CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

direction-attribute

Use when reviewing templates, rendered HTML, or shared components related to Set text direction for RTL languages. Validate the final browser-facing markup, not just the source framework abstraction.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/direction-attribute/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A lean, well-structured review skill: concrete attribute-level guidance, an unambiguous Check/Fix/Explain/Review flow, and exemplary progressive disclosure that keeps the body minimal while pointing to a single clearly-labeled reference file. The only gaps are minor — slight repetition of bidi advice and no post-fix verification step.

DimensionReasoningScore

Conciseness

The ~35-line body is compact and free of concept tutorials; every section carries task-relevant guidance. Minor trimming opportunities exist: the opening consequence sentence ("RTL text displays incorrectly, UI elements appear backwards...") explains what Claude already knows, and the <bdi>/bidi-isolation advice appears in both Quick Reference and Fix. This matches anchor 4 (efficient with minor over-explanation) rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

Guidance is concrete and executable for an instruction-only skill: "Set dir="rtl" on <html> for Arabic, Hebrew, Persian, Urdu", "Use dir="auto" for user-generated content", exact attribute values ('ltr', 'rtl', 'auto'), and a specific element (<bdi>). Per the rubric's scoring note, absent inline code is not penalized since the guidance is actionable, but no copy-paste example appears in the body itself, so it sits at anchor 4 rather than anchor 5.

4 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review sections form a clear, logical sequence for this simple review task, and the Check section makes the core action unambiguous (verify the dir attribute plus inline user-generated content). However, there is no re-validation step after applying the Fix (e.g., re-check the rendered markup), which is the minor validation gap that defines anchor 4; anchor 5 requires explicit feedback loops, which this review-only skill lacks. Not anchor 3: the sequence is coherent with no real gaps, and no destructive/batch cap applies.

4 / 5

Progressive Disclosure

The body is a well-organized overview under 50 lines with clear sections, and it delegates all implementation detail, code examples, and framework guidance to references/rule.md — a real bundle file, clearly signaled ("For full implementation details, code examples, and framework-specific guidance, see references/rule.md"), exactly one level deep with no further nesting. This matches the simple-skill anchor 5 pattern.

5 / 5

Total

17

/

20

Passed

Description

70%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.

A solid description with an explicit and specific 'Use when' trigger clause, natural domain terminology, and a clear distinction between rendered markup and framework abstractions. Its main weakness is that the 'what' side lists only one to two actions, leaving the skill's actual capabilities (setting dir values, bidi isolation) implicit.

Suggestions

State the concrete actions the skill performs, e.g. "Sets dir attributes (ltr/rtl/auto) on html and inline elements and applies <bdi> bidi isolation for mixed-direction user content", to raise specificity.

Add common trigger synonyms such as "right-to-left", "Arabic", "Hebrew", "localization (i18n)", or "dir attribute" so users phrasing the need differently still match the skill.

DimensionReasoningScore

Specificity

The description names a concrete domain ("templates, rendered HTML, or shared components related to Set text direction for RTL languages") and one to two actions ("reviewing", "Validate the final browser-facing markup"), but does not comprehensively list what the skill actually does (set dir attributes, apply dir="auto", bidi isolation). It matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive) better than anchor 4, which expects several distinct specific actions listed.

3 / 5

Completeness

Both parts are present: an explicit 'when' ("Use when reviewing templates, rendered HTML, or shared components related to Set text direction for RTL languages") and a 'what' ("Validate the final browser-facing markup, not just the source framework abstraction"). The 'when' is explicit and specific, but the 'what' is thin — one validation action rather than a clear statement of capabilities — so it fits anchor 4 rather than anchor 5's fully concrete what+when pairing.

4 / 5

Trigger Term Quality

Good natural-term coverage: "reviewing templates", "rendered HTML", "shared components", "text direction", "RTL languages" — phrases a user working on markup review would naturally say. A few common terms are missing ("right-to-left" spelled out, "Arabic", "Hebrew", "dir attribute", "localization/i18n"), so it falls short of anchor 5's comprehensive synonym coverage but clearly exceeds anchor 3's partial coverage.

4 / 5

Distinctiveness Conflict Risk

The RTL/text-direction niche is distinctive ("Set text direction for RTL languages", "final browser-facing markup"), so it is mostly distinguishable from sibling HTML-review skills. Minor overlap risk remains with general i18n/localization or accessibility review skills, keeping it below anchor 5's clear-niche bar.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

thedaviddias/Front-End-Checklist

Path

skills/direction-attribute/SKILL.md

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.