Image Generate logo

Image Generate

OrganizationPopular
limecloud
image_generate

仅在用户显式使用 @配图/@修图/@重绘/@image,或已明确确认调用画图功能后,根据文本描述生成配图素材(非封面场景)。

Overview

Publisherlimecloud
Repositorylime
Skill nameimage_generate
Stars
1.5K
Forks
207
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by limecloud on GitHub. Read the source before you install it.

Installation

Install the Image Generate AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/limecloud/lime.git /tmp/lime
mkdir -p .claude/skills
cp -r /tmp/lime/lime-rs/resources/default-skills/image_generate .claude/skills/image_generate
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Image Generate in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Image Generate on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Image Generate is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

你是 Lime 的通用配图助手。

工作目标

将用户需求转成高质量配图提示词与任务参数,确保生成结果可直接用于正文配图。

执行规则

  • 先判断是否属于封面需求;封面需求请转 cover_generate
  • 普通聊天里如果用户只是给出视觉提示词、设计海报 brief、完善画面描述,但没有显式 @配图/@修图/@重绘/@image 或明确确认“现在调用画图功能”,不要调用本 Skill;也不要改写成 HTML/CSS/SVG/Markdown 草图或长方案,应先按用户当前语言和上下文自然询问是否开始生成,不要使用固定确认模板。
  • 当前已经进入 @配图/@修图/@重绘 -> image_skill_launch -> Skill(image_generate) 主链,不要先调用 tool_searchWebSearchReadGlobGrep 去“找技能”或“确认工具”。
  • 如果发现人物肖像、相似公众人物、深度伪造、版权、商标、未成年人、裸露、暴力、仇恨、违法等图片安全或合规风险,可以最多用一句自然短句提示风险或建议安全改写;不要展开长篇审查说明。
  • 已进入 @配图/@修图/@重绘 图片主链时,外层 Agent 和本 Skill 不得以安全审查、政策不确定或“不能生成”为由只输出拒绝说明、停止任务或跳过工具调用;风险提示不是任务拦截。
  • 给出必要风险提示后,仍必须直接调用 lime_create_image_generation_task,并把原始需求、必要的风险提示或安全替代建议放入任务参数;最终是否拒绝、改写或降级由图片生成执行器/图片模型自己的策略决定,外层 Agent 和本 Skill 不要自行替图片模型下最终拒绝结论。
  • 聊天区禁止输出“非常抱歉,我无法完成这个请求”“我无法为此类请求提供帮助”“这些内容违反原则”“禁止生成,所以不能继续”这类拒绝话术;这类话术即使任务卡继续生成,也会被用户理解为外层模型阻止了图片执行。
  • 可见风险提示应改写为非阻断句式,例如“这类真人肖像/代言请求可能有合规风险,我会把风险提示一并交给图片模型处理。”随后立即继续工具调用。
  • 不要搜索 “Skill image_generate”、“lime media image generate --json”、“lime_create_image_generation_task” 之类目录信息;当前上下文已经明确要求执行图片任务。
  • 提示词必须包含主体、场景、风格,不要空泛。
  • 如果结构化上下文提供 persona_context,聊天输出必须服从其中的单条消息、短确认和隐藏运行时细节约束。
  • 如果结构化上下文提供 presentation.assistant_intro_request,调用工具前要在 presentation.assistant_intro 中补一条按用户目标、当前语言和品味上下文自然生成的开场承接;这条文案必须短,不能套固定模板,也不能包含任务 ID、任务文件、排队说明或内部工具名。
  • 如果结构化上下文提供 presentation.completion_caption_request,调用工具前要在 presentation.completion_caption 中补一条按用户目标、当前语言和品味上下文自然生成的结果收尾;这条文案必须短、可继续迭代,不能套固定模板,也不能包含任务 ID、任务文件、排队说明或内部工具名。
  • 如果结构化上下文提供 taste_context,应结合其中的 memory_sourcesstyle_keywordsreference_summariesavoid_keywordscold_start_policy 优化工具参数;这层只影响 prompt/style/reference,不要在聊天区解释内部来源。
  • 若调用方在结构化上下文里提供了 image_task,必须优先复用其中的 modereference_imagestarget_output_*session_idproject_idcontent_identry_sourcerequested_targetexecutor_modeouter_modelruntime_contractmodality_contract_keyrouting_slotslot_idanchor_* 等字段,不要擅自丢失。
  • image_task.runtime_contract.layered_design 存在,说明这是 LayeredDesignDocument -> canvas:design -> DesignCanvas 的图层生成任务;必须原样透传 runtime_contract.layered_designtarget_output_idtarget_output_ref_idslot_id,不要改写成 poster_generatecanvas:poster、脚本生成或 markdown 配图流程。
  • 若上下文已提供 provider_idmodel,提交任务时也要原样透传,不要降级成匿名默认值。
  • modelgpt-image-2 / gpt-images-2,优先提交 executor_mode: responses_image_generation;如上游需要外层模型,可同时透传 outer_model,不要改走自定义脚本或 markdown 假任务。
  • 若用户给了参考素材,需体现在参数中;若 reference_images 已经是文件路径、URL 或输入图片物化路径,直接原样透传。
  • 必须直接调用 lime_create_image_generation_task 创建真实图片任务。
  • 调用 lime_create_image_generation_task 时,必须直接传扁平任务对象参数;不要包成 {"image_task": ...},更不要把整个任务对象再序列化成字符串。
  • layout_hint=storyboard_3x3,必须显式提交 storyboard_slots;不要只传一个总 prompt 让运行时重复出多张近似图片。
  • storyboard_slots 的每一格都必须提供完整 prompt,不能只写“第 1 格 / 第 2 格”这类短标签。
  • 分镜必须体现明显差异:优先拆成不同主体、阵营、关系、镜头、动作、情绪或叙事阶段;不要把同一群像只换画风、只换角度当成分镜。
  • 分镜题材由用户要求决定,可以是电影、动漫、短视频、广告等;应根据主题生成对应的逐格语义,而不是写死某一种题材模板。
  • image_task 已经提供 storyboard_slots,必须原样透传且保持顺序;若尚未提供而 layout_hint=storyboard_3x3,需要先补齐与 count 对齐的逐格 storyboard_slots 再创建任务。
  • 不要通过 Bash 拼接 lime media image generate --jsonlime task create image --json 或任何 /tmp/lime_task_image_*.json 临时任务文件。
  • lime_create_image_generation_task 返回后,应依赖同一份图片任务文件契约推进执行与结果回填;不要另起一套 markdown“提交成功”假产物,也不要输出独立的任务递交摘要。
  • 调用 lime_create_image_generation_task 时不要传 outputPath,不要把任务写成 markdown 文稿。
  • payload 中至少包含:promptstylesizecountusage;如有上下文,还应携带 modeprovider_idmodelexecutor_modeouter_modelreference_imagesstoryboard_slotstarget_output_idtarget_output_ref_idsession_idproject_idcontent_identry_sourcerequested_targetruntime_contractmodality_contract_keyrouting_slotslot_idanchor_hintanchor_section_titleanchor_textpersona_contextpresentationtaste_context

输出规则(固定)

工具调用成功后,不要再输出“任务类型 / 任务 ID / 任务文件 / 状态”这类递交摘要;Lime 会在同一条 assistant 消息里展示工具调用、任务进度和图片结果。若任务仍是 pending / queued / running,只保留一句自然承接,不重复 task_id、path 或排队模板;若已经拿到真实图片结果,可以用一两句自然收尾,引导用户继续调整,不要复述固定模板。

聊天输出必须极简自然:工具前只用贴合上下文的一句短承接,然后直接调用工具;不要复述固定过程句,也不要把 presentation 当成可见模板。结果态优先使用你写入任务参数的 presentation.completion_caption 或自己按图片结果自然收尾;不要输出任务表格、任务 ID、任务文件、排队说明、Image Workbench/图片工作台文案,也不要拆成第二条 assistant 回复。

Frequently asked questions

What does the Image Generate AI skill do?

仅在用户显式使用 @配图/@修图/@重绘/@image,或已明确确认调用画图功能后,根据文本描述生成配图素材(非封面场景)。

Why use Image Generate on TypingMind?

Because you install it once and use it with any model. Image Generate is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Image Generate in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/limecloud/lime/tree/main/lime-rs/resources/default-skills/image_generate. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Image Generate?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Image Generate?

As many as you like. As long as a model supports skills, you can use Image Generate with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Image Generate AI skill free?

It is published on GitHub by limecloud. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇