Google Slides logo

Google Slides

Organization
vm0-ai
google-slides

Google Slides API for reading and editing presentations and speaker notes. Use when user mentions "Google Slides", "slides", "presentation", "speaker notes", or shares a docs.google.com/presentation link.

Overview

Publishervm0-ai
Repositoryvm0-skills
Skill namegoogle-slides
Stars
76
Forks
18
Bundled files
Instructions only
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.

  • Self-contained

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

  • Open source

    Published by vm0-ai on GitHub. Read the source before you install it.

Installation

Install the Google Slides 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/vm0-ai/vm0-skills.git /tmp/vm0-skills
mkdir -p .claude/skills
cp -r /tmp/vm0-skills/google-slides .claude/skills/google-slides
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Google Slides 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 Google Slides 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 Google Slides 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.

Google Slides

Read and edit Google Slides presentations through the Google Drive connector.

Official docs: https://developers.google.com/workspace/slides/api/reference/rest


When to Use

Use this skill when you need to:

  • Read presentation structure, slide content, or speaker notes
  • Create presentations or slides
  • Insert, replace, delete, or format presentation text
  • Update speaker notes without changing slide content or design
  • Generate slide thumbnails

Prerequisites

Connect the Google Drive connector at app.okou.ai/connectors.

Troubleshooting: If requests fail, run okou doctor check-connector --env-name GOOGLE_DRIVE_TOKEN or okou doctor check-connector --url https://slides.googleapis.com/v1/presentations/<presentation-id> --method GET

The Slides API reuses $GOOGLE_DRIVE_TOKEN. Reading presentations is allowed by default. Creating or modifying presentations requires the presentations.create or presentations.write Google Drive connector permission.


How to Use

Base URL: https://slides.googleapis.com/v1

The presentation ID is in the URL:

text
https://docs.google.com/presentation/d/<presentation-id>/edit

1. Read a Presentation

Read the presentation structure, slides, page elements, and notes pages:

bash
curl -s "https://slides.googleapis.com/v1/presentations/<presentation-id>" --header "Authorization: Bearer $GOOGLE_DRIVE_TOKEN" | jq '{presentationId, title, revisionId, slides}'

2. List Speaker Notes

Read every slide's speaker notes object ID and current text:

bash
curl -s "https://slides.googleapis.com/v1/presentations/<presentation-id>" --header "Authorization: Bearer $GOOGLE_DRIVE_TOKEN" | jq '[.slides[] | .slideProperties.notesPage as $notes | {slideObjectId: .objectId, speakerNotesObjectId: $notes.notesProperties.speakerNotesObjectId, text: ([$notes.pageElements[]? | select(.objectId == $notes.notesProperties.speakerNotesObjectId) | .shape.text.textElements[]?.textRun.content] | join(""))}]'

Always read the presentation immediately before editing. Object IDs can change when a presentation is edited in the Google Slides UI.

3. Replace Existing Speaker Notes

Use the speakerNotesObjectId returned by the previous request. Write to /tmp/google_slides_request.json:

json
{
  "requests": [
    {
      "deleteText": {
        "objectId": "<speaker-notes-object-id>",
        "textRange": {
          "type": "ALL"
        }
      }
    },
    {
      "insertText": {
        "objectId": "<speaker-notes-object-id>",
        "insertionIndex": 0,
        "text": "Updated speaker notes"
      }
    }
  ],
  "writeControl": {
    "requiredRevisionId": "<revision-id>"
  }
}

Then run:

bash
curl -s -X POST "https://slides.googleapis.com/v1/presentations/<presentation-id>:batchUpdate" --header "Authorization: Bearer $GOOGLE_DRIVE_TOKEN" --header "Content-Type: application/json" -d @/tmp/google_slides_request.json | jq '{presentationId, writeControl}'

When updating multiple slides, include each slide's deleteText and insertText requests in the same requests array. A batch update is atomic: if one request is invalid, none of the changes are applied.

4. Add Speaker Notes to an Empty Notes Shape

If the speaker notes shape has no text, omit deleteText. Write to /tmp/google_slides_request.json:

json
{
  "requests": [
    {
      "insertText": {
        "objectId": "<speaker-notes-object-id>",
        "insertionIndex": 0,
        "text": "New speaker notes"
      }
    }
  ],
  "writeControl": {
    "requiredRevisionId": "<revision-id>"
  }
}

Then run:

bash
curl -s -X POST "https://slides.googleapis.com/v1/presentations/<presentation-id>:batchUpdate" --header "Authorization: Bearer $GOOGLE_DRIVE_TOKEN" --header "Content-Type: application/json" -d @/tmp/google_slides_request.json | jq '{presentationId, writeControl}'

The Slides API creates the speaker notes shape automatically when it receives a valid text operation using a speakerNotesObjectId that does not yet have a shape.

5. Create a Presentation

Write to /tmp/google_slides_request.json:

json
{
  "title": "Quarterly Review"
}

Then run:

bash
curl -s -X POST "https://slides.googleapis.com/v1/presentations" --header "Authorization: Bearer $GOOGLE_DRIVE_TOKEN" --header "Content-Type: application/json" -d @/tmp/google_slides_request.json | jq '{presentationId, title, url: ("https://docs.google.com/presentation/d/" + .presentationId + "/edit")}'

6. Replace Text Throughout a Presentation

Write to /tmp/google_slides_request.json:

json
{
  "requests": [
    {
      "replaceAllText": {
        "containsText": {
          "text": "Old text",
          "matchCase": true
        },
        "replaceText": "New text"
      }
    }
  ],
  "writeControl": {
    "requiredRevisionId": "<revision-id>"
  }
}

Then run:

bash
curl -s -X POST "https://slides.googleapis.com/v1/presentations/<presentation-id>:batchUpdate" --header "Authorization: Bearer $GOOGLE_DRIVE_TOKEN" --header "Content-Type: application/json" -d @/tmp/google_slides_request.json | jq '.replies[0].replaceAllText'

7. Create a Slide

Write to /tmp/google_slides_request.json:

json
{
  "requests": [
    {
      "createSlide": {
        "insertionIndex": 1,
        "slideLayoutReference": {
          "predefinedLayout": "TITLE_AND_BODY"
        }
      }
    }
  ],
  "writeControl": {
    "requiredRevisionId": "<revision-id>"
  }
}

Then run:

bash
curl -s -X POST "https://slides.googleapis.com/v1/presentations/<presentation-id>:batchUpdate" --header "Authorization: Bearer $GOOGLE_DRIVE_TOKEN" --header "Content-Type: application/json" -d @/tmp/google_slides_request.json | jq '.replies[0].createSlide.objectId'

8. Get a Slide Thumbnail

bash
curl -s "https://slides.googleapis.com/v1/presentations/<presentation-id>/pages/<page-object-id>/thumbnail" --header "Authorization: Bearer $GOOGLE_DRIVE_TOKEN" | jq '{contentUrl, width, height}'

Guidelines

  1. Read the latest presentation and revision ID immediately before writing.
  2. Use writeControl.requiredRevisionId to avoid overwriting concurrent edits.
  3. Batch related changes so dependent requests succeed or fail together.
  4. Only the text inside the speaker notes shape is editable; other notes-page properties are read-only.
  5. Preserve slide content and design when the request only concerns speaker notes.
  6. Request presentations.write only when a mutation is required.

Frequently asked questions

What does the Google Slides AI skill do?

Google Slides API for reading and editing presentations and speaker notes. Use when user mentions "Google Slides", "slides", "presentation", "speaker notes", or shares a docs.google.com/presentation link.

Why use Google Slides on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vm0-ai/vm0-skills/tree/main/google-slides. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Google Slides?

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 Google Slides?

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

Is the Google Slides AI skill free?

It is published on GitHub by vm0-ai. Check the repository for licensing terms. 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 👇