000-jeremy-content-consistency-validator

Validate messaging consistency across website, GitHub repos, and local documentation generating read-only discrepancy reports. Use when checking content alignment or finding mixed messaging. Trigger with phrases like "check consistency", "validate documentation", or "audit messaging".

1.17x

Quality

—

Does it follow best practices?

Impact

86%

1.17x

Average score across 6 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

50%

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

The body is structurally clean and concise, but its instructions are abstract rather than executable, the workflow lacks validation checkpoints, and its reference pointers dangle against a missing references/ directory.

Suggestions

Make the Instructions concrete and executable: show actual commands using the allowed tools (e.g., grep/WebFetch to pull each source, diff to compare messaging) instead of 'Compare content systematically across sources'.

Add validation checkpoints to the workflow, such as confirming all content sources are accessible before comparing and verifying the generated report covers every source pair.

Either create the referenced references/errors.md and references/examples.md files or remove the dangling 'See {baseDir}/references/...' pointers so progressive disclosure resolves to real content.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept over-explanation, but it contains a filler overview line ('This skill provides automated assistance for the described functionality') and a vague Resources section whose tokens do not earn their place.	2 / 3
Actionability	The Output section specifies concrete deliverables (severity counts, source-pair comparisons, terminology matrix, action items with file/line), but the Instructions are abstract ('Compare content systematically across sources') with no concrete commands despite Bash(diff:) and Bash(grep:) tools being allowed.	2 / 3
Workflow Clarity	A clear 6-step sequence is present, but there are no explicit validation checkpoints (e.g., confirming all sources are accessible before comparing), so checkpoints are missing rather than explicit.	2 / 3
Progressive Disclosure	Sections are well-organized and references are signaled one level deep, but the referenced files ({baseDir}/references/errors.md and examples.md) do not exist in the bundle, so the navigation is broken rather than usable.	2 / 3
	Total	8 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-constructed description with explicit 'Use when' triggers and good natural-language keywords; its only weakness is modest action specificity, naming the domain well but listing only two concrete verbs.

Dimension	Reasoning	Score
Specificity	Names the domain concretely (website, GitHub repos, local documentation) and two actions (validate messaging consistency, generate discrepancy reports), but does not list multiple distinct concrete verbs, so it stops at anchor 2 rather than 3.	2 / 3
Completeness	Clearly states what it does (validate messaging consistency and generate read-only discrepancy reports) and when to use it via an explicit 'Use when...' clause plus 'Trigger with phrases like...', satisfying both halves; voice is third person with no penalty.	3 / 3
Trigger Term Quality	Includes several natural phrases a user would actually say ('check consistency', 'validate documentation', 'audit messaging', 'checking content alignment', 'finding mixed messaging'), giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (cross-platform messaging consistency across website, GitHub, and local docs) with mostly distinct triggers, making it unlikely to fire for the wrong skill despite 'validate documentation' being somewhat generic.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: majiayu000/claude-skill-registry
Commit: 8271354

Reviewed: about 18 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.