CtrlK
BlogDocsLog inGet started
Tessl Logo

llm-parsability

Use when auditing content pages for AI discoverability. Applies to any informational page intended to appear in AI-generated answers, search snippets, or knowledge base extraction.

55

Quality

62%

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/llm-parsability/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.

The body is a well-structured, actionable audit skill with excellent progressive disclosure into references/rule.md. Its main weaknesses are redundancy — the Check and Code Review sections duplicate each other and Explain repeats the intro — and the absence of an explicit verification step in the body's workflow.

Suggestions

Merge the "Check" and "Code Review" sections, which cover the same five criteria, into a single checklist to remove duplication.

Trim or cut the "Explain" section, whose content Claude already knows and which largely restates the intro paragraph.

Add a short verification step to the workflow (e.g., "After fixes, re-inspect the rendered HTML and confirm the JSON-LD validates") or explicitly point to the Verification section of references/rule.md.

DimensionReasoningScore

Conciseness

"Check" and "Code Review" list essentially the same five criteria (semantic tags, JS-free content, standalone headings, JSON-LD, FAQ patterns), and the "Explain" section restates the intro's point about answer engines extracting text — mostly efficient, but several sections could be merged or trimmed.

3 / 5

Actionability

Concrete, specific guidance throughout: exact tags to check ("<h1>–<h6>, <p>, <ul>, <ol>, <table>"), named schema types ("Article, FAQPage, HowTo"), and directive fixes ("Replace JavaScript-rendered content with server-side rendered HTML"). Minor gap: no concrete verification command or example markup in the body itself.

4 / 5

Workflow Clarity

The Check → Fix sequence is clear and the numbered criteria make the audit unambiguous, and the skill's read-only nature means the destructive-operation cap does not apply. However, no post-fix verification checkpoint appears in the body — it lives only in references/rule.md's Verification section, which the workflow never points to.

4 / 5

Progressive Disclosure

The ~45-line body is a concise overview with well-organized sections, and it ends with a clearly signaled one-level-deep pointer — "For full implementation details, code examples, and framework-specific guidance, see `references/rule.md`" — and that file exists and holds exactly those details (code examples, FAQ/HowTo JSON-LD, SSR patterns, exceptions, verification).

5 / 5

Total

16

/

20

Passed

Description

53%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 an explicit trigger and a reasonably distinct AI-discoverability niche, but it is essentially one trigger sentence plus a scope statement. It never clearly states what the skill does, and it lacks common natural synonyms for the domain.

Suggestions

Add a leading capability statement before the trigger clause, e.g., "Evaluates whether page content is parseable by LLMs and recommends structural fixes (semantic HTML, JSON-LD, server-side rendering)."

Include natural trigger variations users would actually say, such as "LLM visibility", "AI search results", "AI Overviews", or "answer engine citations".

Make the what/when split explicit: one sentence of concrete actions, then a separate "Use when..." sentence, mirroring the rubric's 5-anchor example pattern.

DimensionReasoningScore

Specificity

"auditing content pages for AI discoverability" names the domain and one concrete action, but the description lists no other specific capabilities (e.g., checking semantic markup, JSON-LD, or server-rendered content), so coverage is not comprehensive.

3 / 5

Completeness

The "when" is explicit ("Use when auditing content pages for AI discoverability"), but the "what" is only weakly implied from that trigger phrase — the description never states what the skill actually does (evaluate parseability, recommend restructuring, add JSON-LD) as a standalone capability statement.

3 / 5

Trigger Term Quality

Relevant keywords are present ("content pages", "AI discoverability", "AI-generated answers", "search snippets"), but common natural variations users would say are missing, such as "LLM visibility", "AI search", "AI Overviews", "structured data", or "JSON-LD".

3 / 5

Distinctiveness Conflict Risk

"AI discoverability", "AI-generated answers", and "knowledge base extraction" carve a clear LLM-visibility niche that is mostly distinct, with only minor overlap risk against closely related SEO skills such as a structured-data rule.

4 / 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
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.