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

61%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-sectioned overview that appropriately defers detail to a single real reference file. Its main weaknesses are the absence of any executable command or code in the body itself and the lack of validation/checkpoint guidance for what is a batch checking-and-fixing workflow.

Suggestions

Include one copy-paste-ready command in the body (e.g., a lychee or linkchecker invocation) so Claude can act immediately without opening the reference.

Add an explicit validation checkpoint to the Check/Fix flow (e.g., re-run the checker after fixes until zero broken links remain) to support the batch fixing loop.

Link to references/rule.md from the relevant sections rather than only as a trailing pointer, so navigation is inline and unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean with no over-explanation of concepts Claude already knows; every section is brief. Not a 5 because the Quick Reference list and the Code Review sentence repeat information also implied elsewhere, and a few lines could be tightened; not a 3 because there is no padded or redundant explanation of basics.	4 / 5
Actionability	Names concrete tools ("lychee, linkchecker, or broken-link-checker npm packages") and concrete link types to check (internal, external, anchor, mailto), but the body gives no executable commands or code — all detail is deferred to references/rule.md. Not a 4 because nothing in the body is copy-paste ready; not a 2 because specific tool names and check categories are given.	3 / 5
Workflow Clarity	Check/Fix/Explain/Code Review sections provide a rough sequence, but there are no validation checkpoints or a validate-fix-retry loop for the batch link-checking and fixing process, which the rubric caps at 3 for batch operations. Not a 4 because checkpoints are absent; not a 2 because a recognizable sequence is present.	3 / 5
Progressive Disclosure	The body is an overview with clear section headers and a single clearly-signaled one-level-deep reference to references/rule.md (a real file). Not a 5 because the reference is signaled only at the very end as a plain path rather than inline section-level links, and the Quick Reference could point directly to the relevant reference sections; not a 3 because structure and the one-level reference are solid.	4 / 5
	Total	14 / 20 Passed

Description

62%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 states both what (validate final browser-facing markup) and when (reviewing templates, rendered HTML, shared components), but the awkward "related to Check for broken links" phrasing leaks the rule title and weakens the trigger clarity. Keyword coverage is decent but misses common synonyms like 404s and link rot.

Suggestions

Rewrite the description so the skill purpose reads as a natural action sentence rather than "related to Check for broken links" (e.g., "Validate rendered HTML, templates, and shared components for broken internal, external, anchor, and mailto links. Use when reviewing markup for dead links, 404s, or link rot.").

Add common user-facing synonyms ("dead links", "404s", "link rot", "redirect loops") to improve trigger-term coverage.

List the concrete action verbs beyond review/validate (e.g., check, fix, report) to lift specificity toward a fuller capability description.

Dimension	Reasoning	Score
Specificity	Names the domain and a couple of concrete actions ("reviewing templates, rendered HTML, or shared components", "Validate the final browser-facing markup"), but the action set is limited to reviewing/validating and not comprehensive. Not a 2 because concrete review/validate actions are named; not a 4 because no broader action list is given.	3 / 5
Completeness	Has both a "what" ("Validate the final browser-facing markup") and an explicit "when" ("Use when reviewing templates, rendered HTML, or shared components"), but the "when" is partially muddied by the awkward "related to Check for broken links" phrasing. Not a 5 because the trigger phrasing is not as crisp as the anchor example; not a 3 because both what and when are explicitly stated.	4 / 5
Trigger Term Quality	Includes relevant natural terms ("broken links", "rendered HTML", "templates", "shared components", "markup") but misses common synonyms a user would say ("dead links", "404s", "link rot"). Not a 4 because keyword coverage has noticeable gaps; not a 2 because several genuinely natural terms are present.	3 / 5
Distinctiveness Conflict Risk	The broken-link-in-rendered-markup niche is mostly distinct, though "reviewing templates, rendered HTML, or shared components" overlaps with general HTML-review skills. Not a 5 due to that overlap; not a 3 because the broken-link focus keeps it clearly niche.	4 / 5
	Total	14 / 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: 30756a7

Reviewed: 5 days 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.