Agent skill

Youtube Studio Computer Use

by swyxio in swyxio/skills

Automate YouTube Studio through tab-bound Chrome control when API access is unavailable, insufficient, or slower for Studio-only edits.

MITAuto-check passedProductivity & Automation

Install Youtube Studio Computer Use

skills CLI
$ npx skills add swyxio/skills --skill youtube-studio-computer-use -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install swyxio/skills youtube-studio-computer-use --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/youtube-studio-computer-use .claude/skills/youtube-studio-computer-use && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
youtube-studio-computer-use
GitHub stars
176
Token cost
~1.4k tokens
SKILL.md length
749 words
Files
4 (incl. scripts, references)
Skills in repo
89
Repo updated
First seen
Licence
MIT

At a glance

Automate YouTube Studio through tab-bound Chrome control when API access is unavailable, insufficient, or slower for Studio-only edits.

  • Works in 5 steps: Bind a dedicated Studio tab and open the… → Wait for the edit page to be fully… → Use tab-bound accessibility actions or… → …
  • Editing existing videos
  • SKILL.md covers Use This Skill, Ground Rules, Browser Automation Pattern and Thumbnails, plus 2 more sections
  • Runs Python scripts from its folder; reaches studio.youtube.com

What it does

Youtube Studio Computer Use is an agent skill from swyxio/skills. Automate YouTube Studio through tab-bound Chrome control when API access is unavailable, insufficient, or slower for Studio-only edits. Use for editing existing videos, adding thumbnails, changing visibility, scheduling, selecting playlists, and verifying saved Studio state. Prefer API or youtube-studio-batch-upload for pure upload/download/metadata preparation when stable API credentials or batch upload workflows are available.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/studio-dom-patterns.md` and `scripts/studio_edit_driver.py`).

It sits in Productivity & Automation, covering Desktop control. It works with YouTube. The repository describes itself as: Agent skills for Claude Code and other AI agents. The licence is MIT.

When your agent uses it

  • Editing existing videos
  • Adding thumbnails
  • Changing visibility
  • Selecting playlists

Example prompts

  • “/youtube-studio-computer-use”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Bind a dedicated Studio tab and open the edit page: https://studio.youtube.com/video//edit. Verify the channel and video ID.
  2. Wait for the edit page to be fully rendered. Require body text, a thumbnail/input area when needed, and the Edit video visibility status…
  3. Use tab-bound accessibility actions or locators. Use DOM evaluation only within the current adapter's documented capabilities; do not…
  4. Use the adapter's file-chooser interface for uploads. Use native Computer Use only for unsupported native controls after coordinating…
  5. Save, wait, verify, and append to the ledger before continuing.

What it can do on your machine

Read from SKILL.md and the folder at commit 038ef34. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • studio.youtube.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Youtube Studio Computer Use loads about 1.4k tokens when it runs, and up to ~3k if it reads all its reference files. Until then it costs about 115 tokens; SKILL.md has 749 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~115
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from swyxio/skills at commit 038ef34, republished under its MIT licence (© swyxio). 749 words, ~1,432 tokens.

Download SKILL.mdSave it as .claude/skills/youtube-studio-computer-use/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
youtube-studio-computer-use
description
Automate YouTube Studio through tab-bound Chrome control when API access is unavailable, insufficient, or slower for Studio-only edits. Use for editing existing videos, adding thumbnails, changing visibility, scheduling, selecting playlists, and verifying saved Studio state. Prefer API or youtube-studio-batch-upload for pure upload/download/metadata preparation when stable API credentials or batch upload workflows are available.

YouTube Studio Computer Use

Use This Skill

Use this skill when the task must operate the live YouTube Studio UI in Chrome:

  • Add or replace thumbnails on existing videos.
  • Schedule or reschedule videos through Studio visibility controls.
  • Fix metadata, playlist, audience, visibility, or save states when API setup is missing.
  • Batch a series of Studio edit-page operations with a ledger and recovery list.
  • Inspect DOM state and use tab-bound controls for fragile UI states.

Use youtube-studio-batch-upload instead when the primary job is downloading source videos, staging filenames, building metadata, uploading new videos, or keeping upload ledgers. Use an official YouTube API flow when OAuth/API credentials already exist and the operation is supported cleanly, especially for bulk metadata reads/writes. This skill is for the messy browser path.

Ground Rules

  • Follow resilient-computer-use. The user and other Codex chats may use Chrome concurrently: bind a dedicated Studio tab by stable ID and keep observations, actions, screenshots, and network inspection scoped to it.
  • Inspect fresh state from that tab before UI actions. Do not activate a frontmost window or use AppleScript as the default control path. Coordinate shared focus before any native desktop fallback.
  • Keep a local status JSON/CSV ledger with video_id, title, action, target time, thumbnail path, ok, error, and verification text.
  • Save each video before moving to the next. Verify All changes saved and the intended side-panel state, such as Visibility Scheduled.
  • After interruptions, recover the same tab binding and verify channel/video identity and saved state before retrying. Do not take over another chat's tab.
  • Do not publish private/internal source URLs or notes while making metadata changes.

Browser Automation Pattern

Use the documented tab-bound browser adapter for page operations:

  1. Bind a dedicated Studio tab and open the edit page: https://studio.youtube.com/video/<video_id>/edit. Verify the channel and video ID.
  2. Wait for the edit page to be fully rendered. Require body text, a thumbnail/input area when needed, and the Edit video visibility status control.
  3. Use tab-bound accessibility actions or locators. Use DOM evaluation only within the current adapter's documented capabilities; do not bypass restrictions with AppleScript or injected scripts.
  4. Use the adapter's file-chooser interface for uploads. Use native Computer Use only for unsupported native controls after coordinating shared focus, then return to the tab binding.
  5. Save, wait, verify, and append to the ledger before continuing.

For detailed snippets and known failure modes, read references/studio-dom-patterns.md.

Thumbnails

Use the documented tab-bound file-chooser flow for thumbnail replacement:

  • Inspect the rendered Thumbnail section and identify its upload control.
  • Start the chooser wait, click the upload control through the bound tab, and set the local file through the returned chooser. See browser upload examples.
  • Verify the new preview and wait for Uploading... to clear before saving. Do not substitute localhost fetch or DOM injection when the adapter restricts them.

If Studio shows the new thumbnail but the status object still says pending, inspect the page before retrying; retrying may replace the same thumbnail harmlessly, but do not save until Studio is done uploading.

Show full SKILL.md (252 more words)Show less

Scheduling

Scheduling is fragile because YouTube Studio validates hidden component state, not just input text.

  • Open the visibility popup using the Edit video visibility status control.
  • Select Schedule, then set the date and time.
  • For date, opening the date picker and clicking the visible day is more reliable than assigning text.
  • For time, click the time field and choose the visible listbox option such as 8:30 AM. Merely setting input.value = "8:30 AM" can display the right value while leaving Done disabled.
  • Confirm Done is enabled before clicking it.
  • Click page-level Save, then wait until All changes saved and the side panel shows Visibility Scheduled.

For spaced launches, generate slot times in the local YouTube timezone, e.g. start at 9:30 AM and add 30 minutes per video. Record every assigned time in the ledger.

Recovery

Common recoveries:

  • missing file input: the thumbnail section has not rendered. Scroll to Thumbnail and wait again.
  • thumbnail still uploading: inspect the bound tab's upload progress and preview before retrying; reconcile whether the file was already accepted.
  • Done disabled after setting time: choose the time from the dropdown listbox; do not type or assign the value only.
  • missing schedule: the visibility popup did not open or is still collapsed. Re-open the visibility control and inspect visible popup text.
  • Wrong page or lost binding: recover the exact Studio tab ID and inspect fresh tab state before continuing.

Never bulldoze through failures in a batch. Stop, patch the driver, and resume from the ledger with the next available publish slot.

© swyxio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in youtube-studio-computer-use of swyxio/skills.

  • SKILL.md
  • agents/openai.yaml
  • references/studio-dom-patterns.md
  • scripts/studio_edit_driver.py

Open the folder on GitHubat commit 038ef34

Compare with similar skills

Youtube Studio Computer Use next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Youtube Studio Computer Use compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Youtube Studio Computer Use this skillswyxio/skills176—~1.4kAutomated safety check: PassMIT
Vision SkillsAnionex/agent-vision-toolkit1.2k—~4kAutomated safety check: PassMIT
Mac Computer UseTo3akaRin/mac-computer-use1.1k—~495Automated safety check: PassMIT
Crabbox Appsopenclaw/openclaw392k—~1.5kAutomated safety check: PassMIT
Agent Managementautonomous-ai/Physical-AI-Operating-System407—~1.7kAutomated safety check: PassApache-2.0
Computer Usebam-bam-2/solo-skills3671 repos~915Automated safety check: PassMIT

Similar skills

  • Vision Skills

    Anionex/agent-vision-toolkit

    Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and…

    1.2k GitHub stars~4k tokensUpdated 2 days ago
    Productivity & AutomationAuto-check passed
  • Mac Computer Use

    To3akaRin/mac-computer-use

    操作 macOS 桌面应用,探测窗口和自动化接口、截图、读取或修改辅助功能元素、执行鼠标键盘动作,以及通过 CDP 操作内嵌 Chromium 页面。适用于桌面应用自动化与界面验收;普通网页任务优先使用已有浏览器工具。

    1.1k GitHub stars~495 tokensUpdated 16 days ago
    Productivity & AutomationAuto-check passed
  • Crabbox Apps

    openclaw/openclaw

    A skill your agent uses when asked to open, run, test, or show an app in Crabbox, including native desktops, web previews, and computer use on a temporary machine.

    392k GitHub stars~1.5k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Agent Management

    autonomous-ai/Physical-AI-Operating-System

    Legacy Autonomous Buddy control for explicitly requested Buddy coding sessions.

    407 GitHub stars~1.7k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Computer Use

    bam-bam-2/solo-skills

    Use Orca's computer-use CLI to inspect and operate local desktop app windows through accessibility trees, screenshots, and safe UI actions.

    367 GitHub starsUsed in 1 repo~915 tokens
    Productivity & AutomationAuto-check passed
  • Cloud Computer Use

    davidondrej/cloudroom-core

    See and control desktop apps on this Cloud sandbox’s virtual Linux screen with cloudroom computer-use: launch GUI apps you build or install, read their UI, click, type, and take screenshots.

    282 GitHub stars~881 tokensUpdated yesterday
    Productivity & AutomationAuto-check: notes

More from swyxio/skills

All 89 skills in this repo
  • Programmatic Agents

    swyxio/skills

    Run a selected coding-agent CLI programmatically, with latency, error, usage, cost, and trace logging.

    176 GitHub stars~2.2k tokensUpdated 5 days ago
    Auto-check passed
  • Design, implement, audit, or refresh protected username and handle namespaces for public products.

    176 GitHub stars~1.1k tokensUpdated 5 days ago
    Auto-check passed
  • New Mac Setup

    swyxio/skills

    Fully automated new Mac setup for fullstack web developers and AI engineers.

    176 GitHub stars~4.3k tokensUpdated 5 days ago
    Auto-check passed
  • Youtube API

    swyxio/skills

    Manage YouTube videos programmatically via the YouTube Data API v3 — upload video files, upload custom thumbnails, update video metadata (titles, descriptions, tags), and query video/channel info…

    176 GitHub stars~2.2k tokensUpdated 5 days ago
    Auto-check passed
  • Batch YouTube Studio upload workflow for videos sourced from Airtable, Google Drive, Loom, YouTube, or local files.

    176 GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-check: warnings
  • Reconstruct and visually analyze paired agent, game, or policy trajectories to determine whether changed actions produced their intended effects.

    176 GitHub stars~1.8k tokensUpdated 5 days ago
    Auto-check passed

Works with

Questions about Youtube Studio Computer Use

What does Youtube Studio Computer Use do?

Automate YouTube Studio through tab-bound Chrome control when API access is unavailable, insufficient, or slower for Studio-only edits. Youtube Studio Computer Use is an agent skill from swyxio/skills. Automate YouTube Studio through tab-bound Chrome control when API access is unavailable, insufficient, or slower for Studio-only edits.

When should I use Youtube Studio Computer Use?

Youtube Studio Computer Use fits situations like: editing existing videos; adding thumbnails; changing visibility; selecting playlists.

How do I install Youtube Studio Computer Use in Claude Code?

Run `npx skills add swyxio/skills --skill youtube-studio-computer-use -a claude-code`. Or copy the skill folder (youtube-studio-computer-use in swyxio/skills) into .claude/skills/youtube-studio-computer-use in your project. Claude Code loads it when a task matches its description.

How do I install Youtube Studio Computer Use in Codex?

Run `npx skills add swyxio/skills --skill youtube-studio-computer-use -a codex`. Or copy the skill folder (youtube-studio-computer-use in swyxio/skills) into .agents/skills/youtube-studio-computer-use in your project. Codex loads it when a task matches its description.

Can I use Youtube Studio Computer Use in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add swyxio/skills --skill youtube-studio-computer-use -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/youtube-studio-computer-use, .gemini/skills/youtube-studio-computer-use, .github/skills/youtube-studio-computer-use and .opencode/skills/youtube-studio-computer-use in your project.

What does Youtube Studio Computer Use need to run?

Going by SKILL.md and its folder, Youtube Studio Computer Use needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Youtube Studio Computer Use access the network?

SKILL.md names 1 domain. In commands or code: studio.youtube.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Youtube Studio Computer Use safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Youtube Studio Computer Use use?

Youtube Studio Computer Use is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Youtube Studio Computer Use use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.

What are the alternatives to Youtube Studio Computer Use?

Skills that share tags, products or a category with Youtube Studio Computer Use: Vision Skills (Anionex/agent-vision-toolkit, 1.2k stars), Mac Computer Use (To3akaRin/mac-computer-use, 1.1k stars), Crabbox Apps (openclaw/openclaw, 392k stars) and Agent Management (autonomous-ai/Physical-AI-Operating-System, 407 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Youtube Studio Computer Use?

swyxio (a GitHub user) maintains it in swyxio/skills, which has 176 GitHub stars. The repository holds 89 skills in this directory. The repository was last updated on October 5, 2026.

Source: swyxio/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.