lint-rule-development

Step-by-step guide for creating and implementing lint rules in Biome's analyzer. Use when implementing rules like noVar, useConst, or any custom lint/assist rule, adding code actions to fix diagnostics, implementing semantic analysis for binding references, or adding configurable options to rules.

Quality

92%

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

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and well-sequenced with real commands and validation loops, plus a properly signaled one-level reference. Its main weakness is redundancy: the diagnostics pillars and magic-comments guidance are each stated twice, slightly inflating the token budget.

Suggestions

Remove the duplicate 'High Quality Diagnostics' section (or the 'Three Diagnostic Pillars' block) so the three-pillar guidance appears once and points to the diagnostics-development skill.

Consolidate the repeated magic-comments/test-file guidance into a single block and fix the broken code fence at the '// should generate diagnostics' example (lines ~266-269).

De-duplicate the two 'Tips' sections (one near the semantic/query guidance, one at the end) into a single consolidated tips list.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and actionable, but the three-pillar diagnostics guidance is duplicated (the top 'Three Diagnostic Pillars' section repeats in 'High Quality Diagnostics') and the magic-comments/test-file block restates itself, including a broken code fence at the // should generate diagnostics example.	2 / 3
Actionability	Provides fully executable Rust scaffolding, exact `just` and `cargo` commands, and copy-paste-ready code for rules, semantic queries, code actions, and options.	3 / 3
Workflow Clarity	Clear sequence (scaffold -> implement -> quick test -> snapshot -> codegen -> format/lint) with validation checkpoints and feedback loops such as `cargo insta accept/reject` and format-then-lint before commit.	3 / 3
Progressive Disclosure	Well-organized sections with a real one-level-deep reference (references/OPTIONS.md) and clear signals to sibling skills (diagnostics-development, testing-codegen, changeset) without nested indirection.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 specific, complete, and well-scoped to the Biome lint-rule niche with explicit 'Use when' triggers and natural domain keywords. It is a strong example of a capability and trigger description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'creating and implementing lint rules', 'adding code actions to fix diagnostics', 'implementing semantic analysis for binding references', 'adding configurable options' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly states what it does ('Step-by-step guide for creating and implementing lint rules') and when to use it via a 'Use when...' clause enumerating concrete triggers.	3 / 3
Trigger Term Quality	Covers natural domain terms a Biome contributor would say: 'noVar', 'useConst', 'lint/assist rule', 'code actions', 'semantic analysis', 'binding references', 'configurable options'.	3 / 3
Distinctiveness Conflict Risk	Niche is tightly scoped to Biome's analyzer with named example rules, making it unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: biomejs/biome
Path: .claude/skills/lint-rule-development/SKILL.md
Commit: c50a853

Reviewed: 9 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.