CtrlK
BlogDocsLog inGet started
Tessl Logo

weak-internal-links

Use when applies to any site with more than 20 pages. Use when auditing site architecture, investigating why certain pages underperform in search, or after a site migration.

44

Quality

46%

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/weak-internal-links/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 compact, well-sectioned overview that delegates details to a single well-placed reference file — excellent progressive disclosure. Its weaknesses are operational: the core crawl step has no concrete method or tool, and the workflow lacks any explicit verification checkpoint for what is a batch link-editing operation.

Suggestions

Make the Check step executable: name a concrete crawl method or script (e.g., a crawler export or command) for building the internal link graph, instead of just "Crawl the site and build an internal link graph".

Add an explicit verification step to the workflow (e.g., re-crawl the affected page set or check Google Search Console after adding links), or point to the Verification section of references/rule.md from the Fix section.

Remove the duplication between the intro paragraph and the Quick Reference bullets — both state the PageRank/discovery idea twice within a few lines.

DimensionReasoningScore

Conciseness

The intro paragraph and the Quick Reference bullets both explain the same PageRank/discovery idea ("Internal links are how search engines discover pages and how PageRank flows through a site" vs. "Internal links pass PageRank — more quality internal links to a page signal its importance"), and the opener restates a concept Claude already knows. Mostly tight, but there is unnecessary duplication that could be trimmed.

3 / 5

Actionability

"Crawl the site and build an internal link graph" names the step but gives no tool, command, or script to accomplish it, and all executable code examples (HTML link patterns, threshold table) live only in references/rule.md. Concrete numeric guidance exists ("at least 3–5 internal links", orphan = 0 links), so this is partial rather than vague guidance.

3 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review sections give a recognizable sequence, but there is no validation checkpoint in the body: verification is only vaguely implied via "describe how to verify the final page output", and adding links across many pages is a batch edit with no re-crawl/verify feedback loop. Per the rubric's cap for batch operations without feedback loops, workflow clarity cannot exceed 3.

3 / 5

Progressive Disclosure

A ~45-line overview with a single, clearly signaled, one-level-deep reference — "see `references/rule.md`" — which is a real file holding the thresholds, code examples, and framework guidance. The split is appropriate (overview inline, details external), matching the anchor for well-structured one-level-deep disclosure.

5 / 5

Total

14

/

20

Passed

Description

36%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 is a pure trigger list: it says when to use the skill but never what the skill does, and even the triggers omit the skill's own topic vocabulary (internal links, orphan pages). It reads as a fragment of a good description with its first half missing.

Suggestions

Add a capability statement before the trigger clause, e.g., "Audits internal link equity, finds orphan and weakly-linked pages, and fixes internal linking. Use when..."

Fix the broken opening clause: "Use when applies to any site with more than 20 pages" should be "Use when the site has more than 20 pages".

Include the skill's core topic terms as triggers — "internal links", "internal linking", "orphan pages" — so users asking about linking directly can find it.

DimensionReasoningScore

Specificity

The description contains no capability statement — only trigger scenarios like "auditing site architecture" and "investigating why certain pages underperform in search", plus a broken opening clause ("Use when applies to any site..."). The domain is implied but the skill's actual actions (auditing and fixing internal linking) are never named, matching the anchor 'Names the domain but actions are minimal or generic'.

2 / 5

Completeness

The 'when' is explicit and multi-scenario, but the 'what' is completely missing — the description never states what the skill does. This fits the anchor 'only when is present without what'; it is not a 1 because the trigger guidance is concrete and specific rather than vague.

2 / 5

Trigger Term Quality

Some natural trigger phrases are present ("site architecture", "site migration", "pages underperform in search"), but the core topic vocabulary — internal links, internal linking, orphan pages, link equity, PageRank — is entirely absent, so a user asking about those would not surface this skill. This matches 'Some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

Triggers are somewhat specific, but "auditing site architecture" and "after a site migration" would equally match sibling SEO skills (crawlability, redirects, sitemaps, dead-end pages) in the same family. This matches 'Somewhat specific but could still overlap with similar skills'.

3 / 5

Total

10

/

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.