← Search

Fal redesign — award-tier design passes for coded websites
Design 🧪 Install ran in our test sandbox · Nov 11, 2026 📌 Pinned version: commit 9ca8504
Install test only, on the date shown. This does not guarantee the code is safe.
🔎 Install prompt analysis · 2026-10-13 : runs commands · installs packages
⚙ Needs: a fal.ai account with FAL_KEY set in the…

Fal redesign — award-tier design passes for coded websites

Screenshot a coded site, have a vision model write an edit prompt, render the redesigned reference via fal-ai image edit, and get a build-spec with hard constraints plus design tokens — plus iterate and greenfield generate modes

At a glance
What
Screenshot a coded site, have a vision model write an edit prompt, render the redesigned reference via fal-ai image edit, and get a build-spec with hard constraints plus design tokens — plus iterate and greenfield generate modes
Cost
Free
Needs
a fal.ai account with FAL_KEY set in the environment (paid, metered API — each design pass calls fal.ai image and OpenRouter vision models), Node 18+ to run the bundled runtime
Install
Copy the installer prompt below into your Muse — your agent does the rest.

Version:

@
Created by: @fal-ai-community

Quick answer

Fal redesign is a free Muse skill, a listing for the redesign pipeline for coded websites, but rendering uses a paid fal-ai API, so check costs first. Hand it a local HTML file or a dev-server URL and the bundled Node runtime runs four modes: upgrade, describe, iterate, and greenfield generate, producing a build-spec with hard constraints plus design tokens.

⌁

Install

Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 9ca8504

Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a fal.ai account with FAL_KEY set in the environment (paid, metered API — each design pass calls fal.ai image and OpenRouter vision models), Node 18+ to run the bundled runtime Install "Fal redesign — award-tier design passes for coded websites" for me. It gives my agent @fal-ai-community's four-mode redesign pipeline: upgrade (screenshot a local HTML file or dev-server URL, vision model drafts the edit prompt, fal-ai/gpt-image-2/edit renders the redesigned reference image, and I get a Markdown build-spec with "Hard constraints" plus tokens.json to apply to the real HTML), describe (re-run a build-spec on an existing after.png), iterate (screenshot the implemented site and get a delta-spec vs the reference), and generate (freeform brief → mockup → single-file HTML, with parallel variants and a comparison gallery). IMPORTANT: the repo states no license — fetch from the link only, and reproduce nothing beyond the link. Repository: https://raw.githubusercontent.com/fal-ai-community/skills/9ca850412943251fc9a466c4c29fdaf7a303a3d8/skills/fal-redesign/SKILL.md Pinned version: install the code at commit 9ca850412943251fc9a466c4c29fdaf7a303a3d8 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and the runtime/ folder) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and the runtime scripts for anything suspicious (unexpected network calls beyond fal.ai and OpenRouter, shell commands, credential harvesting). This repo should contain zero secrets in code — the only credential is the FAL_KEY environment variable, never committed. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its runtime/ folder into the agent's skills directory, in a folder named "fal-redesign". 4. Verify with no network calls: frontmatter valid, files in place (do not run npm install until I give the go-ahead). 5. Report what was installed, where, and what I still need to do myself (e.g. run `cd runtime && npm install`, set my FAL_KEY in the environment — I pay for the fal.ai usage myself). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.

🔒 Security, provenance and what this touches
🧭 What this touches
  • It can run commands on your Muse’s computer.
  • It can download and install software packages.
Install prompt analysis · 2026-10-13
🔒 Security and provenance
📌 Pinned version: commit 9ca8504 · 2026-10-13
🧪 Install ran in our test sandbox · Nov 11, 2026
👁 Observed during the install test · Nov 11, 2026 : no network contact
🔎 Install prompt analysis · 2026-10-13 : runs commands · installs packages
What the scan found — excerpts from the install prompt
  • runs commands — 4. Verify with no network calls: frontmatter valid, files in place (do not run npm install until I give the go · 4. Vérifie sans appels réseau : frontmatter valide, fichiers en place (ne lance pas npm install sans mon feu v
  • installs packages — 4. Verify with no network calls: frontmatter valid, files in place (do not run npm install until I give the go · 4. Vérifie sans appels réseau : frontmatter valide, fichiers en place (ne lance pas npm install sans mon feu v
🔎 Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a skill before installing →

✓

Verification certificate

Dated facts about what was checked for this listing, and how. This is not a safety certification.

Pinned version
9ca8504 · 2026-10-13
Sandbox install test
Install ran in our test sandbox · Nov 11, 2026
Creator identity
Not verified
Fingerprint watch
Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Install prompt analysis
2026-10-13 : runs commands · installs packages

Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify

?

Questions

How do I install a skill?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.