reading-level

Use when reviewing content pages for user experience and SEO. Applies to blog posts, landing pages, how-to guides, and any long-form content intended for a broad audience.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/reading-level/SKILL.md

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 good progressive disclosure and specific readability thresholds, but it carries redundant sections, restates common knowledge in 'Explain', and lacks a concrete computation method and a post-fix validation step.

Suggestions

Trim or remove the 'Explain' section — Claude already knows what readability, bounce rate, and dwell time are — and merge 'Code Review' into 'Check' to eliminate duplication.

Provide the Flesch Reading Ease formula or a concrete estimation method instead of 'calculate or estimate', or fold the computation fully into references/rule.md and reference it explicitly.

Add a re-validation step after 'Fix' (e.g. recompute the grade level to confirm it dropped to Grade 8 or below) so the workflow has an explicit feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with useful Quick Reference/Check/Fix sections, but the 'Explain' section restates concepts Claude already knows (readability, bounce rate, dwell time) and 'Code Review' largely duplicates 'Check', so it could be tightened.	2 / 3
Actionability	It gives concrete thresholds (Flesch-Kincaid Grade Level, Flesch Reading Ease 60-70, sentences >25 words, paragraphs >4 sentences, subheadings every 200-300 words), but handwaves the core computation as 'calculate or estimate' with no formula or tool, deferring the real method to the reference.	2 / 3
Workflow Clarity	The Check -> Fix sequence is logical, but there is no re-validation step to confirm the grade level improved after fixes, and the 'Code Review' section duplicates 'Check', muddying which flow to follow.	2 / 3
Progressive Disclosure	SKILL.md is a concise, well-sectioned overview that points to a clearly signaled, one-level-deep reference (references/rule.md, which exists) for full implementation details and code examples, splitting content appropriately.	3 / 3
	Total	9 / 12 Passed

Description

65%

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 a clear, natural trigger and good coverage of content-type keywords, but it is vague about what the skill concretely does and omits its core concept (reading level/readability), weakening both completeness and distinctiveness.

Suggestions

Name the concrete actions the skill performs, e.g. 'Calculate the Flesch-Kincaid reading grade level, flag long sentences and passive voice, and suggest plain-language rewrites.'

Include 'reading level' or 'readability' in the description so the skill's actual purpose is explicit and clearly distinguishable from generic SEO or content-review skills.

Dimension	Reasoning	Score
Specificity	It names the domain — 'content pages', 'user experience and SEO', and content types — but lists no concrete actions; 'reviewing content pages' is abstract rather than specifying what the skill actually does (e.g. calculate a reading grade, flag long sentences, suggest rewrites).	2 / 3
Completeness	It has a strong explicit 'Use when ...' trigger and content-type guidance, but the 'what' is vague ('reviewing content pages for user experience and SEO') and never mentions reading level or readability, which is the skill's actual purpose — so the what is only weakly answered.	2 / 3
Trigger Term Quality	Includes natural terms a user would actually say — 'blog posts', 'landing pages', 'how-to guides', 'long-form content', 'SEO', and 'user experience' — giving good coverage of likely trigger phrasing.	3 / 3
Distinctiveness Conflict Risk	The broad 'user experience and SEO' framing without the words 'reading level' or 'readability' could overlap with a generic SEO or content-review skill, so it is not a clearly distinct niche.	2 / 3
	Total	9 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: thedaviddias/Front-End-Checklist
Path: skills/reading-level/SKILL.md
Commit: 48405aa

Reviewed: about 7 hours ago

Table of Contents

Discovery Implementation Validation

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.