parser-development

Use this skill when implementing or modifying Biome parser behavior, including `.ungram` grammars, lexers, token sources, parse rules, separated lists, error recovery, and parser fixtures. Do not use merely for consuming an existing AST/CST.

Quality

88%

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

83%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 concise and highly actionable with a strong review checklist, but its workflow lacks an explicit feedback loop for the batch codegen step, capping workflow_clarity at 3. Progressive disclosure is good though not maximal.

Suggestions

Add an explicit validation/feedback loop to the Workflow after codegen and test runs (e.g., 'If snapshots fail, fix the parse rule and re-run focused tests until green') to lift workflow_clarity above the batch-operation cap.

Move the detailed Presence Contract and Error Recovery sections into a referenced file (e.g., references/parser-recovery.md) and keep only the key rule inline, improving progressive_disclosure toward 5.

Add one or two short copy-paste fixture examples (a minimal ok/ and error/ case) to make the testing guidance even more immediately executable.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout; it never explains what a parser, lexer, or AST is and assumes Claude's competence, with each line earning its place.	5 / 5
Actionability	Provides concrete executable guidance — the 'just gen-grammar <lang>' command, named APIs (expect/eat/.ok()/.or_add_diagnostic), specific fixture dirs, quick_test, and testing-codegen — covering the common parser tasks actionable by reference to the canonical guide.	5 / 5
Workflow Clarity	The 6-step Workflow is sequenced and a Review Checklist supplies verification, but a grammar-codegen/batch workflow lacks an explicit validate→fix→retry feedback loop, so the batch-operation validation cap applies.	3 / 5
Progressive Disclosure	Well-organized sections with a clear one-level-deep References block (CONTRIBUTING.md, *.ungram, parser-infra dirs) and easy navigation; not a 5 because some detail (Presence Contract, Recovery) is inlined rather than split out, and no bundle files exist to offload it.	4 / 5
	Total	17 / 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 highly distinct, with concrete trigger phrasing and a useful negative boundary. Its only minor gap is keyword synonym coverage, which keeps trigger_term_quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete sub-actions — '.ungram grammars, lexers, token sources, parse rules, separated lists, error recovery, and parser fixtures' — with comprehensive coverage of the parser-development domain and a sharp negative boundary.	5 / 5
Completeness	Explicitly answers both 'what' (implement/modify Biome parser behavior across enumerated tasks) and 'when' ('Use this skill when implementing or modifying…'), with the negative boundary further sharpening the trigger context.	5 / 5
Trigger Term Quality	Strong natural domain keywords ('parser', 'lexer', 'grammar', 'error recovery', 'parse rules', 'fixtures') that a Biome contributor would actually say, but missing a few synonyms/variations like 'parsing' or 'tokenization'.	4 / 5
Distinctiveness Conflict Risk	Narrowly scoped to Biome parser internals via distinctive triggers ('.ungram', 'token sources', 'separated lists') plus a negative exclusion, yielding minimal overlap with other skills.	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/parser-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.