CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

68%

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-checker/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A lean, well-structured overview that delegates implementation detail correctly to a single one-level-deep reference file. The main gaps are the complete absence of executable commands in the body (only tool names and link-type categories) and an implicit check-then-fix workflow with no explicit sequencing.

Suggestions

Add one inline quick-start command to the Quick Reference, e.g., 'npx lychee https://example.com' or 'linkchecker https://example.com', so the body is actionable without opening the reference.

Make the Check → Fix sequence explicit as numbered steps with the tool invocation and a re-check after fixing ('run checker → fix flagged links → re-run until clean'), replacing the implicit phase headers.

Delete or merge the 'Explain' section, which restates the intro sentence almost verbatim and duplicates the 'Why It Matters' content already in references/rule.md.

DimensionReasoningScore

Conciseness

The body is lean with no padding about concepts Claude already knows; the only over-explanation is the 'Explain' section restating the intro sentence nearly verbatim ("Explain why broken links hurt user experience, SEO rankings, and credibility") and the 'Check' section overlapping the Quick Reference bullets. Not score 5 due to that duplication; not score 3 because the rest is tight and every other section earns its place.

4 / 5

Actionability

The body names concrete tools ("lychee, linkchecker, or broken-link-checker npm packages") and link types ("internal, external, anchor, and mailto"), but contains zero executable commands — 'Use automated link checking tools to identify and fix broken links' is direction, not instruction, with the actual commands delegated to references/rule.md. Not score 4 because there is no inline code or command at all; not score 2 because the tool names and link-type taxonomy are specific, high-value guidance.

3 / 5

Workflow Clarity

Phases are listed (Check, Fix, Explain, Code Review) giving a discernible check-then-fix flow, but the sequence is implicit and has no checkpoints or commands, matching anchor 3 ('sequence present but checkpoints missing or implicit'). Not score 2 because the phases are coherent and well-defined; not score 4 because no explicit ordering with executable steps exists. The destructive/batch validation cap does not apply since link checking is read-only.

3 / 5

Progressive Disclosure

The body is a clear overview and the single one-level-deep reference is appropriately split and well signaled: 'For full implementation details, code examples, and framework-specific guidance, see references/rule.md' — and references/rule.md exists and holds exactly that (install and run commands for lychee/linkchecker, CI/CD configs) with no nested references. Not score 4 because there are no organization gaps: no content is inlined that belongs in the reference, and nothing is buried.

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 has a proper third-person 'Use when...' trigger and names a clear niche, but the capability statement stays abstract ('validate the final browser-facing markup') without concrete actions or natural synonyms like 'dead links' or '404s'. The templated phrasing shared with sibling rules also weakens distinctiveness.

Suggestions

State concrete actions in the description, e.g., 'Runs lychee/linkchecker against rendered HTML to flag broken internal, external, anchor, and mailto links' instead of the abstract 'validate the final browser-facing markup'.

Add natural trigger synonyms users would actually say — 'dead links', '404s', 'URL checking', 'link validation' — to the Use when clause.

Replace the templated 'related to Check for broken links' phrasing with a distinct trigger so the skill differentiates itself from sibling frontendchecklist skills that share the same boilerplate.

DimensionReasoningScore

Specificity

The description names the domain ("Check for broken links") and 1-2 concrete actions ("reviewing templates, rendered HTML, or shared components", "Validate the final browser-facing markup"), but never states what validation concretely involves (e.g., running a link checker, flagging 404s). It is not score 2 because it goes beyond naming the domain with two actionable directives, and not score 4 because it does not list several specific actions — the 'what' stays abstract.

3 / 5

Completeness

Both parts are present: an explicit 'Use when' clause ("Use when reviewing templates, rendered HTML, or shared components...") and a 'what' ("Validate the final browser-facing markup, not just the source framework abstraction"). Not score 5 because the 'what' lacks concrete trigger phrases — 'validate the markup' does not say what a violation is (broken/404 links) — and not score 3 because the 'when' is explicit, not merely implied.

4 / 5

Trigger Term Quality

"broken links", "rendered HTML", and "templates" are relevant keywords a user might say, but common variations are missing: "dead links", "404s", "URL validation", "link checker". It fits anchor 3 ('some relevant keywords but missing common variations or synonyms') better than 4, and better than 2 because it has more than one or two generic keywords.

3 / 5

Distinctiveness Conflict Risk

The boilerplate "Use when reviewing templates, rendered HTML, or shared components related to..." would be shared verbatim by sibling frontend-checklist skills, leaving only the trailing rule name as differentiator — real overlap risk with closely related HTML-review skills. Not score 4 because the differentiator is an awkwardly embedded rule title rather than a distinct trigger phrase, and not score 2 because the niche (broken links in rendered markup) is still named.

3 / 5

Total

13

/

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-checker/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.