formatter-development

Use this skill when implementing or debugging Biome formatter behavior, IR composition, node rules, layout selection, source-comment handling, verbatim formatting, idempotency, internal specs, or Prettier comparison. Do not use for generic snapshot commands or parser changes.

Quality

89%

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

86%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 a tight, well-structured overview that gives concrete commands and rules without padding, with clean one-level-deep references. It could improve by adding a copy-paste node-rule code example and an explicit validate-fix-retry loop.

Suggestions

Add one complete, copy-paste `FormatNodeRule` / `fmt_fields` example so the node-rules guidance is fully executable rather than principle-level.

Make the feedback loop explicit in the workflow (e.g. 'If snapshots diverge or reformatting fails: fix the IR, re-run `just f`, re-verify convergence') to reach the top workflow_clarity anchor.

Clarify which command runs the narrowest spec test (a concrete invocation) so step 'Run the narrowest formatter crate or spec test first' is directly executable.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes contributor competence: it never explains what Biome or a formatter is, and every line states a project-specific rule, IR primitive, or command rather than padding with background.	5 / 5
Actionability	Provides executable shell commands (`just gen-formatter <lang>`, `just f`, `just l`, exact prettier-compare invocations) and concrete IR primitives (`space()`, groups), but much of the node-rules and layout guidance is architectural principle rather than copy-paste code, leaving minor gaps.	4 / 5
Workflow Clarity	The Workflow section is a clearly sequenced 1–6 process with checkpoints ('inspect snapshots', 'Review snapshots before accepting them') and a Review Checklist, but it lacks an explicit error-recovery/feedback loop phrased as 'if it fails, fix and re-run'.	4 / 5
Progressive Disclosure	Well-organized into focused sections with a clearly signaled, one-level-deep References block pointing to canonical files (CONTRIBUTING.md, spec.rs, README.md); no nested references and the inline content is appropriately overview-level.	5 / 5
	Total	18 / 20 Passed

Description

92%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 specific, complete, and well-bounded, clearly stating what the skill does and when to use it with a useful negative boundary. Its only weakness is that the trigger terms are somewhat jargon-heavy and lack synonyms.

Suggestions

Add a few plainer trigger synonyms (e.g. 'formatting output', 'snapshot diffs') alongside the technical terms to broaden natural phrasing.

Consider naming file extensions or concrete artifacts (e.g. '.snap' snapshot files) to improve trigger_term_quality toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete formatter concerns ('IR composition, node rules, layout selection, source-comment handling, verbatim formatting, idempotency, internal specs, or Prettier comparison'), giving comprehensive coverage of specific capabilities rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' (the enumerated formatter behaviors) and 'when' ('Use this skill when...') plus a negative boundary ('Do not use for generic snapshot commands or parser changes'), matching the concrete-trigger-phrases anchor.	5 / 5
Trigger Term Quality	Includes natural domain terms a Biome contributor would say ('Biome formatter behavior', 'Prettier comparison', 'internal specs', 'idempotency'), but the list leans technical and omits common synonyms/variations, so it is not fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Biome formatter development) with distinct triggers and an explicit exclusion clause, keeping conflict risk with adjacent skills minimal.	5 / 5
	Total	19 / 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: biomejs/biome
Path: .claude/skills/formatter-development/SKILL.md
Commit: 7d54688

Reviewed: 1 day 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.