- Home
- Skills
- Image & Video
- mid journey prompt forge
Works with the AI Agents you already use
mid journey prompt forge
Generate, debug, and iterate Midjourney V8.2 prompts with technical precision and style consistency.
$10
mid journey prompt forge
Example session with this skill installed
I need a prompt for a cinematic shot of a weathered fisherman in his 60s, wearing a yellow oilskin, on a boat during a storm. Make it look like a high-end film. AR 21:9.
- Read your context and instructions
- Compiled the mid journey prompt
I have generated three versions optimized for Midjourney V8.2. The prompts prioritize the subject and use specific cinematic lighting cues rather than generic quality terms.
Midjourney V8.2 Prompts
1 · Faithful — closest to what you asked
A weathered fisherman in his 60s wearing a bright yellow oilskin, standing on the deck of a tossing wooden boat, dark stormy seas and crashing waves, wide cinematic shot, dim natural light, grainy 35mm film aesthetic, moody teal and orange tones --ar 21:9 --raw --s 50
2 · Elevated — same idea, stronger composition/light
Close-up of a grizzled fisherman in a salt-sprayed yellow oilskin, rain lashing against his face, turbulent North Sea background, dramatic rim lighting from a distant lighthouse, hyper-detailed skin textures, cinematic anamorphic lens, cold maritime palette --ar 21:9 --raw --s 150
3 · Wild — a bolder interpretation
Extreme wide shot of a tiny fishing trawler caught in a massive dark swell, one lone figure in yellow oilskin visible on deck, bioluminescent foam in the waves, ethereal moonlight breaking through storm clouds, surreal scale, fine art photography style --ar 21:9 --c 20 --s 400
Knobs:
- More rain detail → add "heavy rainfall caught in mid-air"
- Shift to vintage look → replace "35mm film" with "1970s Kodachrome"
- Increase intensity → add "--exp 20" for more dynamic range
Next steps
- Copy the code block of your preferred variant.
- Paste into Discord or the MJ web alpha following the
/imaginecommand. - If the sea is too calm, increase chaos by adding
--c 40.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop wasting Midjourney credits on plastic-looking generations or syntax errors. Most failed prompts suffer from tag soup, buried subjects, or parameters that conflict with the active model version. This skill provides a systematic approach to prompt engineering, ensuring your ideas translate into valid, high-fidelity images on the first run.
What it does
- Prompt generation creates three distinct variants for any idea: Faithful, Elevated, and Wild.
- Image reverse-engineering analyzes uploaded images to extract subject, lighting, and medium for recreation.
- Syntax linting runs every prompt through a validator to catch parameter errors and version mismatches.
- Batch consistency generates sets of prompts for storyboards or campaigns using shared style blocks and
--srefstrategies. - Prompt debugging diagnoses why a result looks generic or ignores details, providing a specific fix.
How it works
- Define the mode by providing an idea, a bad prompt to fix, or an image to reverse-engineer.
- Fill the brief as the agent silently maps the subject, composition, lighting, and medium.
- Apply model logic to select the correct parameters for photorealism, stylization, or surrealism based on Midjourney V8.2 or V7.
- Copy the result directly from the code blocks provided in the structured output.
Frameworks & tools
Specifically designed for Midjourney V8.2, V8.1, V7, and Niji models. Uses a custom linting script to validate against official parameter rules.
Why this beats prompting it yourself
Writing "8k masterpiece" adds noise that Midjourney's latest models ignore. This skill replaces vague adjectives with concrete descriptors and handles the complex math of stylization, chaos, and reference weights so you don't have to look up documentation.
Use cases
- Generating a consistent character across multiple scenes for a storyboard.
- Converting a low-quality brand sketch into a high-fidelity cinematic product shot.
- Fixing "garbled text" errors by applying proper quoting and positioning logic.
- Reverse-engineering the specific film stock and lighting of a reference photo.
Known limitations
Does not support real-person likenesses or trademarked logos. Prompts are limited to 1024 characters per Midjourney technical constraints.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Video Skills.
Strictly avoids living-artist names, trademarks, and real-person likenesses. Limited to 1024 characters per prompt. Requires manual URL insertion for image references.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 26 days ago