CtrlK
BlogDocsLog inGet started
Tessl Logo

broken-links

Use when auditing metadata, crawlability, structured data, or indexability related to Resolve internal broken links. Verify the rendered HTML and HTTP response rather than relying only on source files.

49

Quality

53%

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/broken-links/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized with a clean one-level-deep reference to a verified bundle file, but it is held back by an unnecessary concept-explanation directive, vague scanning guidance without tooling, and missing validation checkpoints in the check→fix workflow.

Suggestions

Drop or trim the 'Explain' section's directive to explain 'crawl budget' and the impact intro — Claude already knows these and the tokens compete with context.

Add a concrete scanning method or tool (e.g. a crawler command, grep for href targets, or a link-checker) so 'Scan the website' becomes executable rather than abstract.

Insert an explicit validation checkpoint in the workflow — e.g. after fixing, re-crawl the affected routes and confirm no 404/5xx remains before treating the rule as satisfied.

DimensionReasoningScore

Conciseness

The body is mostly lean, but the intro sentence explains broken links' impact ('frustrate users and waste crawl budget ... harming your site's SEO') and the 'Explain' section directs explaining 'crawl budget' — a concept Claude already knows, which the rubric penalizes. Not score 3 because these tokens do not earn their place; not score 1 because most sections are efficient.

2 / 3

Actionability

Some concrete guidance exists ('Identify and fix all internal links that return 404 or 5xx', 'Update the broken link to the correct URL or remove it', 'Flag exact routes or templates'), but there are no executable commands, tools, or code in the body and 'Scan the website' is vague with no method. Not score 1 because it gives specific actionable direction rather than purely abstract description.

2 / 3

Workflow Clarity

A loose Check → Fix sequence is present and well-sectioned, but there are no explicit validation checkpoints in the body, and batch link-fixing across a site warrants a verify/re-crawl step. Per the rubric, missing validation in batch operations caps this at 2. Not score 1 because the steps are listed and ordered.

2 / 3

Progressive Disclosure

The body is a concise overview split into clear sections and points to a single one-level-deep reference ('see references/rule.md') that exists on disk and is clearly signaled, matching the score-3 anchor. Not score 2 because navigation is easy and content is appropriately split rather than inlined.

3 / 3

Total

9

/

12

Passed

Description

50%

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 an explicit 'Use when' trigger and names a concrete SEO domain, but its capability statement is awkwardly embedded and it relies on jargon-heavy terms while missing common user phrasings like '404' or 'dead links'. It is moderately specific and moderately distinctive.

Suggestions

Lead with concrete actions before the trigger, e.g. 'Detects and fixes internal links returning 404 or 5xx errors. Use when ...' so 'what it does' is stated as a leading capability rather than embedded in the trigger clause.

Add natural trigger variations users actually say — 'broken links', 'dead links', '404s', 'link errors' — and drop the awkward mid-sentence title 'Resolve internal broken links'.

Tighten distinctiveness by foregrounding 'broken/dead internal links (404/5xx)' as the primary trigger so it does not overlap with general crawlability or structured-data audit skills.

DimensionReasoningScore

Specificity

It names a concrete domain ('auditing metadata, crawlability, structured data, or indexability') and an action ('Verify the rendered HTML and HTTP response'), but stops short of listing multiple distinct concrete actions like the score-3 anchor ('extract, fill, merge'). Not score 1 because it does name specific domains and a verifying action rather than vague language.

2 / 3

Completeness

An explicit 'Use when...' trigger answers 'when', but the 'what' is awkwardly framed — the capability is conveyed through the trigger clause and an inserted title ('Resolve internal broken links') plus a method sentence rather than a clear leading action statement. Not score 3 because it does not cleanly state 'what this does' with leading concrete actions as in the anchor.

2 / 3

Trigger Term Quality

It covers relevant SEO terms ('broken links', 'metadata', 'crawlability', 'structured data', 'indexability') but is missing common layperson variations ('404', 'dead links', 'link errors') and the embedded title 'Resolve internal broken links' mid-sentence makes the phrasing awkward and jargon-heavy. Not score 3 because coverage of natural user phrasings is incomplete.

2 / 3

Distinctiveness Conflict Risk

The 'broken links' niche is distinct, but the trigger lists broad SEO-audit terms ('metadata, crawlability, structured data, indexability') that could overlap with other SEO/indexability skills. Not score 1 because it is anchored to a specific SEO task rather than being fully generic.

2 / 3

Total

8

/

12

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.

Validation15 / 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.