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

77%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/ultracite/skills/ultracite/SKILL.md

Quality

Content

67%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.

A comprehensive, highly actionable body with strong progressive disclosure into real reference files and clear migration/setup workflows. Its main weakness is verbosity: redundant Summary and 'When to Load References' sections and repeated command blocks inflate the token budget, and a couple of bundle assets are not wired in.

Suggestions

Collapse the ~100-line 'When to Load References' section and the Summary's restated Use-when/install blocks — the inline 'see references/X.md' links already provide navigation, so the duplication mainly costs tokens.

Dedupe the `bun x ultracite init --linter ...` command block, which appears near-identically in 'Choosing a Provider', 'Quick Start', and 'Summary'.

Either add a README.md or remove the 'See README.md for complete interactive features documentation.' reference, and link the bundled .example config files (e.g. references/biome.jsonc.react.example, lefthook.yml.example) from the relevant sections.

Dimension	Reasoning	Score
Conciseness	At ~888 lines the body is mostly actionable, but contains several padded/redundant sections — the ~100-line 'When to Load References' block re-lists references already linked inline, the Summary restates the Use-when list and install commands, and the `bun x ultracite init` block is repeated near-verbatim in three places.	3 / 5
Actionability	Provides concrete, executable guidance throughout — real `bunx ultracite init ...` invocations with flags, complete biome.jsonc/.vscode snippets, package.json scripts, and git-hook examples — covering the common cases with only minor gaps.	4 / 5
Workflow Clarity	Multi-step processes (v6→v7 migration, manual setup, project-suitability assessment) are clearly numbered and include validation checkpoints like 'Run npx ultracite doctor to validate configuration' and 'Test linting: npx ultracite check .', with only minor gaps.	4 / 5
Progressive Disclosure	Good one-level-deep structure: inline 'see references/X.md' links plus a navigation section, and all 14 referenced reference files exist. Minor gaps: line 174 references a missing README.md, and the bundled .example config files (biome.jsonc.react.example, lefthook.yml.example, lint-staged.config.example) are never referenced from the body.	4 / 5
	Total	15 / 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, third-person description that clearly states what Ultracite does and gives an explicit 'Use for ...' trigger list covering the main scenarios. It is specific, well-keyworded, and unlikely to fire for unrelated skills.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete capability areas — 'multi-provider linting/formatting (Biome, ESLint, Oxlint)', 'provider selection', 'Git hooks', 'MCP integration', 'AI hooks', 'migrations', 'type-aware linting', 'monorepo errors' — with only minor gaps in coverage.	4 / 5
Completeness	Explicitly answers both what it does ('multi-provider linting/formatting (Biome, ESLint, Oxlint)') and when to use it via the 'Use for ...' clause enumerating concrete triggers (v6/v7 setup, provider selection, Git hooks, MCP integration, AI hooks, migrations).	5 / 5
Trigger Term Quality	Good coverage of natural terms users would say — 'linting/formatting', 'Biome', 'ESLint', 'Oxlint', 'Git hooks', 'monorepo', 'migrations' — though a few common synonyms (e.g. 'prettier replacement', 'auto-fix') are not surfaced in the description itself.	4 / 5
Distinctiveness Conflict Risk	Clear niche tied to the named Ultracite tool with distinct triggers (v6/v7, MCP, AI hooks, provider selection); minimal conflict risk with unrelated skills.	5 / 5
	Total	18 / 20 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
Path: plugins/ultracite/skills/ultracite/SKILL.md
Commit: ad16332

Reviewed: 12 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.