testing-codegen

Guide for testing workflows and code generation commands in Biome. Use when running snapshot tests for lint rules, managing insta snapshots, or regenerating analyzer/parser/formatter code after changes.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

A highly actionable, well-organized reference of concrete Biome testing and codegen commands. Its weaknesses are length/redundancy and a monolithic structure that could offload detailed specs to reference files.

Suggestions

Move the lengthy "Top-Level Comment Convention" spec (table + rules + HTML-ish examples) into a reference file and summarize the mandatory rule in SKILL.md with a one-level-deep link.

De-duplicate codegen guidance: keep either the "Code Generation Commands" section or the "Code Generation Dependencies" table, not both.

Tighten or remove explanatory bullets that restate concepts Claude knows (e.g., the list of what `dbg!` output "helps you understand") to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly concrete commands, but padded: the "Top-Level Comment Convention" section is very long, codegen guidance is duplicated between the commands section and the dependencies table, and bullets restate what `dbg!` output shows — concepts Claude already knows.	2 / 3
Actionability	Fully executable guidance — exact `just`/`cargo insta` commands, precise spec paths like `tests/specs/{group}/{rule}/`, and copy-paste-ready quick_test Rust snippets.	3 / 3
Workflow Clarity	Steps are listed but organized as a command catalog rather than sequenced multi-step workflows with explicit validate→fix→retry checkpoints; the destructive snapshot-pruning step has built-in safety, but other checkpoints remain implicit.	2 / 3
Progressive Disclosure	No bundle files exist and the ~430-line body is monolithic, with the comment-convention spec and codegen catalog inlined rather than split into reference files; sections are well-organized and cross-skill links are signaled, but it is far over the 50-line simple-skill threshold.	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.

A strong, third-person description that names concrete capabilities and gives an explicit Use-when trigger scoped to the Biome codebase. It cleanly answers what, when, and for whom without fluff.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "running snapshot tests for lint rules", "managing insta snapshots", "regenerating analyzer/parser/formatter code" — matching the anchor that lists several specific actions.	3 / 3
Completeness	Explicitly states what ("Guide for testing workflows and code generation commands in Biome") and an explicit "Use when" trigger clause, answering both what and when.	3 / 3
Trigger Term Quality	Natural domain terms a Biome contributor would actually say (snapshot tests, lint rules, insta snapshots, code generation) with good coverage and no jargon-only gaps.	3 / 3
Distinctiveness Conflict Risk	Scoped to Biome with distinct triggers (insta snapshots, analyzer/parser/formatter codegen) unlikely to fire 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/testing-codegen/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.