CtrlK
BlogDocsLog inGet started
Tessl Logo

dead-end-pages

Use when auditing a site's internal link graph for dead-end pages, suggesting related-content links to add to thin or standalone pages, or reviewing CMS templates that produce link-free content pages.

63

Quality

75%

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/dead-end-pages/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.

A lean, well-structured instructional body with concrete thresholds and a clean hand-off to a single reference file. The main issue is redundancy: the Explain section and the Check/Code Review pair repeat content that could be consolidated, which is the main token-efficiency cost.

Suggestions

Merge the "Check" and "Code Review" sections, which both describe counting same-domain <a href> links in <main>/<article> and excluding templated navigation — keep one authoritative procedure.

Drop or fold the "Explain" section: it restates the intro's crawler-discovery concept that Claude already knows; at most keep the one non-obvious point about edges in the link graph.

Add a brief note on handling intentional exceptions (login, utility, staging pages) or point to the Exceptions section of references/rule.md so flagged pages aren't treated as fixable dead ends.

DimensionReasoningScore

Conciseness

The "Explain" section ("Internal links are the edges of your site's graph. Crawlers navigate by following links...") re-explains the crawler concept already stated in the intro, and "Check" and "Code Review" give near-duplicate counting/exclusion instructions. Not a 2 because each section is individually brief, but the redundancy is more than minor.

3 / 5

Actionability

Concrete, executable guidance: parse "<main> or <article>", count same-domain "<a href>" links, flag pages with "fewer than 2", add "2–5 topically related pages" with a worked CSS Grid example and a fallback "Related articles" section. Minor gap: no actual crawler command or script invocation inline (deferred to the reference).

4 / 5

Workflow Clarity

The Fix section is a clear six-step sequence with a verification checkpoint ("Re-crawl after changes to verify the links appear in the rendered DOM"). Not 5 because there is no error-recovery loop for flagged pages that are intentional exceptions (e.g. login or utility pages), which the reference file covers but the body omits.

4 / 5

Progressive Disclosure

A short, well-sectioned overview (Quick Reference, Check, Fix, Explain, Code Review) with a clearly signaled one-level-deep pointer: "For full implementation details, code examples, and framework-specific guidance, see references/rule.md" — the file exists and contains exactly that.

5 / 5

Total

16

/

20

Passed

Description

80%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 specific, well-scoped description with concrete actions and an explicit "Use when" trigger clause. Its main weakness is that the trigger conditions mirror the task list rather than naming user-side situations, and a few natural synonym phrases are absent.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — "auditing a site's internal link graph for dead-end pages", "suggesting related-content links to add to thin or standalone pages", "reviewing CMS templates that produce link-free content pages" — with comprehensive coverage of the audit/suggest/review workflow. It matches the comprehensive anchor rather than 4 because no meaningful capability in this niche is left unlisted.

5 / 5

Completeness

Both what (audit link graph for dead-ends, suggest related-content links, review CMS templates) and when (explicit "Use when" clause) are present. It falls short of 5 because the when-conditions are the tasks themselves rather than independent user-side triggers (e.g. "when the user mentions dead ends or an SEO/internal-linking audit").

4 / 5

Trigger Term Quality

Natural domain terms like "internal link graph", "dead-end pages", "related-content links", and "link-free content pages" are present and would be said by users running a link audit. A few natural variations are missing (e.g. "outgoing links", "internal linking", "orphan pages"), keeping it just below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

"Dead-end pages" and "link-free content pages" form a clear niche with distinct triggers, but the description overlaps the broader internal-linking/SEO audit space (e.g. a general internal-links skill), so minor overlap risk remains.

4 / 5

Total

17

/

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.