dale

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

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 content is a tight, well-structured linter procedure with a clear loop and a real, properly signaled reference file. Its main gaps are an abstract rule-triggering mechanism and the absence of a validation/checkpoint step for the batch rule pass.

Suggestions

Specify how a rule 'triggers' concretely (e.g., token/regex match against the rule's `tokens` field from rule-schema.yml) rather than leaving 'reason has been triggered' abstract.

Add a validation checkpoint after the rule loop, e.g., confirm every file in ./rules was processed and abort with a message if a rule fails to parse.

Trim the persona reinforcement to a single sentence to push conciseness toward fully lean.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with no padding about what markdown or linting is, but the repeated persona framing ("You are not a skill or an agent. You are a piece of software—a linter, called Dale") adds overhead that keeps it just short of the fully lean level-3 anchor.	2 / 3
Actionability	It gives concrete per-rule steps with quoted utterances and a copy-paste-ready output table, but the core mechanism — 'check the document to see if that reason has been triggered' — is abstract rather than a specified executable check, fitting the 'some concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	The Todo-driven loop with 1/2/3a/3b steps and final output is clearly sequenced, but this batch operation over all rules has no validation checkpoint (e.g., confirming every rule ran or handling malformed rules), which caps it at 2 per the destructive/batch feedback-loop guideline.	2 / 3
Progressive Disclosure	The body is sectioned and points to one-level-deep, clearly signaled references ("the skill /references/rule-schema.yml" and the /rules directory), and rule-schema.yml exists as a real file, matching the well-organized, easy-navigation level-3 anchor.	3 / 3
	Total	9 / 12 Passed

Description

22%

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 trigger clause but fails to communicate what the skill actually does, leaving its core capability unstated. Trigger terms are present but narrow. It is borderline-distinguishable yet underspecified.

Suggestions

Add the core capability, e.g. 'Lints markdown documents against a configurable rules engine and reports violations in a table.'

Broaden trigger-term coverage to include '.md', 'documentation', and 'edit docs' alongside 'markdown' and 'docs/'.

Combine what and when in one sentence: 'Lints markdown in docs/ against ./rules/*.yml and prints a violations table; run whenever a markdown file in docs/ is edited.'

Dimension	Reasoning	Score
Specificity	The description ("Any time a markdown file is edited in the docs/ directory, this skill should be run.") names a trigger condition but zero concrete capabilities — it never states what the skill does, matching the vague/no-actions anchor rather than the 'names domain and some actions' level 2.	1 / 3
Completeness	It supplies an explicit 'when' but omits 'what' entirely — the skill's actual function (linting markdown against rules) is absent, so it is missing one of the two required elements per the level-1 anchor.	1 / 3
Trigger Term Quality	"markdown file" and "docs/ directory" are relevant natural terms, but coverage is thin and misses common variations like ".md", "documentation", or "edit docs", fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The docs/ + markdown trigger is a recognizable niche, but without naming the linting capability it could still overlap with general documentation-editing skills, matching 'somewhat specific but could still overlap.'	2 / 3
	Total	6 / 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.