CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

An excellent single-file skill body: dense, well-sectioned, and highly actionable for a Biome contributor, with a test-first workflow, a presence contract, and a review checklist. Its only gaps are the absence of a complete parse-rule code example and an explicit fix-and-re-run feedback loop after failing tests.

DimensionReasoningScore

Conciseness

The body is lean and efficient throughout — terse bullet fragments, imperative guidance, one shell command, and zero explanation of concepts Claude already knows (e.g., what a lexer is). Every token earns its place, matching the 5 anchor.

5 / 5

Actionability

Concrete, executable guidance dominates: `just gen-grammar <lang>`, the `expect`/`eat`/`.ok()`/`.or_add_diagnostic(...)` API choices, `quick_test`, `ok/` and `error/` fixture directories, and `&str` lexer tests. It stops short of the 5 anchor because no complete example snippet (e.g., a parse-rule or recovery call) is shown — the guidance is specific naming, not copy-paste code.

4 / 5

Workflow Clarity

The 6-step workflow is clearly sequenced and test-first ("Add or adjust focused ok/ and error/ fixtures before changing recovery behavior") with an end-of-loop validation step ("Run the language parser's focused tests and inspect snapshots") plus a dedicated Review Checklist. The 5 anchor's explicit fix-and-re-run feedback loop after a failing test is only implicit, keeping this at 4.

4 / 5

Progressive Disclosure

The body is a clear overview that delegates depth to the canonical repo guide ("Use crates/biome_parser/CONTRIBUTING.md as the canonical parser guide") and one-level-deep, clearly labeled references (References section, `xtask/codegen/*.ungram`, parser crate paths). Sections are well-organized with no nested or buried references, matching the 5 anchor's clear-overview, well-signaled structure.

5 / 5

Total

18

/

20

Passed

Description

87%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.

A strong description: it names a specific niche, comprehensively enumerates the parser subdomains it covers, gives an explicit use-when trigger, and adds a negative boundary that reduces mis-triggering. It is only a notch below perfect because its capability list is noun-heavy rather than action-verb-rich and omits a few natural synonyms.

DimensionReasoningScore

Specificity

The description enumerates concrete capabilities (".ungram grammars, lexers, token sources, parse rules, separated lists, error recovery, and parser fixtures") with comprehensive domain coverage, but relies on a single uniform verb pair ("implementing or modifying") plus an inclusion list rather than the multiple distinct concrete actions of the 5 anchor.

4 / 5

Completeness

It explicitly answers both what ("implementing or modifying Biome parser behavior, including .ungram grammars, lexers, token sources, parse rules, separated lists, error recovery, and parser fixtures") and when ("Use this skill when…"), with a concrete negative boundary ("Do not use merely for consuming an existing AST/CST"). This matches the 5 anchor's explicit what-and-when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural keyword coverage — "parser", "grammar", "lexer", "error recovery", "fixtures", and the ".ungram" extension — that a Biome contributor would actually say. A few natural synonyms ("syntax tree", "diagnostics", "parse errors") are missing, so it falls short of the comprehensive-synonym 5 anchor.

4 / 5

Distinctiveness Conflict Risk

A clear niche (Biome parser internals) with distinct technical triggers and an explicit exclusion clause for mere AST/CST consumption, minimizing overlap with generic parser or code skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.