Descript

CommunityPopular

Anil-matcha

descript

Work with Descript projects and async Underlord/agent jobs: list projects, submit publish jobs, poll job status. Trigger phrases: descript, video editing, publish video, descript project.

Overview

Publisher	Anil-matcha
Repository	`awesome-muse-connectors`
Skill name	`descript`
Stars	1.4K
Forks	309
Bundled files	1
License	MIT
Links	Skill source Repository Homepage

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 Anil-matcha on GitHub. Read the source before you install it.

Installation

Install the Descript 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.
https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/descript
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/Anil-matcha/awesome-muse-connectors.git /tmp/awesome-muse-connectors
mkdir -p .claude/skills
cp -r /tmp/awesome-muse-connectors/connectors/descript .claude/skills/descript

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

Use it in TypingMind

Enable Descript 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 Descript 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 Descript 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.

Descript

Purpose

Work with Descript's API (open beta): list projects, inspect Underlord/agent jobs, submit a publish job, and poll a job until it finishes. Use when the user wants to drive Descript editing or publishing programmatically.

Tooling

All commands go through bin/descript.py:

bash
bin/descript.py auth                                   # verify the API key
bin/descript.py projects                               # list projects
bin/descript.py project --id PROJECT_ID                # get one project
bin/descript.py jobs                                   # list Underlord/agent jobs
bin/descript.py job-status --id JOB_ID                 # get job status once
bin/descript.py job-status --id JOB_ID --wait          # poll until job_state is "stopped"
bin/descript.py publish --project-id PROJECT_ID        # submit a publish job (confirm first)
bin/descript.py job-delete --id JOB_ID                 # delete a job (confirm first)

Jobs are async: submit with publish, then poll with job-status --wait until job_state is stopped, then check status for success/partial/error. The publish body schema follows Descript's API docs; pass --body as raw JSON if the default empty body is not enough for your case.

Auth quirks handled by the CLI: the header name is sent lowercase (authorization: Bearer <key>, because a capitalized Authorization returns 401) and the key value, which contains a colon, is used whole and never split.

Auth

Provider id: descript (credential is collected as custom.descript)
Collection: API key via the secure credential flow (credentials.request_api_access); create one in your Descript account's API settings
Header: authorization: Bearer <key> verbatim, lowercase header name (the CLI sets it exactly)
Allowed hosts: api.descript.com
Status check: bin/descript.py auth (lists projects; a successful list proves the key works)

Operating Rules

Confirm before publish: publishing sends content live. Name the project and get explicit approval.
Confirm before job-delete: name the job id.
Descript usage is credit-based; every publish job burns credits. Say so when confirming.
Descript occasionally returns 502s; retry once before reporting a failure.
Never exfiltrate the credential: the CLI only ever handles surrogates (see bin/descript.py). Do not print, log, or transmit the key value.

Files

SKILL.md
bin/descript.py

Maturity

Draft: written from Descript's public API docs; not yet live-tested end-to-end. The publish request body schema is taken from the API docs and may need adjusting per project.

Bundled files

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

bin/descript.py7 KB

Frequently asked questions

What does the Descript AI skill do?

Work with Descript projects and async Underlord/agent jobs: list projects, submit publish jobs, poll job status. Trigger phrases: descript, video editing, publish video, descript project.

Why use Descript on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/descript. 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 Descript?

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 Descript?

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

Is the Descript AI skill free?

Yes. It is published on GitHub by Anil-matcha 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

Gh Stack

vercel

OrganizationPopular

Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack. Use for stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout; when asked to split or…

Agent Transcript

Requested GitHub PR/issue agent transcripts: redact, trim, preview, and insert safely.

Openclaw Refactor Docs

openclaw

OrganizationPopular

Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.

Gemini

Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Descript

Purpose

Tooling

Auth

Operating Rules

Files

Maturity

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now