derek

KB article quality reviewer. Run against KB articles in docs/kb/ to review frontmatter, article type and structure, title format, product names, and keyword quality. Use when editing or reviewing any file under docs/kb/.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

100%

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-structured, lean, highly actionable reviewer skill with a clear sequenced workflow and no padding of concepts Claude already knows. It is self-contained and well-sectioned, requiring no external bundle for its core task.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what KB articles, frontmatter, or Vale/Dale are beyond a flat 'already handles' list, and each section is a tight table or bullet list where every token earns its place, matching the score-3 anchor rather than the padded score-2 anchor.	3 / 3
Actionability	Guidance is concrete and copy-paste ready: exact field checks ('keywords 8–12 items', 'must start with `kA`'), required heading templates, a literal output-table row, and per-violation line-number rules, matching 'Fully executable ... copy-paste ready' rather than the pseudocode/missing-details score-2 anchor.	3 / 3
Workflow Clarity	A clear sequenced workflow (read style guide → read article → identify type → review areas → output) with an explicit type-identification decision branch and consolidation rules; the destructive/batch validation cap does not apply to this read-only review, so it is not capped at 2.	3 / 3
Progressive Disclosure	The skill is self-contained with no bundle files and is well-organized into clearly labeled sections, with its single external reference (kb_style_guide.md) signaled and only one level deep — no nested reference chain — matching the well-organized, easy-navigation score-3 anchor.	3 / 3
	Total	12 / 12 Passed

Description

77%

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 concrete and explicitly covers both capabilities and a 'Use when' trigger, but its trigger phrasing is somewhat narrow and it could overlap with similar review/linting skills. Broadening the natural trigger terms and sharpening distinctiveness would raise it further.

Suggestions

Add common natural trigger variations users would actually say (e.g., 'Use when checking, validating, or reviewing a KB article, or asking whether a docs/kb/ file is ready to publish').

Sharpen distinctiveness by noting the skill's niche versus Vale/Dale (e.g., 'covers frontmatter, structure, title, product-name, and keyword rules that Vale and Dale do not catch').

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete review actions — 'frontmatter, article type and structure, title format, product names, and keyword quality' — matching the 'Lists multiple specific concrete actions' anchor, and exceeds the score-2 anchor which only names a domain and some actions.	3 / 3
Completeness	It explicitly answers both what ('review frontmatter, article type and structure, title format, product names, and keyword quality') and when ('Use when editing or reviewing any file under docs/kb/') with an explicit 'Use when...' clause, so it is not the score-2 anchor where 'when' is only implied.	3 / 3
Trigger Term Quality	It includes a relevant trigger ('Use when editing or reviewing any file under docs/kb/') but the phrasing is narrow and misses common variations a user would say (e.g., 'check/validate this KB article'), matching 'Some relevant keywords but missing common variations' rather than the broad coverage of score 3.	2 / 3
Distinctiveness Conflict Risk	The niche is somewhat specific (Netwrix KB articles under docs/kb/) but could still overlap with generic doc-review or Vale/Dale-style linters, matching 'Somewhat specific but could still overlap with similar skills' rather than the clearly distinct, low-conflict score-3 anchor.	2 / 3
	Total	10 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: netwrix/docs
Commit: c229736

Reviewed: 2 days 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.