agentleFS
tuanductrantuanductran/hr-skills/.agents/skills/biome/SKILL.md

biome

Skill58 starsChanged 2 months agoMITView on GitHub

Repository guidance for using Biome as the formatter, linter, and code quality tool within the hr-skills monorepo.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run Biome from the repository root.

    line 193
  2. Distinctive:

    Prefer automatic import organization.

    line 195
  3. Distinctive:

    Keep formatting configuration centralized.

    line 197
  4. Distinctive:

    Use repository scripts instead of invoking Biome manually whenever possible.

    line 198
  5. Distinctive:

    Keep formatting fully automated.

    line 210
  6. Distinctive:

    Keep the repository on a single shared Biome configuration.

    line 211
  7. Distinctive:

    Use repository scripts for formatting and linting.

    line 212
  8. Distinctive:

    Keep formatting changes separate from functional changes whenever practical.

    line 215

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Biome

This skill describes how Biome is used throughout the hr-skills monorepo. It covers formatting, linting, import organization, repository conventions, and development workflows.

The repository standardizes on Biome as the primary code quality tool for TypeScript, JSON, JSONC, and YAML files.

Supported tasks

  • Explain how Biome is used within this repository
  • Format source code consistently
  • Review Biome diagnostics
  • Organize imports
  • Validate repository formatting
  • Apply safe code fixes
  • Explain repository formatting conventions
  • Troubleshoot Biome configuration issues
  • Generate repository-compatible Biome configuration

Repository conventions

This repository uses a single Biome configuration located at the repository root.

Biome is responsible for:

  • code formatting
  • linting
  • import organization
  • repository code consistency

Supported file types include:

  • TypeScript
  • JSON
  • JSONC
  • YAML

Repository-generated directories are excluded from analysis.

Formatting conventions

The repository follows these formatting conventions.

  • Tabs for indentation.
  • Indentation width of 4.
  • LF line endings.
  • Maximum line width of 90 characters.
  • Single quotes for JavaScript and TypeScript.
  • Semicolons are always required.
  • Trailing commas are enabled.
  • Parentheses are always used for arrow function parameters.
  • Imports are automatically organized.

These conventions are enforced automatically by Biome.

Linting

The repository enables the recommended Biome rule set, with one override: complexity/useLiteralKeys is turned off (see biome.jsonc).

Linting focuses on:

  • correctness
  • readability
  • maintainability
  • consistent code style

Compiler errors remain the responsibility of TypeScript.

Import organization

Biome automatically organizes imports.

The repository relies on automatic import ordering rather than manual sorting. Safe import organization is part of the Biome toolchain.

Common commands

Check the repository.

bun run check

Apply formatting and lint fixes.

bun run lint

Format files.

bun run format

Run Biome directly.

biome check .

Apply safe fixes.

biome check --write .

Run formatter only.

biome format --write .

Run linter only.

biome lint .

Run CI validation.

biome ci .

The ci command runs formatter, linter, and import organization in read-only mode, making it suitable for continuous integration.

Key prompts

Formatting

  • "Format this TypeScript file using repository conventions."
  • "Explain why Biome reformatted this code."
  • "Review this file for formatting issues."
  • "Apply safe formatting fixes."

Linting

  • "Explain this Biome diagnostic."
  • "Fix Biome lint errors."
  • "Recommend improvements following repository conventions."
  • "Review this pull request for Biome issues."

Imports

  • "Organize imports."
  • "Explain Biome import ordering."
  • "Remove unused imports."
  • "Review import organization."

Configuration

  • "Explain this biome.json configuration."
  • "Generate a repository-compatible Biome configuration."
  • "Review formatter settings."
  • "Review lint rules."

Examples

Check the repository.

bun run check

Automatically apply formatting.

bun run lint

Format the repository.

bun run format

Run Biome directly.

biome check --write .

Tips

  • Run Biome from the repository root.
  • Let Biome format code automatically instead of formatting manually.
  • Prefer automatic import organization.
  • Review diagnostics before suppressing rules.
  • Keep formatting configuration centralized.
  • Use repository scripts instead of invoking Biome manually whenever possible.

Common issues

  • Manually formatting code against repository conventions.
  • Reordering imports manually.
  • Disabling lint rules without justification.
  • Running Biome outside the repository root.
  • Ignoring formatting changes before committing.

Best practices

  • Keep formatting fully automated.
  • Keep the repository on a single shared Biome configuration.
  • Use repository scripts for formatting and linting.
  • Let Biome organize imports automatically.
  • Resolve diagnostics rather than suppressing them.
  • Keep formatting changes separate from functional changes whenever practical.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.