Turbo

Community

tuanductran

turbo

Repository guidance for using Turborepo to orchestrate workspace tasks, builds, validation, testing, and development workflows within the hr-skills monorepo.

Overview

Publisher	tuanductran
Repository	`hr-skills`
Skill name	`turbo`
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 Turbo 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/turbo
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/turbo .claude/skills/turbo

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

Use it in TypingMind

Enable Turbo 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 Turbo 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 Turbo 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.

Turborepo

This skill explains how Turborepo is used throughout the hr-skills monorepo. It covers workspace orchestration, task execution, caching, package filtering, and development workflows.

Turborepo coordinates tasks across every workspace package while Bun provides the runtime and package management.

Supported tasks

Explain how Turborepo is used within this repository
Run workspace tasks from the repository root
Build workspace packages
Validate HR skills and repository metadata
Synchronize generated repository artifacts
Generate the skill maturity matrix
Run tests and TypeScript type checking
Execute filtered workspace tasks
Recommend efficient development workflows
Explain Turborepo caching behavior
Generate CI workflows using Turborepo

Repository usage

This repository uses Turborepo to orchestrate workspace tasks.

Current pipeline tasks include:

build
dev
test
typecheck
validate
sync
matrix

Repository scripts invoke Turborepo from the workspace root while package-level scripts provide the implementation.

Workspace orchestration

Workspace packages define their own scripts.

Examples include:

packages/hr-skills-build
packages/hr-skills-ref

Turborepo automatically coordinates task execution, dependency ordering, and caching across these packages.

Common commands

Run all workspace builds.

bash
bun run build

Run development tasks.

bash
bun run dev

Run repository validation.

bash
bun run validate

Synchronize repository metadata.

bash
bun run sync

Generate the skill maturity matrix.

bash
bun run matrix

Generate the machine-readable skill registry.

bash
bun run registry

Generate usage-informed relevance signals from evaluation golden fixtures.

bash
bun run signals

Search the generated registry by text or domain.

bash
bun run discover "<query>"

Get related-skill recommendations for a skill ID.

bash
bun run recommend <skill-id>

Generate an execution plan for a user intent.

bash
bun run plan "<intent>"

Generate a plan and run it through the workflow runtime.

bash
bun run execute "<intent>"

Run the evaluation framework against eval/datasets.

bash
bun run evaluate

Run every test suite.

bash
bun run test

Run TypeScript type checking.

bash
bun run typecheck

Execute a task directly with Turborepo.

bash
turbo run build

Run a task for a single package.

bash
turbo run build --filter=hr-skills-ref

Run validation for the build package only.

bash
turbo run validate --filter=hr-skills-build

Key prompts

Repository workflows

"Explain how Turborepo is used in this repository."
"Describe the workspace task pipeline."
"Explain how Bun and Turborepo work together."
"List the repository tasks managed by Turborepo."

Development

"Run every workspace build."
"Run validation for the repository."
"Synchronize generated repository artifacts."
"Run tests across every workspace package."

Filtering

"Run a task for a single workspace package."
"Explain how --filter works."
"Recommend the correct package filter."
"Generate filtered Turborepo commands."

CI

"Generate a Turborepo CI workflow."
"Recommend a validation pipeline."
"Explain Turborepo caching."
"Optimize workspace builds for CI."

Pipeline overview

Current repository tasks include:

Task	Purpose
`build`	Build workspace packages
`dev`	Run development tasks
`test`	Execute package test suites
`typecheck`	Run TypeScript type checking
`validate`	Validate HR skills and repository metadata
`sync`	Synchronize generated repository artifacts
`matrix`	Generate `docs/engineering/skill-matrix.md` skill maturity snapshot
`registry`	Generate the machine-readable skill registry (`registry/skills.json`)
`signals`	Generate usage-informed relevance signals from evaluation golden fixtures
`discover`	Search the generated registry by text or domain
`recommend`	Get related-skill recommendations for a skill ID
`plan`	Generate an execution plan for a user intent
`execute`	Generate a plan and run it through the workflow runtime
`evaluate`	Run the evaluation framework against `eval/datasets`

Examples

Build every workspace package.

bash
bun run build

Validate the repository.

bash
bun run validate

Synchronize generated files.

bash
bun run sync

Generate the skill maturity matrix.

bash
bun run matrix

Build only one package.

bash
turbo run build --filter=hr-skills-ref

Run validation only for the build package.

bash
turbo run validate --filter=hr-skills-build

CI recommendations

A typical validation workflow is:

bash
bun install --frozen-lockfile
bun run typecheck
bun run validate
bun run matrix
bun run test
bun run build

Use Turborepo caching to avoid rebuilding unchanged packages.

Tasks such as sync and matrix intentionally disable caching because they always operate on the latest repository state and write files as a side effect. validate is cacheable (it only depends on ^build) — a repeat run with no source changes replays cached results instead of re-validating.

Tips

Execute workspace tasks from the repository root.
Prefer repository scripts (bun run ...) over invoking package scripts directly.
Use --filter during development to reduce execution time.
Let Turborepo determine task execution order.
Keep task outputs deterministic to maximize cache effectiveness.

Common issues

Running package scripts directly instead of using repository commands.
Forgetting to use --filter for package-specific development.
Expecting cached results from tasks that explicitly disable caching.
Running Turborepo outside the repository root.
Defining inconsistent task names across workspace packages.

Best practices

Use repository scripts for everyday development.
Reserve direct turbo run commands for advanced workflows.
Keep task names consistent across every workspace package.
Enable caching only for deterministic tasks.
Use package filters to shorten development feedback loops.
Allow Turborepo to manage workspace execution and dependency ordering.

Frequently asked questions

What does the Turbo AI skill do?

Repository guidance for using Turborepo to orchestrate workspace tasks, builds, validation, testing, and development workflows within the hr-skills monorepo.

Why use Turbo on TypingMind?

Because you install it once and use it with any model. Turbo 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 Turbo in TypingMind?

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

Which AI models can use Turbo?

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 Turbo?

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

Is the Turbo 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.

View all

Openclaw Repair Sweep

openclaw

OrganizationPopular

Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.

Openclaw Test Performance

openclaw

OrganizationPopular

Benchmark, diagnose, and optimize OpenClaw test and plugin-suite runtime, import hotspots, CPU/RSS, heap growth, and slow coverage paths.

Openclaw Testing

Choose proportional OpenClaw tests and checks, diagnose failures, and route environment-sensitive or release proof to its owner.

Release Openclaw Ci

Run, watch, debug, and summarize OpenClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Turborepo

Supported tasks

Repository usage

Workspace orchestration

Common commands

Key prompts

Repository workflows

Development

Filtering

CI

Pipeline overview

Examples

CI recommendations

Tips

Common issues

Best practices

Frequently asked questions

Related AI Skills

Set up your own AI workspace now