issues are zero'), and treats missing keys as blockers. Includes verification commands at each stage. | 3 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but some content that could be in separate files (Architecture Guidance, Performance Notes, Failure Modes) is inline. References to scripts/i18n_audit.py exist but no links to detailed documentation for complex topics like RTL support or SEO localization. | 2 / 3 |
Total | 10 / 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
- daymade/claude-code-skills
- Commit
392d34c
- 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.