biome-linting
Analyze, fix, and validate Biome linting workflows. Use when JavaScript or TypeScript projects need Biome commands, diagnostics, safe fixes, or CI lint gates.
58
67%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./Skills/agent-ops/biome-linting/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 well-crafted skill description that hits all the key criteria. It uses third person voice, names the specific tool (Biome), lists concrete actions, and includes an explicit 'Use when' clause with natural trigger terms covering languages and workflow scenarios. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Analyze, fix, and validate Biome linting workflows' along with specific sub-capabilities like 'Biome commands, diagnostics, safe fixes, or CI lint gates'. | 3 / 3 |
Completeness | Clearly answers both what ('Analyze, fix, and validate Biome linting workflows') and when ('Use when JavaScript or TypeScript projects need Biome commands, diagnostics, safe fixes, or CI lint gates') with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Biome', 'linting', 'JavaScript', 'TypeScript', 'diagnostics', 'safe fixes', 'CI lint gates'. These cover the tool name, languages, and common workflow terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive by specifying 'Biome' as the tool, which is a specific linter/formatter. This clearly differentiates it from ESLint, Prettier, or other general linting skills. The combination of 'Biome' + specific workflow terms makes conflicts unlikely. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads as a generic agent-operations template applied to Biome linting rather than a genuinely useful Biome-specific guide. It lacks any concrete Biome commands, configuration examples, rule references, or executable code, which severely undermines its actionability. The workflow and philosophy sections are reasonable in structure but too abstract to provide meaningful guidance for actual Biome linting tasks.
Suggestions
Add concrete, executable Biome commands (e.g., `biome check .`, `biome lint --apply`, `biome lint --apply-unsafe`) with explanations of when to use each mode (read-only vs safe-write vs unsafe-write).
Include a real example of a biome.json config snippet and show how to interpret/fix common Biome diagnostics with specific rule names.
Replace abstract workflow steps like 'Inspect 2-3 focused surfaces' with Biome-specific steps such as 'Run `biome check --diagnostic-level=info .` to see all current issues' and 'Apply safe fixes with `biome check --apply .`'.
Remove generic agent philosophy content (Philosophy, Anti-Patterns sections) that Claude already knows and replace with Biome-specific gotchas, common CI integration patterns, or a quick-reference command table.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes several sections that are generic process boilerplate (Philosophy, Anti-Patterns, Constraints) rather than Biome-specific knowledge Claude doesn't already know. Phrases like 'Prefer the smallest reversible step that proves or disproves the current assumption' are general agent behavior, not Biome-specific guidance. | 2 / 3 |
Actionability | There are no concrete Biome commands (e.g., `biome check`, `biome lint --apply`), no executable code examples, no specific rule names, no config snippets, and no copy-paste-ready command sequences. The entire skill describes rather than instructs, offering abstract workflow guidance instead of actionable Biome-specific details. | 1 / 3 |
Workflow Clarity | The workflow section provides a numbered sequence with a validation/rerun step, and the Validation section mentions fail-fast behavior. However, the steps are abstract ('Inspect 2-3 focused surfaces', 'Take the smallest action') with no concrete Biome commands or specific validation checkpoints, making it hard to follow for actual Biome linting tasks. | 2 / 3 |
Progressive Disclosure | The skill references a deferred context directory under `Infrastructure/references/deferred-skill-context/agent-ops-biome-linting/` and instructs to load only what's needed. However, no bundle files are provided to verify this structure exists, and the main content lacks the concrete details that should either be inline or clearly pointed to in specific referenced files. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- jscraik/Agent-Skills
- Commit
4c78f98
- 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.