An AI-powered pre-production assistant that converts unstructured creative ideas into production-ready comic scripts, storyboards, and character designs.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install comic-create
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install comic-create using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The comic-create skill is an advanced pre-production planning tool designed to convert brief, unstructured creative prompts into comprehensive, artist-ready comic assets. Ideal for manga artists, editors, and visual creators, this utility bridges the gap between raw imagination and structured, visual direction. As a core offering among Openclaw Skills, it helps writers and creators automate the tedious scaffolding steps of visual storytelling.
Instead of generating raw images, this skill acts as a meticulous textual planner. It optimizes dialogue, designs sequential action beats, structures classic four-panel strips, and maps out balanced page layouts. If user descriptions are sparse, the skill intelligently asks up to three targeted clarifying questions to lock down themes, characters, and formats before generating complete production documents.
# Install the comic-create skill via your Openclaw CLI manager
openclaw install skill comic-create
# Configure global preferences in your workspace configuration
cat <<EOF > .openclaw/config/skills/comic-create.yaml
settings:
default_language: "English"
output_format: "markdown_table"
clarification_threshold: 3
EOF
The comic-create skill leverages structured Markdown tables to compile storyboard assets, ensuring precise visual direction for subsequent drawing stages.
| Field | Format | Description |
|---|---|---|
| Page/Panel | String (e.g., P1-F1) |
The page index and corresponding panel frame number. |
| Visual Content | String | Detailed setting and action description for artists or prompt pipelines. |
| Camera Lens/Angle | String | Perspective directives (e.g., Wide Shot, Close-up, Low-angle). |
| Character Action | String | Specific physical poses, body language, and emotional cues. |
| Dialog / SFX | String | Onomatopoeia and character speech, optimized for bubble constraints. |
| Layout Notes | String | Spatial bubble arrangement, reading direction, and focal pacing. |
Loading
A browser automation skill for capturing screenshots and performing visual reconnaissance to analyze pages for security indicators.

A local, privacy-first audio transcription skill that converts speech to text, subtitles (SRT), or JSON using OpenAI's Whisper model.

A bilingual, vendor-neutral operating playbook designed to convert AI-native startup ideas into stage-appropriate strategic experiments and automated agent workflows.

A utility to parse raw Nuclei vulnerability scan results, filter noise, and generate prioritized markdown reports.

Equip your AI agents with real-time web search, image discovery, and LLM-friendly webpage extraction capabilities using the iFlow Search API.

An automated workflow skill designed to smoothly integrate MobTech SMSSDK into iOS projects with minimal disruption.








































