V3 Cli Invocation Migration logo

V3 Cli Invocation Migration

Community
hatayama
v3-cli-invocation-migration

Migrate only uloop V2 CLI option syntax in agent skills, Markdown, POSIX shell scripts, and PowerShell scripts to V3 syntax. Use when updating first-party or third-party uloop command examples that contain V2-style boolean arguments or renamed options.

Overview

Publisherhatayama
Repositoryunity-cli-loop
Skill namev3-cli-invocation-migration
Stars
578
Forks
49
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the V3 Cli Invocation Migration 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/hatayama/unity-cli-loop/tree/main/Packages/src/TemporarySkills~/v3-cli-invocation-migration/Skill
  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.

Use it in TypingMind

Enable V3 Cli Invocation Migration 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 V3 Cli Invocation Migration 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 V3 Cli Invocation Migration 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.

V3 CLI Invocation Migration

Use this skill to update V2-era uloop CLI option syntax to V3 syntax in agent-facing docs and automation.

Workflow

  1. Read references/first-party-v2-to-v3.md before editing.
  2. Search the repository for uloop invocations and the V2 names listed in the reference.
  3. Inspect nearby context before every edit. Search hits are candidates, not proof.
  4. Edit only files that clearly contain V2 uloop option syntax.
  5. Repeat the searches after editing and report any remaining V2 candidates with the reason each one was left unchanged.
  6. After every Required Search Pass reports zero remaining V2 candidates, tell the user this temporary skill has finished its job and can be removed with uloop skills uninstall-v3-migration --<target> (for example --claude or --codex). Do not uninstall the skill yourself.

Prefer rg for searches when available. If rg is unavailable, use the best available project search tool. Candidate discovery should be repository search plus context inspection, not a generated candidate list.

Validation Rules

  • Verify this migration with targeted search passes and a focused diff review.
  • Do not run Markdownlint as required validation for this migration.
  • If Markdownlint runs anyway and fails, ignore that result for this task. Do not stop, revert, or withhold completion solely because Markdownlint reports existing or unrelated Markdown formatting violations.
  • Do not fix Markdownlint findings as part of this migration unless the finding is directly caused by changing a uloop option token.

Editing Rules

  • Only change option tokens inside confirmed uloop command invocations.
  • Convert V2 boolean arguments from --flag true or --flag=false syntax to V3 flag syntax.
  • For third-party tools, check the tool's current schema or documentation before deciding whether false means removal, a --no-* flag, or a renamed option.
  • For first-party tools, use the reference table. compile, run-tests, get-hierarchy, and replay-input have special renamed negative flags.
  • record-input is removed. Direct users to create recordings in Window > Unity CLI Loop > Recordings instead of translating its options.
  • For first-party boolean options that are not in the reference tables, run uloop <command> --help and apply the boolean rules to the printed default: default: enabled means the V3 default is true, and default: disabled means it is false.
  • Some option names are valid V3 syntax on one command and V2 leftovers on another. Match every hit to its uloop command before editing; the reference lists the known same-name collisions.
  • A valid edit is limited to replacing, adding, or removing a uloop option token and the boolean value attached to that option in the same invocation.
  • Preserve surrounding Markdown, shell, and PowerShell formatting. Do not reflow prose, wrap lines, reorder arguments, normalize unrelated whitespace, trim unrelated trailing spaces, or change indentation.
  • If removing an option leaves extra spaces in that same uloop invocation, collapse only the spaces created by that removal.
  • Do not rename commands, replace removed commands, or rewrite command structure unless the user explicitly asks for command migration.
  • Do not change non-uloop command options, even when they have V2-looking boolean syntax.
  • Do not edit generated installed skills under .agents, .claude, .codex, .cursor, .gemini, .windsurf, .agent, or similar target folders unless the user explicitly asks to migrate installed copies.
  • Do not edit Markdown C# snippets, enum/member references, ordinary DTO/property access, regex match properties, or non-uloop JSON.
  • Do not change protocol versions, release versions, package names, assembly names, or public extension identifiers as part of this migration.

Required Search Passes

  • uloop command lines and examples.
  • Boolean-looking CLI options: --* true, --*=true, --* false, --*=false.
  • First-party renamed options from the reference, including bare flags.
  • Removed or renamed commands: get-project-info, get-version, record-input, unity-search, execute-menu-item, get-menu-items, get-unity-search-providers, get-provider-details, and capture-window (renamed to screenshot). Report these as out-of-scope command migration candidates unless the user explicitly asked to migrate removed commands.

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 V3 Cli Invocation Migration AI skill do?

Migrate only uloop V2 CLI option syntax in agent skills, Markdown, POSIX shell scripts, and PowerShell scripts to V3 syntax. Use when updating first-party or third-party uloop command examples that contain V2-style boolean arguments or renamed options.

Why use V3 Cli Invocation Migration on TypingMind?

Because you install it once and use it with any model. V3 Cli Invocation Migration 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 V3 Cli Invocation Migration in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hatayama/unity-cli-loop/tree/main/Packages/src/TemporarySkills~/v3-cli-invocation-migration/Skill. 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 V3 Cli Invocation Migration?

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 V3 Cli Invocation Migration?

As many as you like. As long as a model supports skills, you can use V3 Cli Invocation Migration with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the V3 Cli Invocation Migration AI skill free?

Yes. It is published on GitHub by hatayama 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 👇