link-checker

Use when reviewing templates, rendered HTML, or shared components related to Check for broken links. Validate the final browser-facing markup, not just the source framework abstraction.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/link-checker/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 with excellent progressive disclosure to a genuine reference file, but its actionable core stops at naming tools and link categories without a single executable command, and the check/fix guidance lacks any validate-and-retry loop for what is inherently a batch operation. Tightening the intro/Explain overlap and adding one runnable lychee or linkchecker invocation would lift the two weakest dimensions.

Suggestions

Include at least one copy-paste-ready command in the body (e.g. a minimal `lychee` or `linkchecker` invocation over the rendered output directory) so the main file is actionable without opening the reference.

Add a short validate-step sequence: run the checker, fix reported links, re-run until the report is clean — giving the batch operation an explicit feedback loop.

Drop the redundant "Explain" section (or the SEO intro sentence) — both make the same point about user/SEO/credibility impact that Claude already knows.

Dimension	Reasoning	Score
Conciseness	The ~30-line body is efficient with compact Quick Reference / Check / Fix / Code Review sections, but includes minor over-explanation Claude already knows — the "Google penalizes 404s" SEO justification and an "Explain" section that restates the intro sentence. This matches the efficient-with-trimmable-excess anchor.	4 / 5
Actionability	It names concrete tools ("lychee, linkchecker, or broken-link-checker npm packages") and check categories ("internal, external, anchor, and mailto links"), but provides no executable commands, flags, or example invocations in the body — some concrete guidance that is incomplete, with the executable detail deferred to references/rule.md. More than a high-level hint, so above 2; not mostly-executable, so below 4.	3 / 5
Workflow Clarity	A rough check -> fix -> monitor sequence is discernible across Quick Reference, Check, and Fix, but the sections are topical rather than a sequenced workflow, and there are no validation or retry checkpoints. Site-wide link checking is a batch operation, and the scoring notes cap workflow_clarity at 3 for batch operations without feedback loops.	3 / 5
Progressive Disclosure	A short, well-organized overview body (sections, quick-reference bullets) with a single clearly signaled one-level-deep reference — "see `references/rule.md`" — that is a real file containing the implementation details. Content is appropriately split and navigation is unambiguous, matching the clear-overview anchor.	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 answers both what and when and uses third person, but the what is only one action, the trigger keywords lack common synonyms (dead links, 404s), and the awkward clause "related to Check for broken links" reads like an unedited template fill-in that muddies the capability statement. It is serviceable but sits below the good examples' clarity and specificity.

Suggestions

Rewrite into a clean capability statement, e.g. "Checks internal, external, anchor, mailto, and tel links in rendered browser-facing HTML for 404s and unintended redirects, using tools like lychee or linkchecker. Use when reviewing templates, server-rendered HTML, or shared components for broken or dead links."

Add natural trigger synonyms users would actually say — "broken links", "dead links", "404s", "link checking" — to improve keyword coverage and reduce the chance of the skill being skipped.

Remove the garbled "related to Check for broken links" phrase so the when-clause reads as a fluent condition rather than a template placeholder.

Dimension	Reasoning	Score
Specificity	Names the domain ("templates, rendered HTML, or shared components") and one concrete action ("Validate the final browser-facing markup, not just the source framework abstraction"), but does not enumerate multiple specific capabilities like what kinds of links get checked or how, so it matches the 1-2-concrete-actions anchor rather than the several-actions anchor.	3 / 5
Completeness	Both parts are present: an explicit trigger ("Use when reviewing templates, rendered HTML, or shared components...") and a what-statement ("Validate the final browser-facing markup, not just the source framework abstraction"). Not a 5 because the what is weakened by the garbled phrase "related to Check for broken links" and the when-clause could name more concrete triggers (broken links, 404s).	4 / 5
Trigger Term Quality	Includes relevant natural keywords ("broken links", "rendered HTML", "templates") but misses common user phrasings such as "dead links", "404s", "link checking", or "href", fitting the anchor for some relevant keywords with missing variations rather than good keyword coverage.	3 / 5
Distinctiveness Conflict Risk	"Broken links" gives it a niche, but the trigger phrase "reviewing templates, rendered HTML, or shared components" is broad frontend territory that many sibling HTML-rule skills would also match, so it is somewhat specific yet still overlaps with similar skills.	3 / 5
	Total	13 / 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/link-checker/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.