Yao Open Skills Sync logo

Yao Open Skills Sync

CommunityPopular
yaojingang
yao-open-skills-sync

Manage the yao-open-skills public collection. Use this skill whenever the user wants to evaluate whether a local skill should be open sourced, import a local skill into the yao-open-skills repository, register which skills are already public, track GitHub sync status, or update the collection README and catalog after adding or refreshing a skill.

Overview

Publisheryaojingang
Repositoryyao-open-skills
Skill nameyao-open-skills-sync
Stars
1.3K
Forks
149
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Yao Open Skills Sync 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.
  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/yaojingang/yao-open-skills.git /tmp/yao-open-skills
mkdir -p .claude/skills
cp -r /tmp/yao-open-skills/skills/yao-open-skills-sync .claude/skills/yao-open-skills-sync
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Yao Open Skills Sync 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 Yao Open Skills Sync 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 Yao Open Skills Sync 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.

Yao Open Skills Sync

Use this skill to manage the public yao-open-skills collection in the current repo root.

This skill is not for creating arbitrary new skills from scratch. It is for intake, governance, sync tracking, and collection maintenance.

Read First

Before changing the collection, read:

  • references/operating-rules.md
  • references/registry-schema.md

Only read repo-wide docs under ../../docs/ if you need more human-facing detail after reviewing the references.

Primary Responsibilities

  • Evaluate whether a local skill is suitable for public release
  • Create a clean public copy under skills/<slug>/
  • Register or update the skill in registry/skills.json
  • Add or update a human-facing usage guide under docs/skills/<slug>.md
  • Regenerate the README catalog and HTML navigation page so the collection homepage stays in sync
  • Record whether the skill is only local, staged, published, or needs an update
  • Push collection changes to GitHub when the user wants the public repo updated

Workflow

1. Inspect the source skill

Given a local path from the user:

  • Confirm the path exists
  • Inspect SKILL.md
  • Identify what should be kept, removed, or rewritten for public release

Watch for:

  • output/, downloads/, .venv/, node_modules/, caches, logs
  • generated reports, exported results, .command helpers, and local scan artifacts
  • private APIs, tokens, cookies, internal references, customer data
  • assets or references that may not be redistributable

2. Decide whether it can be public

Use the publishing rules:

  • If the skill can be cleaned into a self-contained public version, proceed
  • If it mixes public logic with sensitive material, split the public part from the private part
  • If it cannot be safely cleaned, stop and explain why it should not be published

3. Import the public copy

When approved:

  • Copy the public version into skills/<slug>/ under the repo root
  • Keep only the files needed for the public skill
  • Make the structure self-contained and understandable
  • Exclude local output artifacts by default unless the user explicitly wants a safe sample included

4. Register the skill

Upsert the registry entry using:

bash
python3 scripts/register_skill.py \
  --slug <slug> \
  --title "<title>" \
  --summary "<summary>" \
  --source-local-path "<absolute-source-path>" \
  --collection-path "skills/<slug>" \
  --lifecycle active \
  --sync-status <local-only|staged|published|needs-update> \
  --github-repo yao-open-skills \
  --github-url "<url-if-known>" \
  --license "<license>" \
  --tags "tag1,tag2"

Use --last-synced-at YYYY-MM-DD only when the skill has actually been pushed to GitHub.

5. Update the README catalog

After every registry change, run:

bash
python3 scripts/render_collection_pages.py

README and index.html are rendered views. Do not maintain the catalog table or HTML Skill cards manually.

5.5 Write the usage guide

For every published skill, add or update:

text
docs/skills/<slug>.md

The guide should explain:

  • what the skill does
  • when to use it
  • the main workflow
  • important inputs and outputs
  • any local-only outputs that should not be committed back into the repo

6. Publish to GitHub when requested

If the user wants the collection pushed:

  • ensure the public files, registry, and README are already consistent
  • ensure index.html is regenerated from the registry
  • commit the current repo changes with a clear message
  • push to the configured yao-open-skills GitHub repository
  • only after a successful push, mark relevant skills as published and set last_synced_at

If the public repo exists but the local collection has new unpublished changes, use needs-update until the push is complete.

7. Report the result

Always report:

  • whether the skill was accepted for the public collection
  • the final collection path
  • the registry status you wrote
  • whether GitHub publication is still pending
  • what still needs manual confirmation, if anything

Output Expectations

When this skill completes a sync task, the result should leave the collection in a consistent state:

  • public files exist under skills/<slug>/
  • registry/skills.json is up to date
  • README.md catalog and index.html navigation page match the registry
  • if a push was requested, the GitHub repo reflects the same state

Decision Rules

  • Prefer stable, explanatory slugs in kebab-case
  • Do not publish raw private source directories without cleaning them
  • Do not mark a skill as published unless it has actually been synced to GitHub
  • If a published skill's source has changed locally, set sync_status to needs-update

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 Yao Open Skills Sync AI skill do?

Manage the yao-open-skills public collection. Use this skill whenever the user wants to evaluate whether a local skill should be open sourced, import a local skill into the yao-open-skills repository, register which skills are already public, track GitHub sync status, or update the collection README and catalog after adding or refreshing a skill.

Why use Yao Open Skills Sync on TypingMind?

Because you install it once and use it with any model. Yao Open Skills Sync 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 Yao Open Skills Sync in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yaojingang/yao-open-skills/tree/main/skills/yao-open-skills-sync. 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 Yao Open Skills Sync?

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 Yao Open Skills Sync?

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

Is the Yao Open Skills Sync AI skill free?

Yes. It is published on GitHub by yaojingang 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 👇