dale

Any time a markdown file is edited in the docs/ directory, this skill should be run.

Quality

49%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/dale/SKILL.md

Quality

Content

67%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 compact, well-organized instruction skill with concrete per-rule workflow steps and a clear output contract. It loses points mainly on persona padding and slightly informal reference paths rather than on substance.

Suggestions

Trim the persona preamble ("You are not a skill or an agent...") to a one-line identity statement to save tokens.

Express the rule-loop references as markdown links, e.g. [rule-schema.yml](references/rule-schema.yml), for cleaner navigation.

Add a brief explicit checkpoint noting the output table is produced only after all rule Todos are complete.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with sectioned structure, but the persona framing ("You are not a skill or an agent... you are a piece of software—a linter, called Dale") and the repeated verbatim "> You say..." lines could be tightened.	3 / 5
Actionability	Concrete, executable guidance is given: Todo-per-rule tracking, explicit numbered steps (1, 2, 3a, 3b), and a copy-ready output table example, with only minor gaps.	4 / 5
Workflow Clarity	A clear sequenced loop (Todo per rule, check, record violation, then print table) is present; the operation is read-only reporting so no fix-retry feedback loop is required, though checkpoints are implicit rather than stated.	4 / 5
Progressive Disclosure	The short, well-sectioned body signals one-level-deep references to a real bundle file (references/rule-schema.yml) and the rules directory; minor gap is the slash-path notation instead of clean markdown links.	4 / 5
	Total	15 / 20 Passed

Description

31%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 functions as a narrow trigger condition but fails to communicate what the skill actually does, leaving the capability opaque. It is reasonably scoped to the docs/ directory yet generic enough to risk overlap with sibling docs skills.

Suggestions

Lead with the capability, e.g. "Lints markdown files in the docs/ directory against a configurable rules engine and reports violations."

Add a concrete "Use when..." clause with natural trigger terms such as "lint", "check", or "markdown in docs".

Name the deliverable (a violations table) so the skill is distinguishable from generic docs-editing skills.

Dimension	Reasoning	Score
Specificity	The description only states a trigger ("this skill should be run") and names no concrete action or capability; it does not say what the skill does.	1 / 5
Completeness	It provides a clear "when" (markdown edited in docs/) but no "what" — the capability is entirely unstated, matching the "only when present without what" anchor.	2 / 5
Trigger Term Quality	It includes relevant keywords ("markdown file", "docs/ directory") but uses mechanical phrasing ("this skill should be run") and misses natural variations like "lint", "check", or "documentation".	3 / 5
Distinctiveness Conflict Risk	The trigger is somewhat specific (docs/ directory + markdown edit) but, without naming linting as the action, it could still overlap with other docs-related skills.	3 / 5
	Total	9 / 20 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
Path: .claude/skills/dale/SKILL.md
Commit: a2eb049

Reviewed: 3 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.