Skip to content
Skills Library
Design & UX · Building & coding

dream-loop

/dream-loop

Build a game or app from a description so that a live screenshot matches a generated rendering. Use when the user says "dream loop" or asks for something built to a very high level of graphical fidelity.

Repository
dream-loop ↗
Licence
MIT
Last repository change
10.09.2026

Assessment and security

95/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content30 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
12
Scripts
3
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 10.09.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 3 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: scripts/fal-batch.mjs, scripts/fal-batch.test.mjs, scripts/preview-server.py

What it does and when to use it

Build a game or app from a description so that a live screenshot matches a generated rendering. Use when the user says "dream loop" or asks for something built to a very high level of graphical fidelity.

Triggers from the description

dream loop
Original author description

Build a game or app from a description so that a live screenshot matches a generated rendering. Use when the user says "dream loop" or asks for something built to a very high level of graphical fidelity.

How it works

  1. General
  2. The target image
  3. Time budget
Original SKILL.md headings · 45 lines, 437 words
SKILL.md preview
---
name: dream-loop
description: Build a game or app from a description so that a live screenshot matches a generated rendering. Use when the user says "dream loop" or asks for something built to a very high level of graphical fidelity.
license: MIT
---

# dream-loop

This is a process for you to autonomously build extremely impressive visuals, especially for 3D scenes (e.g. in a game or app).

Your first step is to determine which workflow to use:
- If the user told you to use the Plus or Pro workflow explicitly, that's your answer
- If not, check if the user is on a low or high tier coding subscription. "Low tier" means ChatGPT Plus or equivalent. "High tier" means ChatGPT Pro. For low-tier subscriptions, use the Plus workflow. For high-tier, use the Pro workflow.

Plus workflow: read [references/plus-mode/workflow.md](references/plus-mode/workflow.md)

Pro workflow: read [references/pro-mode/workflow.md](references/pro-mode/workflow.md)

Do not read both documents. They are not inter-compatible.

# Guidance applicable to both workflows

## General

Create and use a `.dream-loop` folder for working context/files, and gitignore it.

## The target image

The key piece of Dream Loop is to first create the "dream version" of the user request using image generation, then iterate to build it.

If the user supplies this, use that directly.
If not, you need to generate it.

If you don't have an image generation tool, stop and ask the user to either provide the target image, or connect you to an image generation API.

Before generating the image, determine if there is an existing product or if you're starting fresh. If fresh, you can directly generate a new image. If there's an existing product, you should capture a screenshot of the current version of it, then use that as the baseline input to the image model and generate a refined version of it based on the user direction, so that it is an improvement over the original and not a divergence.

When generating images, avoid using words like "concept art" in the prompt. This is not an artist's interpretation. It is meant to be an exact, realistic target screenshot. You will try to match it down to the pixel. For example, if the user is asking you to make a game, you should prompt the image model for a real in-engine screenshot of the target. Not a cinematic shot, photo, painting, artist concept, etc.

Store the image in `.dream-loop/target.png`.

## Time budget

If the user gives a time budget, record the time at start of the loop (after locking target.png), and check the clock between rounds.

Don't degrade visual fidelity to hit the time budget. Don't take shortcuts. It's better to hit the time limit with meaningful, beautiful progress than with something roughly complete but ugly.

If the user doesn't give a time budget, run until you hit an exit criterion, but warn that this may consume a lot of tokens.

Files in this package (12)
  • .gitignore 1 KB
  • LICENSE 1 KB
  • README.md 2 KB
  • SKILL.md 3 KB
  • references/fal.md 5 KB
  • references/plus-mode/assets-3d.md 3 KB
  • references/plus-mode/workflow.md 2 KB
  • references/pro-mode/assets-3d.md 3 KB
  • references/pro-mode/workflow.md 4 KB
  • scripts/fal-batch.mjs 11 KB
  • scripts/fal-batch.test.mjs 9 KB
  • scripts/preview-server.py 2 KB

Versions

The database has no other skills named dream-loop.

Database snapshot: 13.11.2026 · package version c581c5f48bd3 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 86vault-dream
    Use when the scheduled vault dream runs, or the user asks to consolidate, dream over or tidy the knowledge vault from recent sessions.
  • 82dream
    Review, apply or discard last night's dream (DREAM.md), the proposed tidy-up of Claude's memory that /sundown:shutdown writes. Only runs when the user types /sundown:dream.
  • 90swarm-design
    Design and build a multi-page website fast with a swarm of agents on a live canvas (Swarm Studio), then turn it into a working full-stack app, a promo video, a live deploy, or build an original browser game from a short interview. Use when someone asks for a website, landing…
  • 90dream-review
    Use when asked to review, triage, or resolve rag-rat "dream" findings — the memory-maintenance worklist the `dream` tool produces. Walks the open findings and, per kind, either fixes the underlying memory / coverage gap (which resolves the finding at the root) or records an…
  • 100visual-verification
    Closes the feedback loop on UI work by building the screen, capturing a screenshot, diffing it against the reference design export, and iterating until the difference falls under threshold. Use this after implementing or modifying any screen or widget from a design, whenever…
  • 96review
    Show the memory consolidation proposal that is waiting for approval (from a nightly dream or an earlier /rem:dream) and apply the operations the user picks. Use when the session start note says a dream is waiting, or the user says "show the dream", "review memory changes", "what…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.