A skill your agent uses when コレクションの YouTube サムネイル(thumbnail.jpg)を CTR 最適化し、実効 textrender.mode に従い、既定 aiburnin で文字入り候補を生成・承認してから textless 背景を作るとき、または deterministic で textless main.png/jpg…

Custom licenceAuto-check passedMedia & Creative

Install Thumbnail

skills CLI
$ npx skills add daiki-beppu/youtube-automation --skill thumbnail -a claude-code

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

GitHub CLI
$ gh skill install daiki-beppu/youtube-automation thumbnail --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/daiki-beppu/youtube-automation.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/thumbnail .claude/skills/thumbnail && 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
thumbnail
GitHub stars
169
Token cost
~11k tokens
SKILL.md length
2,760 words
Files
28 (incl. references)
Skills in repo
21
Repo updated
First seen
Licence
Custom licence

At a glance

A skill your agent uses when コレクションの YouTube サムネイル(thumbnail.jpg)を CTR 最適化し、実効 textrender.mode に従い、既定 aiburnin で文字入り候補を生成・承認してから textless 背景を作るとき、または deterministic で textless main.png/jpg…

  • Works in 3 steps: 既存参照の選択(新規生成しない) → テキストオーバーレイ(thumbnail.jpg) → 承認済み thumbnail から textless main を再生成
  • Tasks that involve A/B testing
  • SKILL.md covers 前後工程, 成果物, Overview and チャンネル制約入力(非停止), plus 18 more sections
  • Runs Python and Shell scripts from its folder; calls uv, bash and codex; needs OPENAI_API_KEY

What it does

Thumbnail is an agent skill from daiki-beppu/youtube-automation. Use when コレクションの YouTube サムネイル(thumbnail.jpg)を CTR 最適化し、実効 textrender.mode に従い、既定 aiburnin で文字入り候補を生成・承認してから textless 背景を作るとき、または deterministic で textless main.png/jpg を先行生成して実フォント合成するとき、--compare で生成済み候補を競合と 320px 比較するとき、--test で Studio の A/B テストを設計・記録するとき、--iterate で伸びた動画の勝因を次のサムネへ還元するとき、または --loop で textless main.png/jpg から Veo / fal.ai / Gemini Omni Flash のループ動画背景を生成するとき。「サムネイル生成」「画像生成」「アイキャッチ」「サムネ比較」「モバイル表示テスト」「サムネ A/B テスト」「Test & Compare」「伸びた動画のサムネ改善」「ループ動画」「Hailuo」「背景動画」「loop.mp4」で発動。競合の勝ちパターン分析は…

Its SKILL.md is about 11k tokens, which your agent loads only when the skill is triggered. The skill folder holds 28 other files, including reference files (for example `config.default.yaml`, `references/archive-approved-thumbnail.py` and `references/channel-adaptation.md`).

It sits in Media & Creative, covering A/B testing and AI video generation. It works with YouTube and fal. The repository describes itself as: YouTube チャンネル自動化 共有コア.

When your agent uses it

  • Tasks that involve A/B testing
  • Tasks that involve AI video generation

Example prompts

  • “/thumbnail”

Requirements

  • Python 3
  • A Bash shell
  • A credential in OPENAI_API_KEY

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. 既存参照の選択(新規生成しない)
  2. テキストオーバーレイ(thumbnail.jpg)
  3. 承認済み thumbnail から textless main を再生成

What it can do on your machine

Read from SKILL.md and the folder at commit 4725876. 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 script files (Python and Shell, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • uv
    • bash
    • codex
    • jq

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

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • OPENAI_API_KEY

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

Context cost

Thumbnail loads about 11k tokens when it runs, and up to ~49k if it reads all its reference files. Until then it costs about 152 tokens; SKILL.md has 2,760 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~152
When it runs · the whole SKILL.md, loaded when a task matches
~11k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~49k

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); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 2,760 words (~10,874 tokens).

“コレクション用サムネイルを config/skills/thumbnail.yaml(skill-config)に基づいて生成する。 チャンネルごとにスタイル・キャラ・参照画像が異なり、すべて skill-config から動的に読み取る。 画像生成プロバイダー(Gemini / OpenAI / codex)は image_generation.provider で切り替え可能。手動候補選択の共通契約は operator guide に従う。”

— opening of SKILL.md by daiki-beppu, Custom licence
name
thumbnail
purpose
作る

Read the full SKILL.md on GitHub

Files

SKILL.md and 27 other files (references) in .claude/skills/thumbnail of daiki-beppu/youtube-automation.

  • SKILL.md
  • config.default.yaml
  • references/archive-approved-thumbnail.py
  • references/channel-adaptation.md
  • references/codex-image-batch.sh
  • references/codex-image.sh
  • references/codex-prompt.py
  • references/compare.md
  • references/compare_thumbnails.py
  • references/finalize_planning_preview.py
  • references/generate_image.py
  • references/generate_loop_video.py
  • references/generation-workflows.md
  • references/history-schema.md
  • references/iterate.md
  • references/loop.md
  • references/operator-guide.md
  • references/prompt-schema.md
  • references/prompting.md
  • references/provider-guidance.md
  • … and 8 more

Open the folder on GitHubat commit 4725876

Compare with similar skills

Thumbnail 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.

Thumbnail compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Thumbnail this skilldaiki-beppu/youtube-automation169—~11kAutomated safety check: PassCustom licence
Generate Youtube Thumbnailkrusemediallc/arcads-claude-code1.6k—~2.4kAutomated safety check: NotesMIT
Video-to-Sprite Animation Generator0x0funky/agent-sprite-forge4.3k—~3.8kAutomated safety check: PassMIT
Character Design with genmediafal-ai-community/skills249—~1.3kAutomated safety check: PassNone
Seedance Faceless Channelrediumvex/ai-video-generator-claude406—~4.4kAutomated safety check: PassMIT
AI Marketing VideosNeverSight/learn-skills.dev2163 repos~2.1kAutomated safety check: PassNone

Similar skills

  • Generate Youtube Thumbnail

    krusemediallc/arcads-claude-code

    Generate high-CTR YouTube thumbnails using Nano Banana 2 via the Arcads external API.

    1.6k GitHub stars~2.4k tokensUpdated 16 days ago
    Media & CreativeAuto-check: notes
  • Video-to-Sprite Animation Generator

    0x0funky/agent-sprite-forge

    Turns one approved master still into a full set of animated action clips for a character, one image-to-video take per action, then packages them for a game engine.

    4.3k GitHub stars~3.8k tokensUpdated 2 days ago
    Media & CreativeAuto-check passed
  • Character Design with genmedia

    fal-ai-community/skills

    Builds consistent characters, reference and expression sheets, outfit variations and character-to-video shots with the genmedia CLI while keeping identity stable.

    249 GitHub stars~1.3k tokensUpdated 9 days ago
    Media & CreativeAuto-check passed
  • Seedance Faceless Channel

    rediumvex/ai-video-generator-claude

    Generate faceless content video prompts for Seedance 2.0 on Higgsfield.

    406 GitHub stars~4.4k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • AI Marketing Videos

    NeverSight/learn-skills.dev

    Create AI marketing videos for ads, promos, product launches, and brand content.

    216 GitHub starsUsed in 3 repos~2.1k tokens
    Media & CreativeAuto-check passed
  • Clean Cut

    hassancs91/claude-youtube-editor

    Step 1 of the AI Video Editor pipeline — turn raw talking-head footage into a clean master cut.

    322 GitHub stars~4.3k tokensUpdated 1 mo ago
    Media & CreativeAuto-check: notes

More from daiki-beppu/youtube-automation

All 21 skills in this repo
  • Analytics

    daiki-beppu/youtube-automation

    A skill your agent uses when YouTube Analytics の収集・分析・レポート表示を一括実行または一段だけ実行するとき。フラグなしは収集→分析→表示を状態判定付きで進める。公開済み動画の失速分析は --flop と videoid / collection / --since <N、登録者・再生回数など YouTube 統計の表示は --status…

    169 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Audit

    daiki-beppu/youtube-automation

    A skill your agent uses when 整合性・動画本体・公開後メタデータ・価値ループの監査を一括実行または一段だけ実行するとき。フラグなしは4監査を状態判定付きで進め、音楽ムード × サムネ × タイトルは --alignment、動画解析は --video、ローカルと YouTube のメタデータ整合は --metadata、価値ループは --value-loop…

    169 GitHub stars~975 tokensUpdated yesterday
    Auto-check passed
  • Channel Research

    daiki-beppu/youtube-automation

    A skill your agent uses when チャンネル調査を状態判定付きで一括実行または一段だけ実行するとき。競合データ収集は --benchmark、追加競合候補の発掘は --discover、TTP・ニッチ仮説の比較または収集済みデータ分析は --market、競合コメントからの視聴者インサイト抽出は --voice、競合サムネイルの上位群・下位群比較は…

    169 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Channel Strategy

    daiki-beppu/youtube-automation

    A skill your agent uses when チャンネル戦略を状態判定付きで一括実行または一段だけ実行するとき。第一ペルソナは --persona、視聴シーンは --scene、制作制約への翻訳は --constraints、開設後の方向性・ポジショニング・差別化の再検討は --direction…

    169 GitHub stars~897 tokensUpdated yesterday
    Auto-check passed
  • Distrokid Helper

    daiki-beppu/youtube-automation

    A skill your agent uses when コレクションの楽曲を DistroKid 配信用に準備し、distrokid-helper Chrome 拡張へ渡すローカルサーバーを起動したいとき(30-distrokid 生成 / disc 分割 / metadata.md / ジャケット 3000×3000 新規生成 / uv run yt-collection-serve…

    169 GitHub stars~3.1k tokensUpdated yesterday
    Auto-check passed
  • Extension

    daiki-beppu/youtube-automation

    A skill your agent uses when Chrome 拡張(suno-helper / distrokid-helper / community-helper)の導入・更新、または拡張向け collection server の起動・停止を行うとき。「拡張入れて」「extension 更新」「サーバー起動」で発動。排他的な --install / --update /…

    169 GitHub stars~520 tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Thumbnail

What does Thumbnail do?

A skill your agent uses when コレクションの YouTube サムネイル(thumbnail.jpg)を CTR 最適化し、実効 textrender.mode に従い、既定 aiburnin で文字入り候補を生成・承認してから textless 背景を作るとき、または deterministic で textless main.png/jpg…. Thumbnail is an agent skill from daiki-beppu/youtube-automation.

When should I use Thumbnail?

Thumbnail fits situations like: tasks that involve A/B testing; tasks that involve AI video generation.

How do I install Thumbnail in Claude Code?

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

How do I install Thumbnail in Codex?

Run `npx skills add daiki-beppu/youtube-automation --skill thumbnail -a codex`. Or copy the skill folder (.claude/skills/thumbnail in daiki-beppu/youtube-automation) into .agents/skills/thumbnail in your project. Codex loads it when a task matches its description.

Can I use Thumbnail 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 daiki-beppu/youtube-automation --skill thumbnail -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/thumbnail, .gemini/skills/thumbnail, .github/skills/thumbnail and .opencode/skills/thumbnail in your project.

What does Thumbnail need to run?

Going by SKILL.md and its folder, Thumbnail needs Python and a shell for the scripts in its folder, the command-line tools its instructions call (uv, bash, codex and jq) and credentials named OPENAI_API_KEY. Our summary lists: Python 3; A Bash shell; A credential in OPENAI_API_KEY.

Does Thumbnail access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Thumbnail 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. Review the folder before installing.

What licence does Thumbnail use?

Thumbnail has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Thumbnail use?

About 11k tokens (SKILL.md is roughly 43k 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 38k tokens, read only when the agent opens those files.

What are the alternatives to Thumbnail?

Skills that share tags, products or a category with Thumbnail: Generate Youtube Thumbnail (krusemediallc/arcads-claude-code, 1.6k stars), Video-to-Sprite Animation Generator (0x0funky/agent-sprite-forge, 4.3k stars), Character Design with genmedia (fal-ai-community/skills, 249 stars) and Seedance Faceless Channel (rediumvex/ai-video-generator-claude, 406 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Thumbnail?

daiki-beppu (a GitHub user) maintains it in daiki-beppu/youtube-automation, which has 169 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 7, 2026.

Source: daiki-beppu/youtube-automation on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.