dale

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

Quality

44%

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

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 body lays out a clear, sectioned linter workflow with concrete per-rule steps and an output example, but it carries unnecessary persona padding and lacks an explicit validation step in its batch rule loop.

Suggestions

Drop or shorten the role-play preamble ("You are not a skill or an agent...") to respect token budget.

Add an explicit validation checkpoint after running all rules — e.g. confirm every rule file was visited before printing the output table.

Either include the referenced ./rules/*.yml and /references/rule-schema.yml in the bundle or clarify that they live in the host project, so the references are not dangling.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient at ~40 lines, but the persona framing ("You are not a skill or an agent. You are a piece of software—a linter, called Dale") is unnecessary explanation that could be trimmed, landing on the mostly-efficient anchor.	3 / 5
Actionability	It gives concrete process steps and exact utterances for each rule, but the actual violation-detection logic is left implicit rather than specified, so guidance is actionable but incomplete.	3 / 5
Workflow Clarity	The sequence is clearly numbered (Todo per rule; steps 1, 2, 3a, 3b) but there is no validation checkpoint confirming each rule was applied correctly before producing output, capping this batch-over-rules workflow at 3.	3 / 5
Progressive Disclosure	The short body is well-organized into Overview, Rules Engine, Output, and Troubleshooting sections; it sits just below the top anchor because the referenced /references/rule-schema.yml and /rules paths are not present in the bundle.	4 / 5
	Total	13 / 20 Passed

Description

36%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 purely as a trigger clause tied to edits in docs/ and never tells Claude what the skill actually does. It is adequately specific about when to run but fails on the what-it-does axis.

Suggestions

Lead with what Dale does, e.g. "Lints markdown files in docs/ against rules in ./rules/*.yml and reports violations in a table."

Add an explicit 'Use when...' clause with natural synonyms such as lint, check, or review markdown docs.

Mention the output artifact (a violation table) so the description conveys the concrete result, not just the trigger.

Dimension	Reasoning	Score
Specificity	The description names the domain ("a markdown file is edited in the docs/ directory") but states no concrete actions — it says only when to run, never what Dale does, so it sits below the midpoint toward anchor 2.	2 / 5
Completeness	Only the 'when' is present without any 'what' — the description never reveals that Dale is a linter, matching the anchor where only 'when' is present without 'what'.	2 / 5
Trigger Term Quality	It includes one concrete trigger ("markdown file is edited in the docs/ directory") but lacks common variations or synonyms a user would naturally say (lint, check, docs), matching the some-relevant-keywords anchor.	3 / 5
Distinctiveness Conflict Risk	The docs/ + markdown trigger is reasonably specific and unlikely to fire for unrelated skills, but it could still overlap with general documentation skills, matching the somewhat-specific anchor.	3 / 5
	Total	10 / 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: fbd32cf

Reviewed: 4 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.