auto-import-rules

Enforces dlt import conventions and ordering. Use when writing or modifying Python imports in dlt/ or tests/.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%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 maximally concise and points clearly to a single rules file with an explicit override note, which suits a simple routing skill. Its weakness is that all substantive guidance is delegated to an external file that is not bundled here, so the skill is only as good as that reference.

Suggestions

Inline a one-line summary of the core import-ordering rules so the skill is actionable even if @.claude/rules/imports.md is unavailable.

Confirm @.claude/rules/imports.md is bundled (e.g., under references/) or document where it is resolved from, so the one-level-deep reference is verifiable.

Add a brief section header (e.g., '## Rule source') so the pointer has minimal structure rather than reading as a bare line.

Dimension	Reasoning	Score
Conciseness	The body is a single line — 'Use @.claude/rules/imports.md regardless of path setting' — with zero padding and no explanation of concepts Claude already knows, matching the score-5 'lean and efficient' anchor.	5 / 5
Actionability	Quotes 'Use @.claude/rules/imports.md regardless of path setting' — a concrete, specific directive with an exact path and an explicit override condition, but the actual executable rules live in the referenced file rather than inline, leaving a minor gap versus the copy-paste-ready score-5 anchor.	4 / 5
Workflow Clarity	This is a single-purpose skill and the one action is unambiguous ('Use @.claude/rules/imports.md regardless of path setting'); the simple-skill exception applies and there are no destructive or batch operations to require validation.	5 / 5
Progressive Disclosure	Quotes the single one-level-deep @-path reference '@.claude/rules/imports.md' which is clearly signaled, matching the score-4 'good structure, references mostly clear' anchor; it falls short of score-5 because the body offers no overview or sectioning beyond a bare pointer, and the referenced file is not present in the bundle to verify.	4 / 5
	Total	18 / 20 Passed

Description

82%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 is concise, third-person, and clearly states both capability and trigger conditions scoped to a specific niche. It fully satisfies the what/when requirement with natural trigger terms; its only mild weakness is that the listed actions are not exhaustive.

Dimension	Reasoning	Score
Specificity	Quotes 'Enforces dlt import conventions and ordering' — names the domain and two concrete actions (enforcing conventions, ordering) but the actions are not comprehensive, matching the score-3 anchor rather than the multi-action score-4 anchor.	3 / 5
Completeness	Explicitly answers both 'what' ('Enforces dlt import conventions and ordering') and 'when' ('Use when writing or modifying Python imports in dlt/ or tests/') with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Quotes 'writing or modifying Python imports in dlt/ or tests/' — natural phrases a user would say with good keyword coverage; falls just short of score-5 because synonyms like 'import statements' or 'import order' are missing.	4 / 5
Distinctiveness Conflict Risk	Quotes 'dlt import conventions' and 'in dlt/ or tests/' — a clear niche scoped to a specific library and directory set with distinct triggers and minimal conflict risk, matching the score-5 anchor.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: dlt-hub/dlt
Path: .claude/skills/auto-import-rules/SKILL.md
Commit: 04c80cd

Reviewed: about 15 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.