Summarizer

Organization

zoom

summarizer

Zoom AI Services Summarizer for synchronous transcript summarization and asynchronous batch summary jobs. Use for conversation recaps, action items, detailed summaries, Build-platform JWT auth, S3 transcript archives, and webhook-driven summary pipelines.

Overview

Publisher	zoom
Repository	`skills`
Skill name	`summarizer`
Stars	78
Forks	16
Bundled files	8
License	MIT
Links	Skill source Repository

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.
8 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by zoom on GitHub. Read the source before you install it.

Installation

Install the Summarizer 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.
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/zoom/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/summarizer .claude/skills/summarizer

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

Use it in TypingMind

Enable Summarizer 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 Summarizer 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 Summarizer 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.

Zoom AI Services Summarizer

Current API audit: Official docs and OpenAPI were rechecked on 2026-07-10. The May 21, 2026 release added batch job listing/cancellation and a details field on batch file list/detail responses; all endpoints are included below.

Implementation guidance for Zoom AI Services Summarizer across:

synchronous inline transcript summarization (POST /aiservices/summarizer/summarize)
asynchronous batch transcript-file jobs (/aiservices/summarizer/jobs*)
recap, action item, detailed summary, and combined summary tasks
Build-platform JWT generation and server-side credential handling
webhook-driven batch status updates

Official docs:

https://developers.zoom.us/docs/ai-services/
https://developers.zoom.us/docs/ai-services/summarizer/
https://developers.zoom.us/docs/ai-services/summarizer/fast-mode/
https://developers.zoom.us/docs/ai-services/summarizer/batch-mode/
https://developers.zoom.us/api-hub/ai-services/methods/endpoints.json
Quickstart sample: https://github.com/zoom/ai-services-quickstart/

Routing Guardrail

If the user already has transcript or dialogue text and needs a recap, summary, action items, or full summary, route here first.
If the user has audio/video media and needs text first, route to ../scribe/SKILL.md, then chain here.
If the user needs plain text translated, route to ../translator/SKILL.md.
If the user needs live meeting media before summarization, route to ../rtms/SKILL.md.
If the user needs the raw AI Services endpoint inventory, chain ../rest-api/SKILL.md.
If the user needs webhook signature patterns, optionally chain ../webhooks/SKILL.md.

Core Workflow

Get Build-platform API key and API secret.
Generate an HS256 JWT server-side.
Choose fast mode for inline transcript text or batch mode for stored transcript files.
Select the summarization task: recap, summary, action_items, or full_summary.
Submit the request and persist result.text or batch output files.
For batch jobs, poll job/file status or receive webhook notifications.

Endpoint Surface

Mode	Method	Path	Use
Fast	`POST`	`/aiservices/summarizer/summarize`	Synchronous summarization for inline transcript text
Batch	`POST`	`/aiservices/summarizer/jobs`	Submit asynchronous batch summarization job
Batch	`GET`	`/aiservices/summarizer/jobs`	List batch summarization jobs
Batch	`GET`	`/aiservices/summarizer/jobs/{jobId}`	Inspect job summary/state
Batch	`DELETE`	`/aiservices/summarizer/jobs/{jobId}`	Cancel queued/processing job
Batch	`GET`	`/aiservices/summarizer/jobs/{jobId}/files`	Inspect per-file results
Batch	`GET`	`/aiservices/summarizer/jobs/{jobId}/files/{fileId}`	Inspect one per-file result

Mode Selection

Need	Use
One bounded transcript string under `96 KB`	Fast mode
Many `.vtt`, `.srt`, or `.txt` transcript files in S3	Batch mode
Summary immediately in app UI	Fast mode
Archive or compliance pipeline	Batch mode plus polling/webhooks
Audio/video input	`scribe` first, then `summarizer`

Output Contract

Summarizer returns rendered text in result.text. Treat it as display-ready text or markdown-like content, depending on the requested task:

recap: concise recap
summary: detailed summary
action_items: action item sections grouped by owner
full_summary: recap, summary, and action items together

Chaining

Media to transcript to summary -> ../scribe/SKILL.md + summarizer
Summary to localized output -> summarizer + ../translator/SKILL.md
Batch webhook receiver -> summarizer + ../webhooks/SKILL.md
Raw endpoint discovery -> ../rest-api/SKILL.md
Cross-product routing -> ../general/SKILL.md

Operations

RUNBOOK.md - 5-minute preflight and debugging checklist.

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 Summarizer AI skill do?

Why use Summarizer on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zoom/skills/tree/main/skills/summarizer. 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 Summarizer?

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 Summarizer?

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

Is the Summarizer AI skill free?

Yes. It is published on GitHub by zoom 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

Pr Walkthrough

tldraw

OrganizationPopular

Create a narrated video walkthrough of a pull request with code slides and audio narration. Use when asked to create a PR walkthrough, PR video, or walkthrough video.

Cli Hub Matrix Game Development

HKUDS

OrganizationPopular

Capability-based multi-tool matrix for game development: engine, 3D/2D/audio assets, AI-generated assets, agent playtesting, packaging, store publishing, and telemetry.

Cli Hub Matrix Video Creation

HKUDS

OrganizationPopular

Capability-based multi-tool matrix for video production. Agents pick providers (CLI-Anything harnesses, public CLIs, Python libs, native binaries, cloud APIs) per capability rather than marching…

Cli Hub Meta Skill

Discover agent-native CLIs for professional software. Access the live catalog to find tools for creative workflows, productivity, AI, and more.

Summarizer

Overview