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.
81
75%
Does it follow best practices?
Impact
95%
1.23xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/ultracite/skills/ultracite/SKILL.mdQuality
Discovery
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), its domain (multi-provider linting/formatting), specific providers, and explicit trigger scenarios via a 'Use for...' clause. It uses third-person voice appropriately and packs substantial detail concisely. The only minor weakness is that some terms like 'AI hooks' and 'MCP integration' could be slightly more descriptive, but they serve well as trigger terms for users who know the tool.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: linting/formatting, v6/v7 setup, provider selection, Git hooks, MCP integration, AI hooks, migrations, and troubleshooting configuration/monorepo errors. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (multi-provider linting/formatting with Biome, ESLint, Oxlint) and 'when' ('Use for v6/v7 setup, provider selection, Git hooks, MCP integration, AI hooks, migrations, or encountering configuration, type-aware linting, monorepo errors'). The 'Use for...' clause explicitly lists trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: Biome, ESLint, Oxlint, Git hooks, MCP integration, linting, formatting, monorepo, type-aware linting, migrations. These cover the specific tools and common user terminology well. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — 'Ultracite' is a specific tool name, and the combination of multi-provider linting with specific providers (Biome, ESLint, Oxlint) and version-specific setup (v6/v7) creates a clear niche unlikely to conflict with generic linting or formatting skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent executable examples and concrete commands, but is severely undermined by extreme verbosity. It reads more like comprehensive product documentation than a focused skill file, with repeated information (installation commands appear multiple times, the summary section restates the entire document), marketing-style comparisons, and explanations of concepts Claude already understands. The progressive disclosure structure is partially implemented but the main file retains too much detail inline.
Suggestions
Cut the document by 60-70%: remove the 'Core Goals', 'Key Benefits vs Alternatives', 'When to Use This Skill' marketing sections, and the 'Summary' section which repeats the entire document. Claude can infer suitability from the tool's description.
Consolidate the 'When to Load References' section into a simple table or short list rather than repeating bullet points for each reference file with 4-5 trigger phrases each.
Remove duplicate installation commands - they appear in 'Quick Start', 'Non-Interactive Setup', 'Manual Setup', and 'Summary'. Keep one canonical installation section.
Add explicit validation/error-recovery steps to the ESLint/Prettier migration workflow (currently ends with just 'Test thoroughly') and include what to do when `ultracite doctor` reports failures.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 500+ lines. Contains extensive marketing-style content ('Key Benefits vs Alternatives', 'Core Goals'), repeated information (installation commands appear 3+ times, summary repeats the entire document), explanations of concepts Claude already knows (what a monorepo is, what Git hooks do), and a massive 'When to Load References' section that essentially duplicates the reference list. The 'When to Use This Skill' and 'Consider Alternatives' sections are unnecessarily detailed for Claude. | 1 / 3 |
Actionability | Provides fully executable commands throughout: installation commands with multiple package managers, CLI usage examples, configuration file contents (biome.jsonc, VS Code settings), Git hook scripts, and migration commands. Code examples are copy-paste ready with concrete file paths and flag options. | 3 / 3 |
Workflow Clarity | Multi-step processes like installation and migration are listed but lack explicit validation checkpoints. The v6→v7 migration includes a 'run doctor' step which is good, but the manual migration from ESLint/Prettier (6 steps) has only a vague 'Test thoroughly' at the end. The 'Project Suitability Assessment' workflow is clear but the migration workflow lacks feedback loops for error recovery. | 2 / 3 |
Progressive Disclosure | Good use of references directory with clear file pointers (references/provider-biome.md, references/troubleshooting.md, etc.), but the main SKILL.md contains far too much inline content that should be in reference files. The 'When to Load References' section is a massive block that could be structured more efficiently. The overview itself tries to be comprehensive rather than serving as a concise entry point. | 2 / 3 |
Total | 8 / 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 | |
88da5ff
Table of Contents
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.