Bun by tuanductran — AI Skill for Any LLM

Overview

Publisher	tuanductran
Repository	`hr-skills`
Skill name	`bun`
Stars	78
Forks	20
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

Markdown instructions

A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

Works with any LLM

AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

Self-contained

Everything the model needs lives in the instructions — no extra files to sync.

Open source

Published by tuanductran on GitHub. Read the source before you install it.

Installation

Install the Bun AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/tuanductran/hr-skills/tree/main/.agents/skills/bun
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/tuanductran/hr-skills.git /tmp/hr-skills
mkdir -p .claude/skills
cp -r /tmp/hr-skills/.agents/skills/bun .claude/skills/bun

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bun in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bun on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bun is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed

The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

Switch models mid-chat

Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Bun

This skill explains how Bun is used throughout the hr-skills monorepo. It covers workspace management, development workflows, validation commands, testing, and repository conventions.

The repository standardizes on Bun for all package management and script execution. Turborepo orchestrates tasks across workspace packages.

Supported tasks

Explain how Bun is used within this repository
Install and manage workspace dependencies
Run repository scripts using Bun
Validate HR skills and repository metadata
Synchronize generated repository artifacts
Build workspace packages
Run tests and TypeScript type checking
Troubleshoot Bun workspace issues
Recommend Bun workflows for local development and CI
Explain Bun compatibility with Node.js
Recommend Bun-native APIs when appropriate
Explain when to use Bun-specific features versus Node.js APIs

Repository usage

This repository uses Bun for:

package management
workspace dependency resolution
script execution
TypeScript execution
test execution

Package managers such as npm, pnpm, and Yarn are not supported.

Dependency catalogs

This repository centralizes shared dependency versions using Bun catalogs.

Catalogs ensure that common dependencies are defined once in the root package.json and reused consistently across every workspace package.

Workspace packages should reference shared dependencies using the catalog: protocol instead of repeating version numbers.

Use the default catalog.

json
{
  "dependencies": {
    "typescript": "catalog:"
  }
}

Use a named catalog.

json
{
  "devDependencies": {
    "@biomejs/biome": "catalog:biome",
    "@commitlint/cli": "catalog:commit"
  }
}

Benefits:

keeps dependency versions consistent across the repository
updates shared dependency versions in one place
reduces duplicated version declarations
simplifies workspace maintenance

Internal workspace packages should continue using the workspace:* protocol.

Node.js compatibility

When working in this repository:

Assume Node.js APIs are supported unless Bun documentation states otherwise.
If a package works in Node.js but fails in Bun, treat it as a Bun compatibility issue rather than a repository issue.
Prefer standard node: imports for built-in Node.js modules.
Prefer Bun-native APIs only when they provide a clear repository benefit.

Workspace packages

The repository currently contains multiple Bun workspace packages.

hr-skills-build

Repository tooling responsible for:

validating HR skills
synchronizing repository metadata
maintaining repository conventions

hr-skills-ref

Reusable library responsible for:

parsing SKILL.md
loading skills
validating metadata
generating prompts
exposing reusable APIs for other packages

Common commands

Install dependencies.

bash
bun install

Run validation.

bash
bun run validate

Synchronize generated repository artifacts.

bash
bun run sync

Build every workspace package.

bash
bun run build

Run all test suites.

bash
bun run test

Run TypeScript type checking.

bash
bun run typecheck

Run repository linting and formatting.

bash
bun run check
bun run lint
bun run format
bun run lint:md
bun run lint:md:fix
bun run lint:links

Analyze unused files and dependencies.

bash
bun run knip

Create a release.

bash
bun run release

Key prompts

Compatibility

"Explain Bun compatibility with Node.js."
"Does this Node.js package work with Bun?"
"Explain whether this Node.js API is supported."
"Recommend the Bun-native alternative."

Repository workflows

"Explain how Bun is used in this repository."
"List the common Bun commands used during development."
"Describe the repository workspace structure."
"Explain how Turborepo and Bun work together."

Validation

"Run the repository validation workflow."
"Explain what bun run validate does."
"Explain what bun run sync does."
"Recommend the correct validation order before opening a pull request."

Development

"Build every workspace package."
"Run all tests using Bun."
"Run TypeScript type checking."
"Explain how to troubleshoot Bun workspace issues."

CI

"Generate a Bun-based CI workflow."
"Recommend the fastest validation pipeline."
"Explain how to use Turborepo caching."
"Generate GitHub Actions steps for Bun."

CI recommendations

A typical validation workflow is:

bash
bun ci
bun run typecheck
bun run validate
bun run test
bun run build

This order detects type, validation, and test failures before building distributable artifacts.

Examples

Install dependencies.

bash
bun install

Validate the repository.

bash
bun run validate

Synchronize repository metadata.

bash
bun run sync

Build every package.

bash
bun run build

Run all tests.

bash
bun run test

Tips

Always use Bun for package management and script execution.
Prefer standard node: imports for built-in modules.
Use bun:test instead of node:test.
Prefer Bun-native runtime features only when repository portability is not required.
Check Bun compatibility documentation before assuming a Node.js feature is unsupported.
Prefer workspace commands from the repository root.
Run validation before committing repository changes.
Keep workspace dependencies synchronized.
Use workspace:* for internal package dependencies.
Use Turborepo to execute workspace tasks instead of running packages individually when possible.

Common issues

Using npm, pnpm, or Yarn instead of Bun.
Ignoring workspace dependency relationships.
Assuming unsupported behavior without checking Bun compatibility.
Using node:test instead of bun:test.
Depending on Node.js APIs that Bun documents as partially implemented.
Skipping repository validation before committing.
Forgetting to synchronize generated repository artifacts.
Running package scripts from the wrong workspace.
Missing bun install after dependency changes.
Hardcoding dependency versions that should come from a shared catalog.
Using explicit semver instead of catalog: for repository-standard dependencies.
Updating versions in workspace packages instead of the root catalog.
Using catalog: for internal workspace packages instead of workspace:*.

Best practices

Keep Bun updated across development environments.
Prefer standard node: module specifiers for built-in modules.
Use bun:test for repository tests.
Prefer documented Bun APIs over undocumented compatibility workarounds.
Mention Bun compatibility limitations only when they are relevant to the task.
Run commands from the repository root unless package-specific behavior is required.
Validate changes before opening a pull request.
Use Turborepo to orchestrate workspace tasks.
Keep internal packages versioned through the workspace.
Prefer reproducible installations with bun install --frozen-lockfile in CI.
Use catalog: for shared external dependencies.
Use named catalogs to group related tooling (for example: biome, commit, markdown).
Update dependency versions in the root catalog instead of individual workspace packages.
Use workspace:* only for internal packages.

Frequently asked questions

What does the Bun AI skill do?

Repository guidance for using Bun as the runtime, package manager, and workspace toolchain within the hr-skills monorepo.

Why use Bun on TypingMind?

Because you install it once and use it with any model. Bun is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bun in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tuanductran/hr-skills/tree/main/.agents/skills/bun. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Bun?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bun?

As many as you like. As long as a model supports skills, you can use Bun with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bun AI skill free?

Yes. It is published on GitHub by tuanductran under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Bun

Supported tasks

Repository usage

Dependency catalogs

Node.js compatibility

Workspace packages

hr-skills-build

hr-skills-ref

Common commands

Key prompts

Compatibility

Repository workflows

Validation

Development

CI

CI recommendations

Examples

Tips

Common issues

Best practices

Frequently asked questions

Related AI Skills

Set up your own AI workspace now