CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

77%

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 single-rule skill with actionable thresholds and proper progressive disclosure to references/rule.md. Its main weakness is redundancy: the crawler rationale is explained three times and the 'Check'/'Code Review' sections duplicate each other, which costs conciseness without adding information.

Suggestions

Merge the 'Check' and 'Code Review' sections into one (they repeat the same parse-count-flag-exclude procedure) and delete one copy, which would tighten the body without losing any guidance.

Collapse the crawler-rationale repetition: keep one statement of 'why' (either the intro paragraph or the 'Explain' section, not both, and trim the overlapping 'Quick Reference' bullet) since the crawl mechanics are context Claude already has.

Add a one-line error-recovery loop after the re-crawl verification step (e.g., 'if flagged pages still show fewer than two body links, check whether the CMS template strips inline links or the links are JS-rendered only').

DimensionReasoningScore

Conciseness

The crawler-follows-links rationale is restated in the intro paragraph, a 'Quick Reference' bullet, and the 'Explain' section, and the 'Check' and 'Code Review' sections repeat the same procedure nearly verbatim (parse <main>/<article>, count <a href>, flag fewer than 2, exclude nav/header/footer). The body is short but contains real duplication that could be merged.

3 / 5

Actionability

Concrete thresholds ('fewer than two unique internal links in the main content body'), specific scope ('<main> or <article> element'), explicit exclusions, a worked example (CSS Grid -> Flexbox/responsive posts), and a fallback pattern ('Related articles' or 'See also' section). No code or command snippet appears in the body itself, which keeps it just short of fully copy-paste-ready.

4 / 5

Workflow Clarity

A clear Check -> Fix sequence exists with an explicit verification step ('Re-crawl after changes to verify the links appear in the rendered DOM'), and the skill is simple and non-destructive. It lacks an explicit feedback loop for what to do if the re-crawl still shows dead ends, keeping it below 5.

4 / 5

Progressive Disclosure

The ~37-line body is a well-sectioned overview that delegates implementation detail to references/rule.md (which exists) via a clearly signaled, one-level-deep pointer ('For full implementation details, code examples, and framework-specific guidance, see references/rule.md'). This matches the simple-skill guidance: no nested references, no detail inlined that belongs elsewhere.

5 / 5

Total

16

/

20

Passed

Description

75%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 strong, specific description with an explicit triple 'Use when' trigger structure covering audit, remediation, and template-review scenarios. Its main gap is the absence of a standalone capability statement and of common synonyms like 'internal links' or 'orphan pages' that users may naturally say.

DimensionReasoningScore

Specificity

Names three concrete actions in a specific domain — 'auditing a site's internal link graph for dead-end pages', 'suggesting related-content links to add to thin or standalone pages', and 'reviewing CMS templates that produce link-free content pages'. It stops short of anchor 5 because the flagging criterion itself (pages with fewer than ~2 body internal links) is not stated, but it clearly exceeds the 1-2-action level of anchor 3.

4 / 5

Completeness

An explicit 'Use when...' clause with three concrete trigger scenarios satisfies the 'when', and the gerund actions (auditing, suggesting, reviewing) convey the 'what'. It is below anchor 5 because the 'what' is woven into the when-clauses rather than stated as its own capability sentence, and above anchor 3 because the when is explicit, not weakly implied.

4 / 5

Trigger Term Quality

Natural phrases users would say are present: 'dead-end pages', 'internal link graph', 'related-content links', 'CMS templates', 'link-free content pages'. Common synonyms a user might actually type — 'internal links', 'outgoing links', 'orphan pages' — are missing, which matches anchor 4 (good coverage, a few natural terms missing) rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

'Dead-end pages' is a distinctive niche trigger unlikely to fire for unrelated skills. Minor overlap risk remains with sibling internal-linking and thin-content SEO skills ('suggesting related-content links to add to thin or standalone pages' overlaps with generic internal-link advice), matching anchor 4 (mostly distinct, minor overlap risk) rather than the minimal-conflict profile of anchor 5.

4 / 5

Total

16

/

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/dead-end-pages/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.