Gemini Skill
WJZ-P/gemini-skill
通过 Gemini 官网（gemini.google.com）执行生图、对话等操作。用户提到"生图/画图/绘图/nano banana/nanobanana/生成图片"等关键词时触发。操作方式分三级优先级：首选 MCP 工具 → 次选 Skill 脚本 → 最次连接 Skill 浏览器手动操作（需用户授权）。禁止自行启动外部浏览器访问 Gemini。
Walks a non-coder through structured questions about scene, style, color, text rules and consistency, then auto-generates a complete, ready-to-use batch image-generation skill.
SKILL.md written in Chinese; this summary is our English description.
Install Batch Image Skill Builder
$ npx skills add SpaceZephyr/design-buddy --skill space-image-skill-builder -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install SpaceZephyr/design-buddy space-image-skill-builder --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/SpaceZephyr/design-buddy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/space-image-skill-builder .claude/skills/space-image-skill-builder && 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 "space-image-skill-builder" agent skill from https://github.com/SpaceZephyr/design-buddy/tree/main/space-image-skill-builder into .claude/skills/space-image-skill-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "space-image-skill-builder", 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/SpaceZephyr/design-buddy/tree/main/space-image-skill-builderType 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 SpaceZephyr/design-buddy --skill space-image-skill-builder -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install SpaceZephyr/design-buddy space-image-skill-builder --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SpaceZephyr/design-buddy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/space-image-skill-builder .agents/skills/space-image-skill-builder && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "space-image-skill-builder" agent skill from https://github.com/SpaceZephyr/design-buddy/tree/main/space-image-skill-builder into .agents/skills/space-image-skill-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "space-image-skill-builder", 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 SpaceZephyr/design-buddy --skill space-image-skill-builder -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install SpaceZephyr/design-buddy space-image-skill-builder --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SpaceZephyr/design-buddy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/space-image-skill-builder .cursor/skills/space-image-skill-builder && 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 "space-image-skill-builder" agent skill from https://github.com/SpaceZephyr/design-buddy/tree/main/space-image-skill-builder into .cursor/skills/space-image-skill-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "space-image-skill-builder", 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/SpaceZephyr/design-buddy.git --path space-image-skill-builder--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 SpaceZephyr/design-buddy --skill space-image-skill-builder -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install SpaceZephyr/design-buddy space-image-skill-builder --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SpaceZephyr/design-buddy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/space-image-skill-builder .gemini/skills/space-image-skill-builder && 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 "space-image-skill-builder" agent skill from https://github.com/SpaceZephyr/design-buddy/tree/main/space-image-skill-builder into .gemini/skills/space-image-skill-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "space-image-skill-builder", 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 SpaceZephyr/design-buddy space-image-skill-builderInstalls 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 SpaceZephyr/design-buddy --skill space-image-skill-builder -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/SpaceZephyr/design-buddy.git skills-src && mkdir -p .github/skills && cp -r skills-src/space-image-skill-builder .github/skills/space-image-skill-builder && 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 "space-image-skill-builder" agent skill from https://github.com/SpaceZephyr/design-buddy/tree/main/space-image-skill-builder into .github/skills/space-image-skill-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "space-image-skill-builder", 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 SpaceZephyr/design-buddy --skill space-image-skill-builder -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install SpaceZephyr/design-buddy space-image-skill-builder --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SpaceZephyr/design-buddy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/space-image-skill-builder .opencode/skills/space-image-skill-builder && 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 "space-image-skill-builder" agent skill from https://github.com/SpaceZephyr/design-buddy/tree/main/space-image-skill-builder into .opencode/skills/space-image-skill-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "space-image-skill-builder", 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
space-image-skill-builder- GitHub stars
- 174
- Token cost
- ~1.3k tokens
- SKILL.md length
- 249 words
- Files
- 5 (incl. scripts, references)
- Skills in repo
- 16
- Repo updated
- First seen
- Licence
- None found
At a glance
Walks a non-coder through structured questions about scene, style, color, text rules and consistency, then auto-generates a complete, ready-to-use batch image-generation skill.
- Works in 6 steps: 场景理解（3 个问题） → 风格定义（3-4 个问题） → 内容规则（2-3 个问题） → …
- Creating a custom batch image-generation skill without writing code
- SKILL.md covers 核心理念, 工作流程, 关键设计原则 and 参考文件, plus 1 more section
- Runs Python scripts from its folder; calls gemini
What it does
The skill runs a five-phase interview, asking one question at a time rather than dumping a list: scene understanding covers what kind of batch images are wanted, where they will be used, and roughly how many per run; style definition picks visual style from a filtered shortlist, optionally breaks down an uploaded reference image, and sets color and aspect-ratio preferences; content rules cover whether images need text, where the content comes from, and whether multiple images in a batch must share one consistent look.
After a final confirmation of technical parameters, it automatically assembles the new skill: it maps the user's choices onto one of several known skill shapes, such as an article-illustration flow that splits paragraphs and generates prompts, a logo flow that collects brand information and produces ten variants, or a storyboard flow that splits a story into shots, then creates the skill's full directory with a SKILL.md populated from a template, a style-guide.md built from the matching entries in a style library, and copies the image-generation script into place. The excerpt is cut off while still listing the file-copying step.
When your agent uses it
- Creating a custom batch image-generation skill without writing code
- Turning a reference image's visual style into a reusable skill
- Setting up a skill that keeps multiple generated images visually consistent
Example prompts
- “帮我创建一个文章配图的生图Skill。”
- “Build me a logo-generation skill that produces ten style variants per run.”
- “Create a storyboard image skill that keeps the same visual style across every shot.”
Requirements
- Python to run the bundled generate_image.py script
Workflow steps
6 steps, taken from the step headings in SKILL.md.
- 场景理解（3 个问题）
- 风格定义（3-4 个问题）
- 内容规则（2-3 个问题）
- 技术配置（快速确认）
- 自动生成 Skill
- 展示与试用
What it can do on your machine
Read from SKILL.md and the folder at commit f1d835f. 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.
Shell commands in SKILL.md call:
gemini
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
Batch Image Skill Builder loads about 1.3k tokens when it runs, and up to ~6.6k if it reads all its reference files. Until then it costs about 50 tokens; SKILL.md has 249 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 249 words (~1,311 tokens).
- name
- space-image-skill-builder
Files
SKILL.md and 4 other files (scripts, references) in space-image-skill-builder of SpaceZephyr/design-buddy.
- SKILL.md
- agents/openai.yaml
- references/skill-template.md
- references/style-library.md
- scripts/generate_image.py
Open the folder on GitHubat commit f1d835f
Compare with similar skills
Batch Image Skill Builder 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 |
|---|---|---|---|---|---|---|
| Batch Image Skill Builder this skillSpaceZephyr/design-buddy | 174 | — | ~1.3k | Automated safety check: Pass | None | |
| Gemini SkillWJZ-P/gemini-skill | 832 | — | ~1.1k | Automated safety check: Pass | MIT | |
| ComfyComfy-Org/comfy-skills | 219 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Run SEO Page Looptsingyuai/growth-lab | 2k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Codexyan-labs/yan-skills | 208 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Skill CreatorAzure/azqr | 795 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Comfy
Comfy-Org/comfy-skills
Generate images, video, audio, and 3D with Comfy Cloud — search hundreds of models and workflow templates, run custom ComfyUI workflows, and manage generation jobs through the hosted Comfy Cloud MCP…
Run SEO Page Loop
tsingyuai/growth-lab
Run an SEO page observation-action-review loop with persistent Memory by coordinating demand research, page creation, adversarial review, image generation, IndexNow submission, and performance review.
Codex
yan-labs/yan-skills
当用户明确要求直接操作 Codex CLI 作为后台代理（自选 sandbox、codex review、apply、resume 等原生命令，或用 git worktree 并行布置多个 worker）做代码分析、编辑、审查时使用。普通的“让 Codex 或 GPT-6 写代码、调研、review”派单走 agent-fleet（fleet code）；图片生成与网站视觉素材走…
- Official
Skill Creator
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
Claude Code Skill Developer Guide
diet103/claude-code-infrastructure-showcase
A guide to creating and managing Claude Code skills with auto-activation: skill-rules.json triggers, hooks, enforcement levels, YAML frontmatter and progressive disclosure.
More from SpaceZephyr/design-buddy
All 16 skills in this repoSlide Deck Image Generator
SpaceZephyr/design-buddy
Turns written content into designed slide images from an outline, merges them into PPTX or PDF, and can borrow styles from a registry of brand design systems.
WeChat Article Layout
SpaceZephyr/design-buddy
Turns an article into WeChat Official Account HTML with a local preview, a choice of three visual styles and a button that copies the rich HTML.
Article Illustration Batch Generator
SpaceZephyr/design-buddy
Splits a Markdown article by heading, drafts an image prompt for each section, then generates diagrams with the Gemini API and embeds them in the note.
AI Chart Image Generator
SpaceZephyr/design-buddy
Generates a finished chart image directly with GPT-image-2 from a text description, across ten chart types such as flowcharts, architecture diagrams and SWOT grids in six visual styles.
Space Image Studio
SpaceZephyr/design-buddy
Generates PNG images for four common needs: Xiaohongshu covers, slide illustrations, charts and article logic diagrams, with twelve visual styles and automatic style suggestions.
Batch Logo Generator
SpaceZephyr/design-buddy
Generates ten logo variants in one run from a brand description or an uploaded reference image, with seven style options, using the Gemini image API and saving files to an Obsidian folder.
Related
Categories
Questions about Batch Image Skill Builder
What does Batch Image Skill Builder do?
Walks a non-coder through structured questions about scene, style, color, text rules and consistency, then auto-generates a complete, ready-to-use batch image-generation skill. The skill runs a five-phase interview, asking one question at a time rather than dumping a list: scene understanding covers what kind of batch images are wanted, where they will be used, and roughly how many per run; style definition picks visual style from a filtered shortlist, optionally breaks down an uploaded reference image, and sets color and aspect-ratio preferences; content rules cover whether images need text, where the content comes from, and whether multiple images in a batch must share one consistent look.
When should I use Batch Image Skill Builder?
Batch Image Skill Builder fits situations like: creating a custom batch image-generation skill without writing code; turning a reference image's visual style into a reusable skill; setting up a skill that keeps multiple generated images visually consistent.
How do I install Batch Image Skill Builder in Claude Code?
Run `npx skills add SpaceZephyr/design-buddy --skill space-image-skill-builder -a claude-code`. Or copy the skill folder (space-image-skill-builder in SpaceZephyr/design-buddy) into .claude/skills/space-image-skill-builder in your project. Claude Code loads it when a task matches its description.
How do I install Batch Image Skill Builder in Codex?
Run `npx skills add SpaceZephyr/design-buddy --skill space-image-skill-builder -a codex`. Or copy the skill folder (space-image-skill-builder in SpaceZephyr/design-buddy) into .agents/skills/space-image-skill-builder in your project. Codex loads it when a task matches its description.
Can I use Batch Image Skill Builder 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 SpaceZephyr/design-buddy --skill space-image-skill-builder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/space-image-skill-builder, .gemini/skills/space-image-skill-builder, .github/skills/space-image-skill-builder and .opencode/skills/space-image-skill-builder in your project.
What does Batch Image Skill Builder need to run?
Going by SKILL.md and its folder, Batch Image Skill Builder needs Python for the scripts in its folder and the command-line tools its instructions call (gemini). Our summary lists: Python to run the bundled generate_image.py script.
Does Batch Image Skill Builder 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 Batch Image Skill Builder 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 Batch Image Skill Builder use?
No licence was found for Batch Image Skill Builder or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Batch Image Skill Builder use?
About 1.3k tokens (SKILL.md is roughly 5.2k 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 5.2k tokens, read only when the agent opens those files.
What are the alternatives to Batch Image Skill Builder?
Skills that share tags, products or a category with Batch Image Skill Builder: Gemini Skill (WJZ-P/gemini-skill, 832 stars), Comfy (Comfy-Org/comfy-skills, 219 stars), Run SEO Page Loop (tsingyuai/growth-lab, 2k stars) and Codex (yan-labs/yan-skills, 208 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Batch Image Skill Builder?
SpaceZephyr (a GitHub user) maintains it in SpaceZephyr/design-buddy, which has 174 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on July 6, 2026.
Source: SpaceZephyr/design-buddy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.