Video Generation
bytedance/deer-flow
Generates short videos from a structured JSON prompt, optionally guided by a reference image used as the first or last frame.
Turns a one-line topic, full script or SRT file into Vox-style paper-cut collage video prompts and JSON for Google Flow, planning subtitle shots first and confirming choices twice.
SKILL.md written in Chinese; this summary is our English description.
Install VoxEasy Video Prompt Director
$ npx skills add louchi1984-coder/voxeasy --skill voxeasy -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install louchi1984-coder/voxeasy voxeasy --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "voxeasy" agent skill from https://github.com/louchi1984-coder/voxeasy/tree/main into .claude/skills/voxeasy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "voxeasy", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add louchi1984-coder/voxeasy --skill voxeasy -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install louchi1984-coder/voxeasy voxeasy --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "voxeasy" agent skill from https://github.com/louchi1984-coder/voxeasy/tree/main into .agents/skills/voxeasy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "voxeasy", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add louchi1984-coder/voxeasy --skill voxeasy -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install louchi1984-coder/voxeasy voxeasy --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "voxeasy" agent skill from https://github.com/louchi1984-coder/voxeasy/tree/main into .cursor/skills/voxeasy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "voxeasy", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add louchi1984-coder/voxeasy --skill voxeasy -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install louchi1984-coder/voxeasy voxeasy --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "voxeasy" agent skill from https://github.com/louchi1984-coder/voxeasy/tree/main into .gemini/skills/voxeasy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "voxeasy", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install louchi1984-coder/voxeasy voxeasyInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add louchi1984-coder/voxeasy --skill voxeasy -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "voxeasy" agent skill from https://github.com/louchi1984-coder/voxeasy/tree/main into .github/skills/voxeasy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "voxeasy", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add louchi1984-coder/voxeasy --skill voxeasy -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install louchi1984-coder/voxeasy voxeasy --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "voxeasy" agent skill from https://github.com/louchi1984-coder/voxeasy/tree/main into .opencode/skills/voxeasy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "voxeasy", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
voxeasy- GitHub stars
- 116
- Token cost
- ~977 tokens
- SKILL.md length
- 220 words
- Files
- 37 (incl. scripts, references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- None found
At a glance
Turns a one-line topic, full script or SRT file into Vox-style paper-cut collage video prompts and JSON for Google Flow, planning subtitle shots first and confirming choices twice.
- Works in 7 steps: 接收一句话、完整文案或 SRT；时效性事实与数据先检索验证。 → 完整读取… → 第一次确认字幕、Shot 边界、原始时间、空白和吸附时长；确认前不设计画面。 → …
- Making a Vox-style short video prompt set from a one-line topic
- SKILL.md covers 固定流程, 运行中反馈闭环, 输入与标题 and 参数选择, plus 3 more sections
- Runs Python scripts from its folder; calls python3
What it does
The skill runs in a strict order: plan subtitle shots first, choose parameters next, pick an expression method before translating it into a visual style, and output prompts only after the visual design is confirmed. Input can be a one-line topic, which gets a voiceover script and candidate titles, a full script, kept as written and only grouped and timed, or an SRT file whose original timeline is preserved. Shots are rounded up to 4, 6, 8 or 10 seconds, and a validate_timeline.py script checks an SRT-based plan.
You confirm twice: first the subtitles, shot boundaries and durations, then the full visual design. You also choose the model, the real output aspect ratio and the style yourself; the recommended defaults are Google Flow with Omni Flash and 9:16. For square output, key content goes into a central 1:1 safe area. Each shot carries one core message and one main expression method, judged in order from direct presentation to story scene to visual metaphor, and the final output is an audio-visual table, per-shot prompts and JSON.
A self-learning mechanism records successes, failures and corrections through scripts/self_learning.py. Candidate improvements apply only after passing thresholds, backups and regression checks, and five successful uses only trigger a review, never an automatic change to the skill.
When your agent uses it
- Making a Vox-style short video prompt set from a one-line topic
- Planning subtitle shots from an SRT file while keeping its original timing
- Producing Google Flow prompts and a JSON timeline for a finished script
- Testing a prompt for a single shot before building the whole video
Example prompts
- “用一句话主题“为什么咖啡越喝越困”做一条 Vox 风短视频的 Flow Prompt。”
- “Turn ./subtitles/episode.srt into Vox-style shots, and ask me to confirm the shot boundaries first.”
- “Make a single-shot test prompt for the opening scene of my script about city bike lanes.”
Requirements
- Python 3, for the validation and self-learning scripts
- Access to Google Flow, to use the generated prompts
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- 接收一句话、完整文案或 SRT；时效性事实与数据先检索验证。
- 完整读取 references/timeline-rules.md，按语义和连续时间区间规划 Shot，并向上吸附为 4/6/8/10 秒。
- 第一次确认字幕、Shot 边界、原始时间、空白和吸附时长；确认前不设计画面。
- 让用户明确选择模型、实际生成比例和视觉风格。默认值只能推荐，不能视为已选。
- 完整读取 references/expression-routing.md，逐 Shot 执行：字幕含义 → 核心信息 → 表达方式 → 场景锚点或隐喻映射 → 所选风格转译 → 构图、文字、动作、运镜。
- 第二次确认完整视觉设计；确认前不输出最终英文 Prompt。
- 完整读取 references/output-contract.md，输出声画表、逐 Shot Prompt 与 JSON。用户确认成功或进入无关的新任务后运行 python3 scripts/self_learning.py record-success；累计 5…
What it can do on your machine
Read from SKILL.md and the folder at commit 33023d4. 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, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
VoxEasy Video Prompt Director loads about 977 tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 35 tokens; SKILL.md has 220 words of instructions outside code blocks.
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
Without a licence we can't republish the file, so here is its outline and opening line. It has 220 words (~977 tokens).
- name
- voxeasy
Files
SKILL.md and 36 other files (scripts, references) in the repository root of louchi1984-coder/voxeasy.
- SKILL.md
- .gitignore
- README.md
- agents/interface.yaml
- agents/openai.yaml
- archive/voxeasy-v4.0-original.md
- evals/output/cases.jsonl
- evals/semantic_config.json
- evals/test_self_learning.py
- evals/timeline-invalid-short.json
- evals/timeline-valid.json
- evals/trigger-cases.json
- profiles/data.json
- profiles/lab.json
- profiles/news.json
- profiles/product.json
- … and 21 more
Open the folder on GitHubat commit 33023d4
Compare with similar skills
VoxEasy Video Prompt Director 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| VoxEasy Video Prompt Director this skilllouchi1984-coder/voxeasy | 116 | — | ~977 | Automated safety check: Pass | None | |
| Video Generationbytedance/deer-flow | 83k | 4 repos | ~1.4k | Automated safety check: Pass | MIT | |
| MoneyPrinterTurbo Video Generatorharry0703/MoneyPrinterTurbo | 129k | — | ~2.1k | Automated safety check: Warn | MIT | |
| Video Cover Imageitwanger/toBeBetterJavaer | 18k | — | ~3.3k | Automated safety check: Pass | None | |
| Vox DirectorAlisa0808/vox-director | 2.2k | — | ~5.6k | Automated safety check: Pass | MIT | |
| Gbro Collage Brollpyang5166/gbro-collage-broll | 1.3k | — | ~2.6k | Automated safety check: Notes | MIT |
Similar skills
MoneyPrinterTurbo Video Generator
harry0703/MoneyPrinterTurbo
Installs and runs MoneyPrinterTurbo to turn a topic or script into a finished short video with voice-over, subtitles, stock footage and music.
Video Cover Image
itwanger/toBeBetterJavaer
Generate matched 3:4, 16:9, and 4:3 short-video cover images from toBeBetterJavaer video scripts or AI/Java technical topics.
Vox Director
Alisa0808/vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all…
Gbro Collage Broll
pyang5166/gbro-collage-broll
将约 5 秒口播文稿、观点句或抽象概念做成高级 editorial halftone paper-collage / 半调纸拼贴 B-roll。用户说“collage b-roll”“纸拼贴 b-roll”“半调拼贴”“拼贴风格配画面”“用这段文稿做拼贴动画”“gbro-collage-broll”，或希望把一句文稿转成拼贴视觉隐喻时，必须使用此…
VRGDG H3 Short Film Pipeline
vrgamegirl19/comfyui-vrgamedevgirl
Builds an AI short film in a local ComfyUI with the VRGDG Video Builder, MiniMax H3 scenes, reference images, a music score, QA and a final edit.
Related
Works with
Categories
Questions about VoxEasy Video Prompt Director
What does VoxEasy Video Prompt Director do?
Turns a one-line topic, full script or SRT file into Vox-style paper-cut collage video prompts and JSON for Google Flow, planning subtitle shots first and confirming choices twice. The skill runs in a strict order: plan subtitle shots first, choose parameters next, pick an expression method before translating it into a visual style, and output prompts only after the visual design is confirmed. Input can be a one-line topic, which gets a voiceover script and candidate titles, a full script, kept as written and only grouped and timed, or an SRT file whose original timeline is preserved.
When should I use VoxEasy Video Prompt Director?
VoxEasy Video Prompt Director fits situations like: making a Vox-style short video prompt set from a one-line topic; planning subtitle shots from an SRT file while keeping its original timing; producing Google Flow prompts and a JSON timeline for a finished script; testing a prompt for a single shot before building the whole video.
How do I install VoxEasy Video Prompt Director in Claude Code?
Run `npx skills add louchi1984-coder/voxeasy --skill voxeasy -a claude-code`. Or copy the skill folder (the louchi1984-coder/voxeasy repository) into .claude/skills/voxeasy in your project. Claude Code loads it when a task matches its description.
How do I install VoxEasy Video Prompt Director in Codex?
Run `npx skills add louchi1984-coder/voxeasy --skill voxeasy -a codex`. Or copy the skill folder (the louchi1984-coder/voxeasy repository) into .agents/skills/voxeasy in your project. Codex loads it when a task matches its description.
Can I use VoxEasy Video Prompt Director 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 louchi1984-coder/voxeasy --skill voxeasy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/voxeasy, .gemini/skills/voxeasy, .github/skills/voxeasy and .opencode/skills/voxeasy in your project.
What does VoxEasy Video Prompt Director need to run?
Going by SKILL.md and its folder, VoxEasy Video Prompt Director needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3, for the validation and self-learning scripts; Access to Google Flow, to use the generated prompts.
Does VoxEasy Video Prompt Director access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is VoxEasy Video Prompt Director 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 VoxEasy Video Prompt Director use?
No licence was found for VoxEasy Video Prompt Director or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does VoxEasy Video Prompt Director use?
About 977 tokens (SKILL.md is roughly 3.9k 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 9.4k tokens, read only when the agent opens those files.
What are the alternatives to VoxEasy Video Prompt Director?
Skills that share tags, products or a category with VoxEasy Video Prompt Director: Video Generation (bytedance/deer-flow, 83k stars), MoneyPrinterTurbo Video Generator (harry0703/MoneyPrinterTurbo, 129k stars), Video Cover Image (itwanger/toBeBetterJavaer, 18k stars) and Vox Director (Alisa0808/vox-director, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains VoxEasy Video Prompt Director?
louchi1984-coder (a GitHub user) maintains it in louchi1984-coder/voxeasy, which has 116 GitHub stars. The repository was last updated on August 16, 2026.
Source: louchi1984-coder/voxeasy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.