AI Image Generation and Editing
zhayujie/CowAgent
Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.
Writes the final image prompt for a clear wide establishing shot of an empty scene, fixing foreground, midground, background, exits, floor, walls and key furnishings.
SKILL.md written in Chinese; this summary is our English description.
Install Scene Establishing-Shot Prompt
$ npx skills add chatfire-AI/huobao-drama --skill scene-prompt -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install chatfire-AI/huobao-drama scene-prompt --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/chatfire-AI/huobao-drama.git skills-src && mkdir -p .claude/skills && cp -r skills-src/backend/workspace/skills/prompt-generator/scene-prompt .claude/skills/scene-prompt && rm -rf skills-srcUse ~/.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/
Install the "scene-prompt" agent skill from https://github.com/chatfire-AI/huobao-drama/tree/master/backend/workspace/skills/prompt-generator/scene-prompt into .claude/skills/scene-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene-prompt", 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.
$skill-installer install https://github.com/chatfire-AI/huobao-drama/tree/master/backend/workspace/skills/prompt-generator/scene-promptType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add chatfire-AI/huobao-drama --skill scene-prompt -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install chatfire-AI/huobao-drama scene-prompt --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chatfire-AI/huobao-drama.git skills-src && mkdir -p .agents/skills && cp -r skills-src/backend/workspace/skills/prompt-generator/scene-prompt .agents/skills/scene-prompt && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "scene-prompt" agent skill from https://github.com/chatfire-AI/huobao-drama/tree/master/backend/workspace/skills/prompt-generator/scene-prompt into .agents/skills/scene-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene-prompt", 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 chatfire-AI/huobao-drama --skill scene-prompt -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install chatfire-AI/huobao-drama scene-prompt --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chatfire-AI/huobao-drama.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/backend/workspace/skills/prompt-generator/scene-prompt .cursor/skills/scene-prompt && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "scene-prompt" agent skill from https://github.com/chatfire-AI/huobao-drama/tree/master/backend/workspace/skills/prompt-generator/scene-prompt into .cursor/skills/scene-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene-prompt", 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.
$ gemini skills install https://github.com/chatfire-AI/huobao-drama.git --path backend/workspace/skills/prompt-generator/scene-prompt--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add chatfire-AI/huobao-drama --skill scene-prompt -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install chatfire-AI/huobao-drama scene-prompt --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chatfire-AI/huobao-drama.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/backend/workspace/skills/prompt-generator/scene-prompt .gemini/skills/scene-prompt && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "scene-prompt" agent skill from https://github.com/chatfire-AI/huobao-drama/tree/master/backend/workspace/skills/prompt-generator/scene-prompt into .gemini/skills/scene-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene-prompt", 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 chatfire-AI/huobao-drama scene-promptInstalls 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 chatfire-AI/huobao-drama --skill scene-prompt -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/chatfire-AI/huobao-drama.git skills-src && mkdir -p .github/skills && cp -r skills-src/backend/workspace/skills/prompt-generator/scene-prompt .github/skills/scene-prompt && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "scene-prompt" agent skill from https://github.com/chatfire-AI/huobao-drama/tree/master/backend/workspace/skills/prompt-generator/scene-prompt into .github/skills/scene-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene-prompt", 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 chatfire-AI/huobao-drama --skill scene-prompt -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install chatfire-AI/huobao-drama scene-prompt --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chatfire-AI/huobao-drama.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/backend/workspace/skills/prompt-generator/scene-prompt .opencode/skills/scene-prompt && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "scene-prompt" agent skill from https://github.com/chatfire-AI/huobao-drama/tree/master/backend/workspace/skills/prompt-generator/scene-prompt into .opencode/skills/scene-prompt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scene-prompt", 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
scene-prompt- GitHub stars
- 16k
- Token cost
- ~378 tokens
- SKILL.md length
- 43 words
- Files
- 4
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Writes the final image prompt for a clear wide establishing shot of an empty scene, fixing foreground, midground, background, exits, floor, walls and key furnishings.
- Writing a reusable background reference image prompt for a scene in a short drama
- SKILL.md covers 输出结构（按此顺序组装单段连贯描述，语言跟随会话语言指令）, 空间结构规则, 人物（硬性规则 · 最高优先级） and 视角与氛围, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Describing a location's layout so later shots stay spatially consistent
What it does
The prompt describes one fixed-camera wide shot with no people at all, laid out in foreground, midground and background layers, with the position and style of doors or passages, floor and wall materials and the main furnishings stated relative to each other. The image becomes the background reference anchor for every shot in that scene, so the layout must read clearly, stay self-consistent and be reusable.
Rules cover specifics: one or two foreground framing elements, two to four core furnishings with fixed relative positions, concrete lighting (source direction, color temperature, contrast), a stable eye-level or slightly high wide angle with no fisheye or tilt, and concrete wording for mood. The prompt must end by stating the scene is empty of people, and it forbids text, signage, watermarks and motion blur. The finished text is saved through a save_scene_final_prompt tool, which injects the project's visual style at the front. Language variants exist for English, Japanese and Korean.
When your agent uses it
- Writing a reusable background reference image prompt for a scene in a short drama
- Describing a location's layout so later shots stay spatially consistent
- Producing an empty-scene establishing shot with no characters
Example prompts
- “Write the final scene prompt for an abandoned factory floor at dusk, with no people.”
- “Describe a small noodle shop interior as a wide establishing shot with fixed furniture positions.”
Requirements
- A save_scene_final_prompt tool in the host application
What it can do on your machine
Read from SKILL.md and the folder at commit 26de7df. 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
No scripts in the folder and no shell commands in SKILL.md.
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
Scene Establishing-Shot Prompt loads about 378 tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 43 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); 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 43 words (~378 tokens).
- name
- scene-prompt
Files
SKILL.md and 3 other files in backend/workspace/skills/prompt-generator/scene-prompt of chatfire-AI/huobao-drama.
- SKILL.md
- SKILL.en.md
- SKILL.ja.md
- SKILL.ko.md
Open the folder on GitHubat commit 26de7df
Compare with similar skills
Scene Establishing-Shot Prompt 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 |
|---|---|---|---|---|---|---|
| Scene Establishing-Shot Prompt this skillchatfire-AI/huobao-drama | 16k | — | ~378 | Automated safety check: Pass | Custom licence | |
| AI Image Generation and Editingzhayujie/CowAgent | 47k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Structured Image Generationbytedance/deer-flow | 84k | 4 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Xiaohei Chinese Article Illustrationshelloianneo/ian-xiaohei-illustrations | 12k | 3 repos | ~470 | Automated safety check: Warn | MIT | |
| Canghe Comicfreestylefly/canghe-skills | 461 | 8 repos | ~3.2k | Automated safety check: Pass | None | |
| Nano Banana Pro Prompts Recommend SkillYouMind-OpenLab/nano-banana-pro-prompts-recommend-skill | 1.9k | 1 repos | ~4.1k | Automated safety check: Pass | None |
Similar skills
Structured Image Generation
bytedance/deer-flow
Turns an image request into a structured JSON prompt and runs a bundled Python script to generate the picture, optionally guided by reference images.
Xiaohei Chinese Article Illustrations
helloianneo/ian-xiaohei-illustrations
Plans and generates 16:9 hand-drawn illustrations for Chinese articles on a white background, with a recurring black character and a few red, orange and blue handwritten notes.
Canghe Comic
freestylefly/canghe-skills
Knowledge comic creator supporting multiple art styles and tones.
Nano Banana Pro Prompts Recommend Skill
YouMind-OpenLab/nano-banana-pro-prompts-recommend-skill
Recommend suitable prompts from 10,000+ Nano Banana Pro image generation prompts based on user needs.
Generate Image
ynulihao/AgentSkillOS
Generate or edit images using AI models (FLUX, Gemini). An agent skill from ynulihao/AgentSkillOS.
More from chatfire-AI/huobao-drama
Character Reference Sheet Prompt
chatfire-AI/huobao-drama
Writes the final image prompt for a character reference sheet: a front-face close-up beside front, side and back full-body views, used as the look anchor for later generations.
Prop Product-Shot Prompt Spec
chatfire-AI/huobao-drama
Specifies how to write the final image prompt for a story prop: one item on a pure white background in a standard product-photo view, with true proportions.
Storyboard Video Prompt Writer
chatfire-AI/huobao-drama
Turns one storyboard segment into a time-segmented video-generation prompt with character and scene references, three-second beats and cuts inside the segment.
Novel to Screenplay Rewriter
chatfire-AI/huobao-drama
Rewrites narrated novel chapters into a formatted screenplay with scene headers and dialogue, keeping the plot and cutting camera directions.
Drama Script Entity Extractor
chatfire-AI/huobao-drama
Rules for pulling characters, scenes and key props out of a short-drama episode script and saving them without duplicates, written in Chinese.
Storyboard Breakdown Rules
chatfire-AI/huobao-drama
Rules for splitting a script into storyboard segments of several sub-shots each, with timing, shot elements, and links to scenes, characters and props.
Related
Categories
Questions about Scene Establishing-Shot Prompt
What does Scene Establishing-Shot Prompt do?
Writes the final image prompt for a clear wide establishing shot of an empty scene, fixing foreground, midground, background, exits, floor, walls and key furnishings. The prompt describes one fixed-camera wide shot with no people at all, laid out in foreground, midground and background layers, with the position and style of doors or passages, floor and wall materials and the main furnishings stated relative to each other. The image becomes the background reference anchor for every shot in that scene, so the layout must read clearly, stay self-consistent and be reusable.
When should I use Scene Establishing-Shot Prompt?
Scene Establishing-Shot Prompt fits situations like: writing a reusable background reference image prompt for a scene in a short drama; describing a location's layout so later shots stay spatially consistent; producing an empty-scene establishing shot with no characters.
How do I install Scene Establishing-Shot Prompt in Claude Code?
Run `npx skills add chatfire-AI/huobao-drama --skill scene-prompt -a claude-code`. Or copy the skill folder (backend/workspace/skills/prompt-generator/scene-prompt in chatfire-AI/huobao-drama) into .claude/skills/scene-prompt in your project. Claude Code loads it when a task matches its description.
How do I install Scene Establishing-Shot Prompt in Codex?
Run `npx skills add chatfire-AI/huobao-drama --skill scene-prompt -a codex`. Or copy the skill folder (backend/workspace/skills/prompt-generator/scene-prompt in chatfire-AI/huobao-drama) into .agents/skills/scene-prompt in your project. Codex loads it when a task matches its description.
Can I use Scene Establishing-Shot Prompt 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 chatfire-AI/huobao-drama --skill scene-prompt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scene-prompt, .gemini/skills/scene-prompt, .github/skills/scene-prompt and .opencode/skills/scene-prompt in your project.
What does Scene Establishing-Shot Prompt need to run?
SKILL.md names no scripts, command-line tools or credentials: Scene Establishing-Shot Prompt is instructions for the agent only. Our summary lists: A save_scene_final_prompt tool in the host application.
Does Scene Establishing-Shot Prompt 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 Scene Establishing-Shot Prompt 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 Scene Establishing-Shot Prompt use?
Scene Establishing-Shot Prompt 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 Scene Establishing-Shot Prompt use?
About 378 tokens (SKILL.md is roughly 1.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Scene Establishing-Shot Prompt?
Skills that share tags, products or a category with Scene Establishing-Shot Prompt: AI Image Generation and Editing (zhayujie/CowAgent, 47k stars), Structured Image Generation (bytedance/deer-flow, 84k stars), Xiaohei Chinese Article Illustrations (helloianneo/ian-xiaohei-illustrations, 12k stars) and Canghe Comic (freestylefly/canghe-skills, 461 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Scene Establishing-Shot Prompt?
chatfire-AI (a GitHub organization) maintains it in chatfire-AI/huobao-drama, which has 15,945 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 5, 2026.
Source: chatfire-AI/huobao-drama on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.