Clone Website

Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Prerequisites — Rights first: this skill rebuilds third-party web pages locally at visual fidelity, using their real text and the assets they actually load. The rights in that content and design are not yours and are not granted by this listing or by the template's MIT licence — only clone pages you have the right to reproduce, and clearing any other case is your responsibility. Network at use time is real and required: the skill opens the source URLs in a browser and fetches pages and assets directly over HTTP (fonts, images, SVGs, video), then builds and runs a local app (in this template, a Next.js app) to compare renders. No account, key or payment is needed to install this listing, and nothing is fetched or built during installation — the folder holds instructions and references only. Install "Clone Website" for me. It is the cloning workflow of a website reverse-engineering template: given one or more source URLs, it first maps each page to a local route and records which files own it, then observes the source in a browser (desktop and mobile widths, full scroll, menus, tabs, accordions, carousels, hover and scroll-driven states, computed styles and CSS variables rather than guesses), saving screenshots and a compact page brief. It then builds a complete first pass in the current app using the source's real text and the files it actually loads — fonts, images, SVGs and video, tracked source-URL to local-path — prefers CSS for layout and simple motion, and finally compares source and local pages at the same viewport, scroll position and state, repairs the largest differences first, exercises the local routes and controls, and runs the project's production check before calling anything done. Screenshots, iframes and downloaded production bundles are references only, never the implementation. Its folder holds the main SKILL.md plus two references: an inspection guide and a Framer-and-motion guide for Framer-generated and animated pages. Repository: https://github.com/JCodesMore/ai-website-cloner-template (the skill is the whole .agents/skills/clone-website/ folder at the pinned commit: 3 files in total) Pinned version: install the code at commit ee3f5a2f31fd549b9593fa4f7cf6d2955ee593bb exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/JCodesMore/ai-website-cloner-template into a temporary folder, check out commit ee3f5a2f31fd549b9593fa4f7cf6d2955ee593bb, and copy the .agents/skills/clone-website/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-22: [FINGERPRINTS] - SKILL.md: SHA-256 f5e326e2a51b5af7646ddd42f680797cc5ba7aaa6bdbb4e8b371ea3805287e4c - references/framer-and-motion.md: SHA-256 8c84ee7a399d7751f995018a44305ca470cf915a50ba95a20efabbdd078f3e52 - references/inspection-guide.md: SHA-256 cc86abb90f420019e5e111bab162718cc9a04592c0044687432d3b6dce2e8d4e If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read SKILL.md in full, and tell me in plain words: what the skill does when used, what it connects to, whether it reads or sends any personal information or credentials, and anything that seems unusual. Stop on any red flag and tell me before going further. Confirm these points from the files: - The skill folder holds 3 files only: SKILL.md and references/inspection-guide.md and references/framer-and-motion.md. There is no script and no other code in it; the template app itself (Next.js scaffold) is the rest of the repository and is not part of this listing. - Nothing is sent or fetched during installation itself, apart from downloading this skill folder from GitHub at the pinned commit. No website is opened, inspected or cloned during installation. - At use time the network behaviour is the point of the skill and is disclosed in the prerequisites: it opens the source URLs I give it, fetches their pages and the assets they load (fonts, images, SVGs, video) over HTTP or via the browser, saves source screenshots, and builds a local copy. Out-of-scope links are left pointing at the source and disclosed. - The rights point from the prerequisites is part of the safety picture: the cloned content and design belong to the source site's owners; this listing grants no rights in them, and I am responsible for only cloning what I may reproduce. - Do not open, inspect or clone any website, and do not use the skill in any way during this install: using it is a separate step that only starts when I ask for it later. 3. When I say "yes, install", install it as a skill: copy the whole clone-website folder into the agent's skills directory, in a folder named exactly "clone-website", keeping its 3 files in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: clone-website), the 3 files in place with matching fingerprints. Do not run anything from the folder and do not use the skill to verify. 5. Report what was installed, where, and what I still need to do myself (for example: that using it will open and fetch the third-party pages I name and their assets over the network, that the rights in cloned content and design stay with their owners and are my responsibility, and that it builds the clone as local editable code in my current app). 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.