CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

link-text

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Use descriptive link text. 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/link-text/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.

The body is a compact, well-structured overview that defers implementation detail appropriately to a real, well-organized reference file. Its main weakness is redundancy — the generic-phrase rule and the screen-reader rationale are each stated twice — which wastes tokens without adding guidance.

Suggestions

Merge the overlapping guidance: keep the 'click here'/'read more'/'learn more' list in Quick Reference only, and have the Check section reference it rather than restate it.

Fold the Explain section's rationale into the one-line intro (or vice versa) — the 'screen reader users navigate by listing all links' point is currently made twice.

Name one concrete verification step in the body (e.g. 'run an accessibility tree/link-list audit in DevTools after fixing') instead of the vague 'browser accessibility tooling' pointer.

DimensionReasoningScore

Conciseness

The body is short but repeats itself: the generic-phrase guidance appears twice ("Avoid generic text like 'click here', 'read more', 'learn more'" in Quick Reference vs. "Avoid generic phrases like 'click here', 'read more', 'learn more'" in Check), and the screen-reader rationale appears in both the intro ("'click here' repeated 10 times tells them nothing") and the Explain section ("'click here' repeated multiple times provides no useful information"). This matches 'mostly efficient but includes some unnecessary explanation or could be tightened', not the noticeably-verbose anchor-2 since there is no padding beyond the duplication.

3 / 5

Actionability

Guidance is concrete and executable for an instruction-only skill: exact offending phrases are named, remedies are specific ("Use aria-label or aria-labelledby when visual design requires short text", "Include file type and size for download links", "Use links for navigation to a URL, not for in-page actions"). Minor gaps remain — 'Check that screen readers can understand link purpose out of context' names no method, and verification tooling is unnamed in the body and deferred to the reference — so it sits at 'mostly executable guidance with minor gaps' rather than fully copy-paste-ready.

4 / 5

Workflow Clarity

The Check → Fix → Explain ordering gives an unambiguous review-then-remediate sequence for this simple single-purpose skill, and verification is at least mentioned ('note how to verify the fix with browser accessibility tooling or assistive tech'). It falls short of anchor 5 because no explicit post-fix validation step exists in the body itself — verification detail lives only in the reference file.

4 / 5

Progressive Disclosure

The body is a lean overview under 50 lines with clearly labeled sections, and the single reference is well signaled and one level deep: "For full implementation details, code examples, and framework-specific guidance, see `references/rule.md`" — a file that exists and is itself well organized (code example, common patterns, exceptions, automated/manual verification). This matches 'clear overview with well-signaled one-level-deep references; content appropriately split'.

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 answers both what and when with genuinely concrete inspection actions and natural review vocabulary, but the trigger sentence is awkwardly templated and the shared accessibility-review boilerplate makes it hard to distinguish from sibling rule skills. Solid, usable description with clear room to sharpen its identity.

Suggestions

Rewrite the trigger clause around rule-specific phrases users would actually say, e.g. "Use when reviewing or writing link text, or when you encounter generic labels like 'click here', 'read more', or 'learn more'".

Replace the generic 'check native semantics / keyboard behavior' tail (shared by every accessibility rule) with link-text-specific actions such as 'flag generic link text, apply aria-label/aria-labelledby where short visual text is required, and state download file type and size'.

State the skill's output explicitly — what Claude produces after the review (flagged elements plus replacement link text or ARIA fixes) — to round out the 'what'.

DimensionReasoningScore

Specificity

"Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant" lists several concrete, domain-specific actions. It stops short of comprehensive coverage because it never states the skill's output (flagging generic link text and applying descriptive alternatives), so it fits 'several specific actions; minor gaps' rather than the fully comprehensive anchor.

4 / 5

Completeness

Both parts are present: the 'what' is the concrete inspection sequence and the 'when' is explicit ("Use when reviewing rendered HTML, interactive components, or design-system patterns related to Use descriptive link text"). The 'when' clause reads as awkward template substitution ('related to Use descriptive link text') and covers only review contexts, so it 'could be more explicit or specific' — the anchor-4 wording — rather than cleanly matching the anchor-5 example with natural, concrete trigger phrases.

4 / 5

Trigger Term Quality

Natural review-context terms are present — "rendered HTML", "interactive components", "design-system patterns", "link text", "accessible names", "screen-reader output" — giving good keyword coverage. Common phrasings a user would actually say are missing ("click here", "read more", "a11y", "WCAG", "link labels"), keeping it below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The only rule-specific discriminator is the embedded rule name; the rest ("Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant") is boilerplate that would read identically across sibling accessibility-rule skills, creating real overlap risk within that family. It is more specific than the generic 'works with document files' anchor-3 example but lacks the clear niche triggers of anchor 5.

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/link-text/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.