ultracite

Ultracite multi-provider linting/formatting (Biome, ESLint, Oxlint). Use for v6/v7 setup, provider selection, Git hooks, MCP integration, AI hooks, migrations, or encountering configuration, type-aware linting, monorepo errors.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with clean workflows and excellent progressive disclosure through real reference files. Its main weakness is verbosity and repetition across the Summary and several overlapping sections that inflate token use.

Suggestions

Remove the redundant Summary section (Use when / Consider alternatives / Installation / Most common workflow) which re-states content already covered in dedicated sections above, to cut significant tokens.

Consolidate the repeated provider-selection and init command blocks (they appear in 'Choosing a Provider', 'Quick Start', 'Non-Interactive Setup', and 'Summary') into a single canonical location with cross-references.

Trim the 'Package Versions' and 'Resources' sections or move them into a reference file, since specific versions/dates are time-sensitive and add maintenance burden without aiding Claude's core task.

Dimension	Reasoning	Score
Conciseness	Content is mostly efficient and task-relevant with concrete commands, but the ~790-line body repeats material already covered (Summary re-states Use when/Consider alternatives/Installation, Package Versions and Resources overlap prior sections) and could be tightened; not 3 due to this redundancy, not 1 because it avoids explaining basic concepts Claude already knows.	2 / 3
Actionability	Provides abundant copy-paste-ready, executable commands (`bun x ultracite init --linter biome`, `bunx ultracite check --write`) and complete `biome.jsonc`/VS Code config examples, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Setup and migration steps are clearly numbered (v6→v7 migration steps 1-4, interactive setup 1-10) with an explicit validation checkpoint (`npx ultracite doctor` to validate configuration) and error-recovery guidance.	3 / 3
Progressive Disclosure	Clear overview with well-signaled one-level-deep references (e.g., "see references/configuration-guide.md") plus a dedicated 'When to Load References' trigger map; all referenced files verified present in ./references/.	3 / 3
	Total	11 / 12 Passed

Description

100%

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, trigger-rich, and explicitly pairs what the skill does with when to use it, while occupying a clearly distinct niche. It is concise yet comprehensive without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("linting/formatting", "v6/v7 setup", "provider selection", "Git hooks", "migrations") and names the three providers (Biome, ESLint, Oxlint), matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers what ("multi-provider linting/formatting") and when via a clear "Use for ... or encountering ... errors" clause, satisfying the explicit-trigger anchor; not 2 because both what and when are clearly present.	3 / 3
Trigger Term Quality	Includes natural terms users would say — "linting", "formatting", "Git hooks", "MCP integration", "monorepo errors", "type-aware linting", "migrations" — giving good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	The Ultracite multi-provider niche with provider names and specific triggers (v6/v7 setup, MCP, AI hooks) is distinct and unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (889 lines); consider splitting into references/ and linking	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: secondsky/claude-skills
Commit: c4889f6

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.