Xiaobai Skills logo

Xiaobai Skills

Community
Tyuts
xiaobai-skills

One-click starter pack and curator for Codex/agent skills. Use when a beginner wants a high-quality default skills setup across common needs, when the user asks to install useful skills without researching them one by one, or when the installed skills library needs auditing, deduplication, conflict resolution, global-vs-backup selection, restore planning, or a written skills inventory.

Overview

PublisherTyuts
Repositoryxiaobai-skills
Skill namexiaobai-skills
Stars
59
Forks
5
Bundled files
9
LicenseMIT
Links
  • 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.

  • 9 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Tyuts/xiaobai-skills/tree/main
  4. 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.
2

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/Tyuts/xiaobai-skills.git \
  .claude/skills/xiaobai-skills
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Xiaobai Skills 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 Xiaobai Skills 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 Xiaobai Skills 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.

小白 Skills

小白 Skills is a starter-pack and library-curation workflow for users who do not want to spend hours researching agent skills before getting useful coverage.

It has two jobs:

  1. Install a practical, high-quality default set that covers common beginner needs.
  2. Audit an existing skills library, choose one global default per need, move overlapping alternatives to backup, and keep restore notes for later.

Principles

  • Cover common needs first: skill discovery, skill creation, frontend/UI, content/media tools, image workflows, engineering/TDD, diagnosis, planning, review, and handoff.
  • Prefer narrow concrete skills globally; keep broad process frameworks as backup unless the user explicitly wants that framework.
  • Back up instead of deleting.
  • Write an inventory that future agents can follow.
  • Restore one alternative at a time when the active choice disappoints.

Default Starter Set

When the user asks for a beginner-friendly one-click setup, install or keep:

  • System skills already bundled with Codex:
    • imagegen
    • openai-docs
    • plugin-creator
    • skill-creator
    • skill-installer
  • Discovery:
    • find-skills from vercel-labs/skills
  • Frontend/UI:
    • frontend-master from mineru98/llm-proxy-skills
  • Content, media, conversion, and publishing:
    • baoyu-skills from JimLiu/baoyu-skills
  • Engineering workflow:
    • mattpocock-skills from mattpocock/skills
  • Skills-library governance:
    • xiaobai-skills

Default backup candidates:

  • gstack from garrytan/gstack: rich YC-style product/engineering workflow.
  • superpowers from obra/superpowers: strict brainstorming, planning, TDD, debugging, verification, and subagent methodology.

These are useful, but they overlap heavily with Matt Pocock's engineering skills and with each other. Keep them in backup until the user asks for that style or the active engineering set underperforms.

Install Workflow

Use the bundled script when possible:

powershell
powershell -ExecutionPolicy Bypass -File .\scripts\install-xiaobai-skills.ps1

The script should:

  1. Create ~\.codex\skills if needed.
  2. Install missing default skills from their GitHub sources.
  3. Avoid overwriting existing installs unless -Force is passed.
  4. Move high-conflict backup packs to ~\.codex\skills-backup\xiaobai-YYYY-MM-DD\ when they are present globally.
  5. Write or update SKILLS-GLOBAL-INVENTORY.md.
  6. Tell the user to restart Codex.

If the script cannot be used, perform the same steps manually with PowerShell or GitHub CLI. Prefer GitHub release/archive downloads when git is missing.

Curation Workflow

1. Inventory

Scan active roots:

powershell
Get-ChildItem -LiteralPath "$env:USERPROFILE\.codex\skills" -Force
Get-ChildItem -LiteralPath "$env:USERPROFILE\.codex\skills" -Recurse -Filter SKILL.md -File
Get-ChildItem -LiteralPath "$env:USERPROFILE\.agents\skills" -Force -ErrorAction SilentlyContinue

Also inspect junction/symlink targets directly when recursion does not follow them.

For each SKILL.md, capture:

  • name
  • path
  • description
  • source package
  • whether it is system, active, backup, deprecated, dangerous, personal, or broad workflow-owning

2. Group By Need

Use this coverage map:

  • skill discovery and installation
  • skill creation/editing
  • frontend/UI implementation
  • image generation/editing
  • content/media/document conversion
  • translation and publishing
  • engineering workflow and TDD
  • debugging/diagnosis
  • review/QA/verification
  • planning/PRD/issues
  • docs/knowledge capture
  • deployment/release
  • security audit
  • browser automation
  • platform-specific/mobile work

3. Choose Global Defaults

Tie-breakers:

  1. System or official skills win when sufficient.
  2. Narrow skills beat broad packs.
  3. Stable skills beat deprecated, in-progress, or personal skills.
  4. Safer workflows beat skills that require --yolo, danger, broad shell automation, or unknown external CLIs.
  5. Only one broad engineering/process framework should be global by default.
  6. Concrete conversion/publishing tools can stay global if their triggers are specific.

Recommended default choice:

  • Engineering: Matt Pocock skills.
  • Strict methodology fallback: Superpowers.
  • Product/ship/team workflow fallback: gstack.
  • Frontend: frontend-master.
  • Media/content/conversion: Baoyu skills, with dangerous or duplicate subskills backed up.

4. Move Alternatives To Backup

Never delete by default. Move to:

~\.codex\skills-backup\xiaobai-YYYY-MM-DD\

Suggested structure:

text
xiaobai-YYYY-MM-DD/
  README.md
  packages/
  disabled-global-entries/
  disabled-subskills/

Before moving:

  • Resolve absolute paths.
  • Confirm sources are inside known skills roots.
  • Confirm destinations are inside the backup root.
  • Preserve enough directory structure to restore later.
  • Move junctions/symlinks separately from their target packages.

5. Write Inventory

Write:

  • active global skills and their roles
  • backed-up skills and why
  • backup paths
  • restore commands or manual restore notes
  • restart reminder
  • acknowledgements for the upstream skills used

Use SKILLS-GLOBAL-INVENTORY.md in the workspace and copy it into the backup folder as README.md.

6. Restore

When the active choice performs poorly:

  1. Identify the need category.
  2. Check inventory for backup alternatives.
  3. Restore one candidate at a time.
  4. Restart Codex.
  5. Update the inventory with what changed.

Do not re-enable all backup frameworks at once.

Audit Notes

When acting as the skill creator, optimize for:

  • clear trigger description
  • concise body
  • executable but safe steps
  • good restore path
  • user-friendly beginner language

When acting as the skill reviewer, challenge:

  • overbroad triggers
  • hidden destructive behavior
  • instructions that fight Codex safety policy
  • unclear install paths
  • missing backup/restore plan
  • missing acknowledgements

Acknowledgements

This skill's recommended starter set was shaped around these upstream projects:

  • OpenAI system skills: imagegen, openai-docs, plugin-creator, skill-creator, skill-installer
  • vercel-labs/skills for find-skills
  • mineru98/llm-proxy-skills for frontend-master
  • JimLiu/baoyu-skills
  • mattpocock/skills
  • garrytan/gstack
  • obra/superpowers

Respect each upstream project's license and README before redistribution.

Finish Report

End with:

text
Active:
- <skill/package>: <role>

Backed up:
- <skill/package>: <reason>

Inventory:
- <path>

Next:
- Restart Codex.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Xiaobai Skills AI skill do?

One-click starter pack and curator for Codex/agent skills. Use when a beginner wants a high-quality default skills setup across common needs, when the user asks to install useful skills without researching them one by one, or when the installed skills library needs auditing, deduplication, conflict resolution, global-vs-backup selection, restore planning, or a written skills inventory.

Why use Xiaobai Skills on TypingMind?

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

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

Which AI models can use Xiaobai Skills?

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 Xiaobai Skills?

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

Is the Xiaobai Skills AI skill free?

Yes. It is published on GitHub by Tyuts 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇