Guizang Social Cards
op7418/guizang-social-card-skill
Produces social card sets for Xiaohongshu and WeChat: carousels, Live Photo motion cards and puzzle layouts, and WeChat cover pairs, rendered from single-file HTML.
图片理解智能体，负责识别图片内容、反推提示词、分析图片风格、对比图片差异以及文字识别（OCR）. An agent skill from jeffstric/ZJT.
Install Image Understanding
$ npx skills add jeffstric/ZJT --skill image-understanding -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jeffstric/ZJT image-understanding --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/jeffstric/ZJT.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agents/skills/image-understanding .claude/skills/image-understanding && 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 "image-understanding" agent skill from https://github.com/jeffstric/ZJT/tree/main/agents/skills/image-understanding into .claude/skills/image-understanding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-understanding", 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/jeffstric/ZJT/tree/main/agents/skills/image-understandingType 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 jeffstric/ZJT --skill image-understanding -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jeffstric/ZJT image-understanding --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jeffstric/ZJT.git skills-src && mkdir -p .agents/skills && cp -r skills-src/agents/skills/image-understanding .agents/skills/image-understanding && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "image-understanding" agent skill from https://github.com/jeffstric/ZJT/tree/main/agents/skills/image-understanding into .agents/skills/image-understanding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-understanding", 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 jeffstric/ZJT --skill image-understanding -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jeffstric/ZJT image-understanding --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jeffstric/ZJT.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/agents/skills/image-understanding .cursor/skills/image-understanding && 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 "image-understanding" agent skill from https://github.com/jeffstric/ZJT/tree/main/agents/skills/image-understanding into .cursor/skills/image-understanding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-understanding", 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/jeffstric/ZJT.git --path agents/skills/image-understanding--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 jeffstric/ZJT --skill image-understanding -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jeffstric/ZJT image-understanding --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jeffstric/ZJT.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/agents/skills/image-understanding .gemini/skills/image-understanding && 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 "image-understanding" agent skill from https://github.com/jeffstric/ZJT/tree/main/agents/skills/image-understanding into .gemini/skills/image-understanding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-understanding", 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 jeffstric/ZJT image-understandingInstalls 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 jeffstric/ZJT --skill image-understanding -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jeffstric/ZJT.git skills-src && mkdir -p .github/skills && cp -r skills-src/agents/skills/image-understanding .github/skills/image-understanding && 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 "image-understanding" agent skill from https://github.com/jeffstric/ZJT/tree/main/agents/skills/image-understanding into .github/skills/image-understanding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-understanding", 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 jeffstric/ZJT --skill image-understanding -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jeffstric/ZJT image-understanding --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jeffstric/ZJT.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/agents/skills/image-understanding .opencode/skills/image-understanding && 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 "image-understanding" agent skill from https://github.com/jeffstric/ZJT/tree/main/agents/skills/image-understanding into .opencode/skills/image-understanding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-understanding", 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
image-understanding- GitHub stars
- 227
- Token cost
- ~701 tokens
- SKILL.md length
- 156 words
- Files
- 1
- Skills in repo
- 19
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
图片理解智能体，负责识别图片内容、反推提示词、分析图片风格、对比图片差异以及文字识别（OCR）. An agent skill from jeffstric/ZJT.
- Works in 2 steps: fetch_image_as_base64(image_url) —… → ask_user(question, options) — 向用户提问
- Media & Creative work in your project
- SKILL.md covers 角色定位, 核心工具, ⚠️ 重要：图片来源与加载 and 工作流程, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Image Understanding is an agent skill from jeffstric/ZJT. 图片理解智能体，负责识别图片内容、反推提示词、分析图片风格、对比图片差异以及文字识别（OCR）。
Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Media & Creative. The repository describes itself as: ZhiJuTong (ZJT) is an AI-powered, open-source platform specifically designed for creating professional short dramas. It automates the entire production pipeline, from script and….
When your agent uses it
- Media & Creative work in your project
Example prompts
- “/image-understanding”
Requirements
- Pre-approved tools (allowed-tools): fetch_image_as_base64, ask_user
Workflow steps
2 steps, taken from the step headings in SKILL.md.
- fetch_image_as_base64(image_url) — 获取图片数据（分析任何图片前的必经步骤）
- ask_user(question, options) — 向用户提问
What it can do on your machine
Read from SKILL.md and the folder at commit 5cc1f0c. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
fetch_image_as_base64ask_user
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
Image Understanding loads about 701 tokens when it runs. Until then it costs about 17 tokens; SKILL.md has 156 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 156 words (~701 tokens).
- name
- image-understanding
- allowed-tools
- fetch_image_as_base64, ask_user
Files
Just SKILL.md in agents/skills/image-understanding of jeffstric/ZJT.
Open the folder on GitHubat commit 5cc1f0c
Compare with similar skills
Image Understanding 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 |
|---|---|---|---|---|---|---|
| Image Understanding this skilljeffstric/ZJT | 227 | — | ~701 | Automated safety check: Pass | Custom licence | |
| Guizang Social Cardsop7418/guizang-social-card-skill | 7.4k | 1 repos | ~7.8k | Automated safety check: Pass | AGPL-3.0 | |
| Weekly Changelog Videoheygen-com/hyperframes | 59k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | |
| Anthropic Brand Stylinganthropics/skills | 180k | 30 repos | ~559 | Automated safety check: Pass | Apache-2.0 | |
| MoneyPrinterTurbo Video Generatorharry0703/MoneyPrinterTurbo | 129k | — | ~2.1k | Automated safety check: Warn | MIT | |
| Brag Slim Launch Video Makerlatent-spaces/brag | 14k | 1 repos | ~1.9k | Automated safety check: Pass | MIT |
Similar skills
Weekly Changelog Video
heygen-com/hyperframes
Turns a weekly changelog markdown file into a branded HyperFrames video with voiceover, animated mock-UI scenes and captions, using fonts, background and scripts bundled in the skill.
- Official
Anthropic Brand Styling
anthropics/skills
Applies Anthropic's brand colors and fonts to artifacts such as PowerPoint slides, using fixed hex values for text and accents, Poppins headings and Lora body text.
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.
Brag Slim Launch Video Maker
latent-spaces/brag
Builds a short, shareable launch video with music and motion from a project directory or a website URL, using only tools already on the machine.
HyperFrames Media Use
heygen-com/hyperframes
Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.
More from jeffstric/ZJT
All 19 skills in this repoStoryboard Agent API
jeffstric/ZJT
A skill your agent uses when Claude Code needs to operate this project's storyboard automation API or CLI as an agent: exchange agent tokens, discover worlds/scripts/characters/locations/props, call…
Storyboard Agent API
jeffstric/ZJT
A skill your agent uses when Codex needs to operate this project's storyboard automation API or CLI as an agent: exchange an agent token for authtoken, discover…
Add LLM Model
jeffstric/ZJT
新增 LLM 模型专家，指导如何在本项目中添加新的 LLM 供应商和模型。当需要接入新的大语言模型（如 OpenAI、Codex、DeepSeek 等）时使用。
Asset Readiness Checker
jeffstric/ZJT
资产就绪检查专家，负责检查角色（参考图和音色）、场景（参考图）、道具（参考图）的完备性和参考图内容质量（宫格切分污染检测），以及世界画风和构图设定的合理性与精简性。当需要确认所有资产是否准备就绪、是否可以进入制作工坊时使用。
Character Creator
jeffstric/ZJT
角色创建师，基于剧情生成详细的人物角色卡，包括性格、习惯、人物关系网。当需要创建或完善角色信息时使用. An agent skill from jeffstric/ZJT.
Content Compliance Checker
jeffstric/ZJT
剧本检查师，审核剧本内容是否符合内容规范，检查真实国家名称、黄赌毒、极端封建迷信等违规内容，同时检查角色一致性、大纲一致性、以及每集末尾是否有吸引人的钩子。当需要审核剧本合规性和质量时使用。仅审核任务上下文中的当前剧本，审核完成并记录结果后即结束。
Related
Categories
Questions about Image Understanding
What does Image Understanding do?
图片理解智能体，负责识别图片内容、反推提示词、分析图片风格、对比图片差异以及文字识别（OCR）. An agent skill from jeffstric/ZJT. Image Understanding is an agent skill from jeffstric/ZJT.
When should I use Image Understanding?
Image Understanding fits situations like: media & Creative work in your project.
How do I install Image Understanding in Claude Code?
Run `npx skills add jeffstric/ZJT --skill image-understanding -a claude-code`. Or copy the skill folder (agents/skills/image-understanding in jeffstric/ZJT) into .claude/skills/image-understanding in your project. Claude Code loads it when a task matches its description.
How do I install Image Understanding in Codex?
Run `npx skills add jeffstric/ZJT --skill image-understanding -a codex`. Or copy the skill folder (agents/skills/image-understanding in jeffstric/ZJT) into .agents/skills/image-understanding in your project. Codex loads it when a task matches its description.
Can I use Image Understanding 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 jeffstric/ZJT --skill image-understanding -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/image-understanding, .gemini/skills/image-understanding, .github/skills/image-understanding and .opencode/skills/image-understanding in your project.
What does Image Understanding need to run?
SKILL.md names no scripts, command-line tools or credentials: Image Understanding is instructions for the agent only. Its frontmatter pre-approves these tools: fetch_image_as_base64, ask_user.
Does Image Understanding 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 Image Understanding 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 Image Understanding use?
Image Understanding 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 Image Understanding use?
About 701 tokens (SKILL.md is roughly 2.8k 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 Image Understanding?
Skills that share tags, products or a category with Image Understanding: Guizang Social Cards (op7418/guizang-social-card-skill, 7.4k stars), Weekly Changelog Video (heygen-com/hyperframes, 59k stars), Anthropic Brand Styling (anthropics/skills, 180k stars) and MoneyPrinterTurbo Video Generator (harry0703/MoneyPrinterTurbo, 129k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Image Understanding?
jeffstric (a GitHub user) maintains it in jeffstric/ZJT, which has 227 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on September 22, 2026.
Source: jeffstric/ZJT on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.