multi-agent-image
Standalone multi-agent image generation skill for Hermes. Includes an internal design compiler, GPT-Image-2 generation via apimart.ai, case library reuse, interactive reference selection, batch workflows, and style-consistent series generation.
Hermes Agent · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add kangarooking/kangarooking-skills --skill multi-agent-image技能说明
name: multi-agent-image description: Standalone multi-agent image generation skill for Hermes. Includes an internal design compiler, GPT-Image-2 generation via apimart.ai, case library reuse, interactive reference selection, batch workflows, and style-consistent series generation. version: 3.0.0 author: Hermes Agent license: MIT metadata: hermes: tags: [image-generation, multi-agent, gpt-image-2, apimart, design-compiler, case-library, batch, series] related_skills: [stable-diffusion]
Multi-Agent Image
multi-agent-image is a standalone Hermes skill for image generation workflows.
It is designed for cases where a simple one-line prompt is not enough. Instead of sending raw user input directly to an image model, this skill:
- analyzes the request,
- compiles it into a design-aware prompt,
- generates through
gpt-image-2, - archives the result,
- and optionally reuses successful outputs as future style references.
This skill is independent at runtime. The design compiler is built into this repository and does not require an external skill.
When to Use
Use this skill when the user wants one or more of the following:
- Design-oriented poster generation
- Product images or ad visuals
- PPT cover visuals or chapter art
- Infographic-like or teaching/demo visuals
- Style reference reuse from prior generations
- Interactive “show examples first, then generate” flow
- Batch generation for multiple directions or aspect ratios
- Series generation where multiple images should share one visual language
Do not use this skill for:
- pixel-accurate UI recreation
- editable charts
- exact typography output inside the image
- tasks that require vector, HTML, or PPT-native assets rather than raster images
Architecture
User Request
↓
[Prompt Engineer]
↓
[Style Scout]
↓
[Internal Design Compiler]
↓
[GPT-Image-2 Generation]
↓
[QA + Archive]
↓
[Case Library]
Optional layers on top of the main path:
- Interactive reference selection
- Batch generation
- Series generation
Setup
1. Deploy the skill
The skill source lives in:
~/.hermes/skills/multi-agent-image/
Install runtime files into the working directory:
python3 ~/.hermes/skills/multi-agent-image/scripts/install.py
This prepares:
~/.hermes/agents/multi-agent-image/output/~/.hermes/agents/multi-agent-image/case_library/- agent role folders and memory files
- local runtime scripts copied from the skill
2. Install Python dependencies
pip install openai requests
3. Set API key
export OPENAI_API_KEY="sk-..."
This key is used with the apimart-compatible GPT-Image-2 endpoints in this skill.
Core Components
scripts/design_compiler.py
Internal prompt compiler.
Responsibilities:
- detect task type
- choose defaults for aspect and quality
- build
design_reasoning - compress it into
compiled_brief - produce the final generation prompt
This is the core logic that makes the skill independent.
scripts/design_image.py
CLI entrypoint for the internal compiler.
Use it when you want:
- prompt-only output
- a local design compilation test
- direct generation without the full multi-agent workflow
Example:
cd ~/.hermes/agents/multi-agent-image
python3 design_image.py \
--task poster \
--brief "AI训练营招生海报,强调速度、增长、实战" \
--direction balanced \
--aspect 3:4 \
--prompt-only
It prints:
design_reasoningcompiled_briefpromptsettings
scripts/orchestrator_v2.py
Main workflow entrypoint.
Responsibilities:
- run prompt analysis
- choose task and generation parameters
- optionally select a reference from the case library
- call the internal compiler
- call GPT-Image-2
- archive outputs
- auto-save successful results into the case library
scripts/gpt_image2_generator.py
Low-level GPT-Image-2 client.
Responsibilities:
- submit async generation tasks
- poll task status
- download image results
Use this when you want direct API access without the full workflow.
scripts/case_library.py
Persistent library of past generations.
Responsibilities:
- save outputs by task type
- store metadata and rating
- search by brief, prompt, or tags
- return image paths for reuse as references
scripts/case_selector.py
Interactive helper for Hermes dialogue flows.
Responsibilities:
- render user-facing selection text
- parse replies like
1,n,case_001, or搜索蓝色
scripts/interactive_run.py
Two-phase dialogue wrapper.
Use it when the workflow needs to ask the user before generating.
scripts/batch_generator_v2.py
Batch generation entrypoint.
Supports:
- same brief, multiple directions
- same brief, multiple aspect ratios
- multiple briefs in one run
scripts/series_generator.py
Style-consistent series generator.
Workflow:
- generate a master image
- extract style signals from its compiled brief
- generate child images that follow the same visual system
templates/linear_batch.py
Editable template for resumable sequential runs.
Useful when you want:
- explicit scene lists
- filesystem-based progress monitoring
- style propagation from the first generated image
Internal Design Compiler
The internal compiler produces three layers:
1. design_reasoning
This captures design intent before generation.
Typical fields:
taskcommunication_goalaudiencechannelvisual_systemhierarchy_strategysafe_zone_strategylighting_strategypalette_strategyanti_filler_rulesanti_slop_rules
2. compiled_brief
This is a compressed design brief for generation.
It includes:
- what the image is for
- what should dominate visually
- what space should remain available
- what to avoid
3. prompt
Final model-facing prompt used for GPT-Image-2.
The prompt is generated from design logic, not just from a list of style keywords.
Supported Tasks
The b
阅读完整来源 ↗