type-inference

Guide for working with Biome's module graph and type inference system. Use when implementing type-aware lint rules, understanding type resolution, working on the module graph infrastructure, or implementing type inference for new features.

Quality

82%

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

65%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 content is highly actionable with real, executable Rust examples and a clearly sequenced resolution pipeline, but it is a monolithic document that could be tightened and split across bundle files, and its operational workflows lack explicit validation feedback loops.

Suggestions

Move large reference material (the full TypeData enum and the CSS/HTML module-graph internals) into dedicated bundle files under references/ and link to them one level deep to improve progressive disclosure.

Deduplicate the "Navigate Type References" workflow with "Common Patterns" Pattern 2 and prune "Tips" entries that restate earlier sections to tighten conciseness.

Add an explicit validate-fix-retry checkpoint to the Public Function Audit Rules workflow (e.g. grep -> review -> re-grep until no unjustified public functions remain) to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence with concrete Rust code, but it is lengthy (~400 lines) with redundancy — "Common Patterns" Pattern 2 repeats the "Navigate Type References" workflow and the "Tips" section restates earlier points — so it could be tightened.	2 / 3
Actionability	It provides fully executable, copy-paste-ready Rust code with real APIs (e.g. resolver.resolve_type, TextRange::new, inner_string_text()) and concrete file paths, matching the top anchor for executable guidance.	3 / 3
Workflow Clarity	The three resolution phases are clearly sequenced and the Public Function Audit Rules give a checklist, but operational workflows lack explicit validate-fix-retry checkpoints for the destructive function-removal step, leaving validation implicit.	2 / 3
Progressive Disclosure	No bundle files exist, so all material lives in one ~400-line SKILL.md; sections are well-organized but large reference content (full TypeData enum, CSS/HTML module graph internals) that could be split out is inline, and References point to external crate paths rather than skill bundle files.	2 / 3
	Total	9 / 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-targeted: it states concrete capabilities and provides an explicit Use-when trigger clause scoped to Biome's type inference system. It is a strong, distinctive skill description.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "implementing type-aware lint rules", "understanding type resolution", "working on the module graph infrastructure", and "implementing type inference for new features" — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	It answers both what ("working with Biome's module graph and type inference system") and when via an explicit "Use when..." clause enumerating four triggers, matching the top anchor.	3 / 3
Trigger Term Quality	It uses the natural domain terms a Biome contributor would say ("type-aware lint rules", "type resolution", "module graph", "type inference"), giving good coverage rather than generic jargon.	3 / 3
Distinctiveness Conflict Risk	It is tightly scoped to Biome's module graph and type inference system with distinct, niche-specific triggers, making conflict with other skills unlikely.	3 / 3
	Total	12 / 12 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: biomejs/biome
Path: .claude/skills/type-inference/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.