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.
92
Quality
92%
Does it follow best practices?
Impact
95%
1.23xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/ultracite/skills/ultracite/SKILL.mdDiscovery
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.
This is a strong skill description that clearly identifies the tool (Ultracite), lists specific capabilities (multi-provider linting with Biome/ESLint/Oxlint), and provides explicit trigger conditions. The description uses proper third-person voice and includes both common user terms and specific technical triggers that would help Claude select this skill appropriately.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'linting/formatting', 'v6/v7 setup', 'provider selection', 'Git hooks', 'MCP integration', 'AI hooks', 'migrations'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('multi-provider linting/formatting') and when ('Use for v6/v7 setup, provider selection, Git hooks, MCP integration, AI hooks, migrations, or encountering configuration, type-aware linting, monorepo errors'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'Biome', 'ESLint', 'Oxlint', 'Git hooks', 'linting', 'formatting', 'monorepo', 'type-aware linting', 'configuration'. Good coverage of tool names and common terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific tool names (Ultracite, Biome, ESLint, Oxlint) and unique features (MCP integration, AI hooks). Unlikely to conflict with generic linting skills due to the specific 'Ultracite' branding and version references. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with excellent progressive disclosure and clear workflows. The main weakness is verbosity - sections like 'Core Goals', 'Key Benefits vs Alternatives', and 'When to Use This Skill' explain concepts Claude already understands and could be significantly condensed or removed to improve token efficiency.
Suggestions
Remove or significantly condense the 'Core Goals' and 'Key Benefits vs Alternatives' sections - Claude understands tool tradeoffs and doesn't need marketing-style comparisons
Consolidate the 'When to Use This Skill' section into a brief checklist rather than detailed explanations of ideal vs alternative scenarios
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary explanations (e.g., explaining what Biome is, listing benefits vs alternatives that Claude could infer) and could be tightened. The 'Key Benefits vs Alternatives' and 'Core Goals' sections add bulk without providing actionable guidance. | 2 / 3 |
Actionability | Provides fully executable commands and code examples throughout - installation commands, configuration files, CLI usage, and package.json scripts are all copy-paste ready with specific flags and options documented. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation steps (e.g., 'Verify Installation' with `bunx ultracite doctor`, migration steps with numbered sequences, and the 'Project Suitability Assessment' workflow with clear checkpoints). | 3 / 3 |
Progressive Disclosure | Excellent structure with a clear overview and well-signaled one-level-deep references to specific documentation files (e.g., 'For complete Git hook setup guides, see: references/git-hooks-setup.md'). The 'When to Load References' section provides clear navigation guidance. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (879 lines); consider splitting into references/ and linking | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- 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.