Token导航 LogoToken导航TokenDH.com
前端设计操作浏览器github未标认证来源可访问许可证需确认审计异常

fal-redesign重新设计

Agent Skill

fal-redesign 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

95

周安装

17

GitHub Stars

86

下载量

140
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:fal-redesign(重新设计)
来源仓库:https://github.com/fal-ai-community/skills
仓库路径:skills/fal-redesign
安装命令:
npx skills add https://github.com/fal-ai-community/skills --skill fal-redesign
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/fal-ai-community/skills --skill fal-redesign

简介

用于处理 GitHub 仓库、Issue 与 Pull Request 协作信息。

  • 适合在代码变更跟踪或项目状态管理时提供结构化支持。
  • 可结合原始 README 继续核验具体功能与使用方式。
  • 需注意权限控制,避免触发不必要的网络请求或文件操作。
  • fal-redesign 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

fal-redesign

fal-redesign turns "I coded a site — make it look amazing" into a concrete, implementable design pass.

your index.html          →  screenshot (1920×1200)
screenshot + brand       →  opus-4.7 writes a redesign prompt
screenshot + prompt      →  fal-ai/gpt-image-2/edit → after.png
after.png                →  opus-4.7 writes Markdown build-spec + tokens.json
                         →  returned to Claude Code / Codex

The agent reads after.png + changes.md + tokens.json, applies the spec to the real HTML, refreshes, optionally runs iterate for a residual pixel-fix pass.

When to invoke

  • User has a local index.html or a running dev server and asks to improve the design, make it world-class, redesign, polish, or run a design review.
  • User describes a brand/product in freeform text and asks for a fresh site (greenfield mode → generate).

Do NOT invoke for:

  • Copy-only edits (the skill is visual-design focused).
  • Backend, build config, or infra tasks.

Scripts

scripts/upgrade.sh — redesign a coded site

bash scripts/upgrade.sh --target <path-or-url> [--context "..."] [--variants N] [--out <dir>]

Pass --variants N (2–8) to fan out into N distinct design directions in parallel. You get after-01-<slug>.png, after-02-<slug>.png, … plus a gallery.html to compare them side-by-side. Pick one, then run scripts/describe.sh on the chosen PNG to produce its build-spec. Outputs in <out>/:

  • before.png — current-site screenshot.
  • after.png — redesigned reference image.
  • edit-prompt.txt — transformation prompt fed to gpt-image-2.
  • changes.md — Markdown build-spec with a leading "Hard constraints" section (also echoed to stdout).
  • tokens.json — design tokens (colors, typography clamps, grid, buttons).

scripts/describe.sh — re-run the build-spec on an existing after.png

Useful if the first spec was noisy or if you want to iterate on the spec without regenerating the image.

bash scripts/describe.sh --after <path/to/after.png> [--out <dir>]

scripts/iterate.sh — residual pixel-fix pass

After the agent has implemented the spec, screenshot the live site and emit a delta-spec vs the reference.

bash scripts/iterate.sh --target <path-or-url> --reference <path/to/after.png> [--out <dir>]

Outputs current.png + delta.md.

scripts/generate.sh — greenfield (brief → site)

bash scripts/generate.sh --context "<freeform context>" [--variants 4] [--out <dir>]

Required environment

export FAL_KEY=...   # https://fal.ai/dashboard/keys

Models used:

  • anthropic/claude-opus-4.7 — via openrouter/router and openrouter/router/vision (overridable with FAL_SITE_MODEL).
  • fal-ai/gpt-image-2 — greenfield hero + mockup renders.
  • fal-ai/gpt-image-2/edit — screenshot-to-redesign transformation.

Usage pattern for agents

  1. Check FAL_KEY. If unset, ask the user to export it and stop.
  2. Pick the mode.

- If the user references a file path that exists or a URL (http://localhost:...) → scripts/upgrade.sh. - Otherwise → scripts/generate.sh.

  1. Run the script. Each upgrade pass takes 60–180s (1 screenshot + 2 vision calls + 1 image-edit). Emit a brief status to the user before calling.
  2. Surface the result.

- Open after.png (Read tool) so the user sees the new design. - Paste changes.md in the chat (or the highlights). - Ask: "Want me to implement these changes in <file> now?"

  1. If yes, implement. Read the current file. Apply the spec section by section, obeying the Hard constraints verbatim and pulling exact values from tokens.json. For imagery in the result grid, look at after.png directly and either use <img> placeholders at the matching aspect ratio or source stock that matches the mood.
  2. Optional iterate. After implementation, offer scripts/iterate.sh --target <file> --reference <after.png> for a residual delta-spec. Apply deltas, refresh.

Model notes

  • Opus 4.7 handles multi-image reasoning and produces precise design specs. For 3× cheaper runs with near-parity on this task, set FAL_SITE_MODEL=anthropic/claude-sonnet-4.6.
  • gpt-image-2/edit is the right primitive because it edits an existing screenshot while preserving legible in-image text — avoid substituting other image models here.

Runtime

The skill ships a small Node 18+ runtime under runtime/ (puppeteer, @fal-ai/client, sharp). Scripts npm install on first run. Override the runtime path with FAL_SITE_RUNTIME=/abs/path.

适合场景

01

调用多模型

02

代码和文本生成

03

Agent 推理流程

04

OpenRouter 模型接入

能力概览

能力 1

统一调用多种 LLM

能力 2

支持 Claude、Gemini、Kimi 等模型

能力 3

适合聊天、代码和推理任务

能力 4

可作为 Agent 模型调用入口

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

34.06%
按下载量换算48

Claude

32.41%
按下载量换算45

Cursor

21.13%
按下载量换算30

Gemini CLI

10.1%
按下载量换算14

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

可疑

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills