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.

50

Quality

55%

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

53%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 content is a well-organized overview that correctly offloads detailed code examples to a real one-level reference file, but the body itself is light on executable guidance and its Check/Fix/Explain/Code Review sections are redundant rather than a tightly sequenced workflow.

Suggestions

Add at least one executable verification step in the body (e.g., 'Validate JSON-LD with Google's Rich Results Test' or a view-source command for heading hierarchy) to raise actionability and workflow clarity.

Collapse the redundant 'Explain' section into the intro and merge Quick Reference into Check to remove repeated content and tighten conciseness.

Frame Check → Fix → Code Review as an explicit numbered sequence with a validation checkpoint so the workflow is unambiguous.

DimensionReasoningScore

Conciseness

The body is mostly efficient but the 'Explain' section restates the opening paragraph and the Quick Reference overlaps the Check section, so it could be tightened rather than being lean throughout.

3 / 5

Actionability

It gives concrete checklist items (semantic HTML tags, JSON-LD types Article/FAQPage/HowTo, heading hierarchy) but provides no executable commands or code in the body itself — the actual examples live in references/rule.md — leaving execution details incomplete.

3 / 5

Workflow Clarity

Check, Fix, and Code Review sections imply a sequence but are presented as parallel sections rather than an explicit numbered workflow, and validation checkpoints are implicit with no validate-then-retry loop stated.

3 / 5

Progressive Disclosure

The SKILL.md is an overview that clearly signals a one-level-deep reference ('see references/rule.md') which exists and holds the code examples, though some explanatory content overlaps between the two files and the pointer is placed at the bottom rather than a dedicated References section.

4 / 5

Total

13

/

20

Passed

Description

57%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 well-formed with an explicit 'Use when' trigger and a clear, specific niche, but its action vocabulary is thin ('auditing') and it misses several natural trigger synonyms. It reads as scope-focused rather than capability-rich.

Suggestions

Add 1-2 concrete actions beyond 'auditing' (e.g., 'audit content pages and recommend semantic-HTML/JSON-LD fixes to improve AI discoverability').

Include the natural trigger terms users actually say, such as 'AI Overviews,' 'LLM search,' or 'GEO,' alongside 'AI-generated answers' and 'search snippets.'

Reframe the 'Applies to...' sentence as explicit user-mention triggers ('Use when the user asks about AI discoverability, GEO, or appearing in AI-generated answers').

DimensionReasoningScore

Specificity

The description names the domain ('content pages for AI discoverability') with a single generic action ('auditing') and otherwise lists scope rather than concrete capabilities, matching the 'names domain but actions minimal/generic' anchor.

2 / 5

Completeness

It has an explicit 'Use when...' clause and an applicability sentence giving both what ('auditing content pages for AI discoverability') and when, but the 'when' reads as scope rather than user-mention triggers, so it sits just below the comprehensive concrete-trigger anchor.

4 / 5

Trigger Term Quality

It includes relevant phrases ('AI-generated answers,' 'search snippets,' 'knowledge base extraction') but omits common variations users actually say such as 'AI Overviews,' 'LLM search,' or 'GEO,' fitting 'some relevant keywords but missing common synonyms.'

3 / 5

Distinctiveness Conflict Risk

The AI-discoverability/LLM-parsability niche is fairly distinct with specific triggers, though it carries minor overlap risk with closely related general SEO or structured-data skills.

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.

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.