CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

56

Quality

64%

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

57%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 well-structured overview with exemplary progressive disclosure — a real, well-matched one-level-deep reference. But it loses points on redundancy (the same guidance repeated across Quick Reference, Check, Fix, and Explain sections) and on actionability, since the concrete examples and verification steps live entirely in the reference file while the body's own guidance stays abstract.

Suggestions

Merge the overlapping Check/Fix/Explain/Code Review sections — the generic-phrase list and screen-reader explanation each appear twice — into a single Check-then-Fix flow to eliminate duplication and tighten token efficiency.

Add one compact before/after example in the body (e.g. 'click here' → 'View pricing plans') so the core guidance is actionable without opening references/rule.md.

Turn the verification mention into an explicit step, e.g. 'Verify: open the browser accessibility tree and confirm each link's accessible name is understandable out of context', to close the workflow-clarity validation gap.

DimensionReasoningScore

Conciseness

The body is short but duplicates itself: the generic-phrase list ('click here', 'read more', 'learn more') appears in both Quick Reference and Check, and the screen-reader navigation explanation appears nearly verbatim in both the intro paragraph and the Explain section. More than minor trimming is needed, but it is not padded with background Claude already knows.

3 / 5

Actionability

Names concrete specifics (aria-label/aria-labelledby, file type and size for downloads, specific banned phrases), but the body contains no before/after examples of good vs. bad link text and 'Check that screen readers can understand link purpose out of context' has no operationalized method — all executable examples are delegated to references/rule.md.

3 / 5

Workflow Clarity

A rough sequence exists (Quick Reference → Check → Fix → Explain → Code Review), but verification is only implicit ('note how to verify the fix with browser accessibility tooling or assistive tech' is a mention, not a step), and the Check and Code Review sections overlap without delineating when each applies.

3 / 5

Progressive Disclosure

A concise, well-sectioned overview with one clearly signaled, one-level-deep reference ('For full implementation details, code examples, and framework-specific guidance, see references/rule.md') — the referenced file exists and contains exactly what is promised (code examples, patterns, verification steps).

5 / 5

Total

14

/

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.

A solid description with an explicit 'Use when' clause and a list of concrete inspection actions. Its weaknesses are the circular self-referential trigger phrasing, missing natural synonyms users would actually say, and boilerplate trigger language that would fire identically for sibling accessibility skills.

Suggestions

Replace the circular 'related to Use descriptive link text' trigger with concrete user-facing phrases, e.g. 'Use when you encounter generic link text like "click here", "read more", or "learn more", or when auditing link accessibility'.

State the concrete outcome of the skill (flag and fix non-descriptive link text, suggest aria-label alternatives) rather than only listing inspection actions.

Add natural trigger synonyms such as 'anchor text', 'accessible links', or 'link labels' to distinguish it from sibling accessibility skills that share the same boilerplate trigger.

DimensionReasoningScore

Specificity

Lists several concrete inspection actions ('Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output') but the actions are generic accessibility-review verbs shared by any a11y skill, and it never states the concrete outcome (flagging/fixing non-descriptive link text).

4 / 5

Completeness

Answers both 'what' (check semantics, keyboard behavior, focus flow, accessible names, screen-reader output) and 'when' ('Use when reviewing rendered HTML, interactive components, or design-system patterns'), but the 'when' is circular — 'related to Use descriptive link text' references the skill's own name rather than concrete user-mention triggers.

4 / 5

Trigger Term Quality

Includes good natural terms like 'link text', 'accessible names', 'screen-reader', and 'design-system patterns', but misses common user phrasings such as 'click here', 'read more', 'anchor text', or 'a11y'.

4 / 5

Distinctiveness Conflict Risk

'Use descriptive link text' carves a niche, but the templated trigger ('reviewing rendered HTML, interactive components, or design-system patterns related to...') would be identical across sibling accessibility skills in the same category, creating real overlap risk with closely related a11y rules.

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
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.