Profile Site Maker

Live

Turn a photo and your LinkedIn paste into a personal site, resume and job matches.

musemuse-profile-site-maker.vercel.appOpen

Get it

Connect it to any app that speaks MCP. It has 2 tools: generate_personal_site, regenerate_from_profile. No sign-in.

Muse app: add this URL as a custom connector.
Claude Code: claude mcp add --transport http profile-site-maker https://muse-muse.vercel.app/api/mcp/profile-site-maker
Anything else: add it as a remote server over streamable HTTP.

Each line is what the check ran on, and no more.

This is a model's opinion, not proof.

Nothing here should be taken as tested.

Not checked Whether its answers are true
Not checked ChatGPT: only a person with an account can test it
Not checked Installing the Claude plugin or the Muse gadget pack on a real device
Not checked No Prove it run: nothing it comes with was run for real

A text note asking to drop in a portrait and paste LinkedIn text to get a rendered personal site, a matching resume and job suggestions.

Turning a profile paste and a portrait into a ready personal site.
Producing a matching resume from the same source material so nothing is typed twice.
Adding job suggestions matched to the person's skills and experience.

Muse WonderReads the portrait and pasted profile text, extracts the structured profile and writes site copy, resume text and job match reasons
Muse ImageCreates one abstract banner image matched to the person's field and chosen site tone

There is no live LinkedIn connection. The user must paste their profile text manually.
Job listings are suggested roles with match reasons and search keywords. They are not live postings from a job board, so the user should search those terms on job sites to apply.
Profile details are taken from what the user pastes. Wrong or missing details in the paste will appear in the site and resume until edited.
The portrait is used as provided. The product does not retouch faces or change how a person looks.
Work is saved only in the user's browser. Clearing browser data removes the saved site and resume.

Add it in the Muse app as a custom connector. It exposes 2 actions: generate_personal_site, regenerate_from_profile.

Muse Code made 104 tool calls and 50 edits across 50 files (+727 −64).
npm run verify passed after 2 fix rounds.
Screenshot judge: pass. Final screen shows the rendered personal site for Alex Morgan with banner, portrait, About, Experience, Skills, Education, Projects and Contact sections.
Built in 18 min for about $5.14 in model calls (est.).
Publishing is off for this run (it's a local run, and a published product couldn't reach this machine's gateway), so the product didn't get its own link. The preview, checks and demo above ran for real.
How it was built: 104 tool calls, 50 edits touching 50 files { Read text file `fixtures/sample-1.txt`. Read text file `app/layout.tsx`. Read text file `app/page.tsx`. Read text file `lib/meta/json.ts`. Read text file `lib/meta/client.ts`. <read-skill-result name="meta-ui" status="ok"> <read-skill-result name="meta-reasoning" status="ok"> <read-skill-result name="meta-image" status="ok"> <read-skill-result name="verify" status="ok"> <read-skill-result name="product-ui" status="ok"> Read text file `components/FilePicker.tsx`. Read text file `components/Segmented.tsx`. Read text file `lib/meta/parts.ts`. Read text file `lib/client/resize.ts`. Read text file `tests/smoke.spec.ts`. { {"items":3,"ok":true,"revision":1} Edited `lib/profile.ts`
Imported from a local run. Publishing it to its own link now.