text-expansion

Use when reviewing CSS for fixed dimensions, truncation, or overflow rules on elements that render translatable strings.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/text-expansion/SKILL.md

Quality

Content

65%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a lean, well-structured overview that correctly delegates implementation detail to a real one-level-deep reference file. Its weaknesses are the absence of any executable code or commands in the body itself (particularly for the pseudo-locale build step, which is named but never specified) and the lack of an explicit validate-and-retest loop in the Check/Fix workflow.

Suggestions

Add one copy-paste-ready CSS before/after snippet in the Fix section (fixed width + overflow: hidden vs. min-inline-size), or at minimum the exact pseudo-locale technique or tool name so 'add a pseudo-locale build step' is executable.

Make the Check → Fix workflow an explicit numbered sequence ending in a validation step, e.g. '4. Re-run the pseudolocalized preview and confirm nothing clips or wraps unexpectedly.'

Remove the redundancy between the Quick Reference bullets and the Fix section (min-inline-size and pseudo-locale testing each appear twice), and drop the motivational closing sentence of the intro.

Dimension	Reasoning	Score
Conciseness	The ~35-line body is efficient, with concrete expansion factors (German 30%, Finnish 50%) and specific CSS properties earning their tokens, but the Quick Reference bullets repeat the Fix section and the intro's closing sentence ('far cheaper than fixing them after translations are delivered') is motivational padding — minor instances that could be trimmed, matching anchor 4 rather than anchor 5.	4 / 5
Actionability	Concrete property names appear (min-inline-size, overflow: hidden, white-space: nowrap, text-overflow: ellipsis), but the body contains no code or commands, and 'add a pseudo-locale build step for visual testing' names no tool, command, or configuration — concrete guidance with key details missing, matching anchor 3.	3 / 5
Workflow Clarity	The Check → Fix → Explain → Code Review sections imply a sequence, but there are no explicit steps or validation checkpoints (e.g. re-test the pseudolocalized build after fixes); the verification loop is only implicit, matching anchor 3's 'checkpoints missing or implicit' rather than anchor 4.	3 / 5
Progressive Disclosure	The body is a concise overview with a clearly signaled, one-level-deep pointer ('For full implementation details, code examples, and framework-specific guidance, see references/rule.md') to a bundle file verified to exist with matching content — a clear example of anchor 5's appropriate split and easy navigation.	5 / 5
	Total	15 / 20 Passed

Description

58%Weight 40%Scale 1-5

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 is specific about its review scope and clearly niche, but it merges the 'what' into a single 'Use when' clause and omits the domain's most natural trigger vocabulary (i18n, localization, text expansion). It is serviceable but leaves both capability framing and discoverability partially to inference.

Suggestions

Add an explicit capability statement before the trigger clause, e.g. 'Reviews and fixes CSS that breaks when translated text expands. Use when reviewing CSS for fixed dimensions, truncation, or overflow rules on elements that render translatable strings.'

Include the domain's natural keywords users actually say — 'i18n', 'localization', 'translation', and 'text expansion' — so the description triggers on those phrases.

State the concrete actions the skill performs (check CSS rules, replace fixed sizes, set up pseudo-locale testing) rather than a single 'reviewing' verb.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete review criteria ("fixed dimensions, truncation, or overflow rules on elements that render translatable strings") rather than vague language, but relies on a single action verb ("reviewing") rather than several distinct actions, so it falls between anchors 3 and 4.	4 / 5
Completeness	Only an explicit 'when' clause is present ("Use when reviewing CSS for..."); the 'what' is embedded and implied rather than stated as a capability, which sits above anchor 2's vague when-only example but below anchor 4's requirement of both an explicit 'what' and 'when'.	3 / 5
Trigger Term Quality	"CSS", "truncation", and "overflow" are natural terms a developer would say, but the domain's most common trigger phrases — "i18n", "localization", "translation", "text expansion" — are missing, matching anchor 3's 'missing common variations or synonyms' rather than anchor 4's good coverage.	3 / 5
Distinctiveness Conflict Risk	The CSS-plus-translatable-strings scope carves a clear niche, but 'reviewing CSS for overflow' has minor overlap risk with general CSS or layout review skills, matching anchor 4 rather than anchor 5's minimal-conflict niche.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: thedaviddias/Front-End-Checklist
Path: skills/text-expansion/SKILL.md
Commit: 7bfd868

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.