CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

empty-links

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Fix empty and broken links. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.

Quality

76%

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/empty-links/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 compact, well-structured instruction skill: concrete check/fix guidance, a clear workflow, and exemplary progressive disclosure that defers code examples to a real, relevant reference file. The main cost is redundancy — the Explain section duplicates the intro and Fix duplicates Quick Reference — which inflates tokens without adding information.

Suggestions

Merge or cut the 'Explain' section — it repeats the opening sentence nearly verbatim; one statement of why the issue matters is enough.

Differentiate 'Quick Reference' from 'Fix' — currently the Fix section restates the same bullets; make Quick Reference the terse rule list and Fix the how-to with pointers into references/rule.md.

Name a concrete verification tool or procedure in 'Code Review' (e.g., inspect the accessible name in browser DevTools' accessibility pane or run an axe scan) instead of the generic 'browser accessibility tooling or assistive tech'.

DimensionReasoningScore

Conciseness

The body is lean overall (~250 words) with no padding of concepts Claude already knows, but contains real redundancy: the 'Explain' section repeats the intro nearly verbatim ('Screen readers announce empty links as just \'link\' with no context'), 'Fix' restates the 'Quick Reference' bullets almost word-for-word, and 'Code Review' embeds the rule title in template phrasing. This is 'mostly efficient but could be tightened' rather than the minor trims of a 4 or the verbose padding of a 2.

3 / 5

Actionability

Concrete, named techniques throughout — 'aria-label', 'aria-labelledby', 'visually-hidden text', 'empty anchor tags', 'icon-only links' — with code examples properly deferred to a real references/rule.md. Instruction-only guidance is specific and executable; it falls short of 5 only because verification is generic ('browser accessibility tooling or assistive tech') with no named tool or procedure.

4 / 5

Workflow Clarity

A coherent Check → Fix → Explain → Code Review sequence covers finding, remediating, and verifying the issue, and the skill is simple and non-destructive so no validation cap applies. Not a 5 because fix verification is instructed only vaguely rather than as a concrete checkpoint with a named tool; not a 3 because the sequence is unambiguous and verification is explicitly addressed.

4 / 5

Progressive Disclosure

The body is under 50 lines with clean sections (Quick Reference, Check, Fix, Explain, Code Review) and a single clearly-signaled, one-level-deep reference — 'For full implementation details, code examples, and framework-specific guidance, see references/rule.md' — which exists and contains exactly the promised HTML examples and fixing guidance. This matches the clear-overview-with-well-signaled-references anchor.

5 / 5

Total

16

/

20

Passed

Description

71%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 well-formed with an explicit 'Use when...' trigger and a concrete list of inspection actions, scoring solidly on specificity, trigger quality, and completeness. Its main weakness is distinctiveness: the generic review conditions are shared boilerplate and the link-specific qualifier relies on the rule title rather than natural distinguishing trigger phrases.

Suggestions

Replace the generic opener with link-specific triggers, e.g. 'Use when auditing links, navigation, or accessibility of anchors (empty links, icon-only links, missing aria-labels, broken hrefs)'.

Add natural synonym keywords users actually say — 'accessibility', 'a11y', 'link text', 'screen reader' — to broaden trigger coverage.

Mention the core remediation actions (add accessible text, aria-label, or visually-hidden text) so the 'what' covers the skill's full capability, not just the review half.

DimensionReasoningScore

Specificity

Lists several concrete review actions — 'Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output' — which matches the anchor for several specific actions with minor gaps. It is not a 5 because the remediation actions the skill actually performs (adding aria-label, visually-hidden text) are absent, and not a 3 because it goes beyond naming just 1-2 actions.

4 / 5

Completeness

Both parts are present: an explicit 'Use when reviewing rendered HTML, interactive components, or design-system patterns...' trigger clause and a clear 'what' (check semantics, inspect keyboard behavior, focus flow, accessible names, screen-reader output). Not a 5 because the 'when' partially recycles the rule title ('related to Fix empty and broken links') instead of concrete user-facing trigger phrases; not a 3 because the when-clause is explicit rather than weakly implied.

4 / 5

Trigger Term Quality

Includes good natural keywords users would say — 'rendered HTML', 'empty and broken links', 'screen-reader output', 'focus flow' — but misses common variations such as 'accessibility', 'a11y', or 'link text'. This fits 'good keyword coverage; a few natural terms missing' rather than the comprehensive synonym coverage of a 5 or the partial coverage of a 3.

4 / 5

Distinctiveness Conflict Risk

The opening conditions 'reviewing rendered HTML, interactive components, or design-system patterns' are generic boilerplate shared with sibling accessibility review skills, and the only discriminator is the embedded rule title. It is somewhat specific to links but could still overlap with closely related accessibility skills, fitting the 3 anchor better than 4, where overlap risk would need to be minor.

3 / 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/empty-links/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.