SkillFoxx

ARIS Homepage Generator skill

A skill builds an academic homepage from a CV, retains editable source data and checks publication details against DBLP.

  • 652 ★ on the repository
  • Last commit
  • MIT
Skill

Extended access

Why this level

  • The skill reads a CV and writes site files; publication details go to external checks and the chosen model sees authorized context.
All reasons and checks

wanshuiyin/aris-in-ai-offerAuthor:wanshuiyin

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/aris-homepage-generator

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • The skill reads a CV and writes site files; publication details go to external checks and the chosen model sees authorized context.

This is third-party code. Review the repository files before installing.

What it does

ARIS Homepage Generator turns a CV into an academic homepage. A script extracts text and prepares a handoff; the agent then fills structured data. The user reviews conflicts before the final build. Profile, publications and news remain separate from HTML output. Rendering checks publication details, with optional Codex review. The generator belongs to the ARIS repository, which also contains separate interview study sheets.

Who it is for. For researchers and doctoral candidates who need a simple academic page with checkable publication details.

Good fit when

  • Build a first homepage from a CV.
  • Check publication authors and details on an existing page.
  • Edit profile data separately from generated HTML.
  • Show the owner conflicts between a CV and previous homepage.

Not a fit when

  • You need a complex portfolio with galleries and a custom server.
  • The CV must not reach the selected model or external checks.
  • You expect automatic publication without reviewing extracted data.

Example request

Prepare an academic homepage draft from my CV, show disputed facts and do not publish it.

Limitations

The workflow needs an agent: the script creates a handoff rather than automatically filling extraction JSON. Publication checks use DBLP, so inspect author matches and namesakes manually. Reconcile the CV, old page and images before rendering; conflicts are retained for the owner to resolve. There is no installed standalone executable. Commands call a Python script by repository path, which changes after entering the site directory.

How to disable. Remove the agent skill. Page source data and generated HTML remain in the selected directory; manage any published site separately.

FAQ

Which source files remain editable?

YAML profile data, BibTeX publications and separate Markdown biography and news files.

How do I begin from a PDF CV?

Use `python tools/aris_homepage.py init --from-cv ./cv.pdf --out ./site` with approved input and output.

What is an old homepage used for?

It guides presentation and links. The CV supplies facts, with separate verification.

Is Gemini screenshot critique required?

No. It is optional when available and separate from factual review.

Which page style is implemented?

A minimal text-focused academic page; the richer active-researcher variant remains planned.

Discussion

No questions or reviews yet.

Skills

Before designing a new mechanism the agent checks real arXiv papers, reads them in isolation and converges on the findings.

SkillExtended access438
Official

Official Arize skills: LLM app tracing, experiments, evaluators, prompt optimization and migration from Langfuse

PluginExtended access72

A skill that analyzes a repository and generates files for AI agents: AGENTS.md, pointers, reviewers, CI and templates

SkillExtended access238

my-skills by akitaonrails

akitaonrails my-skills

Fabio Akita's personal set of 24 skills for Claude Code, Codex and opencode: releases, PR audits, security and fact-checking

SkillExtended access302

A library of 30-plus instruction skills for coding agents: planning, building, testing, hallucination guards and shipping

SkillMinimal access217

One rules directory generates instructions, skills, MCP and settings for 52 AI coding assistants and checks them in CI

CLIExtended access169

README in short

The generator separates preparation, extraction, data persistence and rendering. Each stage can be reviewed before replacing the final page.

README badge

Original SKILL.md

---
name: homepage-generator
description: "Generate a fact-checked academic personal homepage from a CV, optionally augmented by an existing manual homepage and an assets directory. Produces editable structured source files (profile.yml + publications.bib + bio.md + news.md) and a single-file HTML page. Uses Codex MCP for independent factual review against DBLP. Optionally uses Gemini multimodal for screenshot critique when available. Use when the user says '做个学术主页', '从CV生成主页', 'aris-homepage', 'generate academic homepage from CV', 'PhD homepage', 'GitHub Pages personal site', or wants a fact-checked academic site."
argument-hint: init --from-cv <cv.docx|cv.pdf|cv.txt> [--from-repos owner/repo,...] [--include-private] [--out <dir>] [--force] | finalize | render --persona theory-minimal [--out <html>] [--override-all] [--no-audit] [--offline] | check [--strict] | doctor
allowed-tools: Bash(*), Read, Write, Edit, WebFetch, mcp__codex__codex
---

# /homepage-generator — fact-checked academic homepage from CV

> **The only personal-site generator that fact-checks your CV before publishing.**
> Cross-model adversarial review: the LLM that drafts your homepage never grades it. A deterministic Python pass checks your publication claims against DBLP on every render; an optional fresh Codex thread then reviews the prose and framing.

## When to use

Generate a single-file HTML academic homepage. Optimized for PhD candidates, postdocs, and early-career researchers with public publications. v1 ships the `theory-minimal` persona (text-heavy academic page in the Zhxie / Avicenna lineage); `active-researcher` (paper thumbnails + news ticker variant) is planned.

**Use when** the user says `做个学术主页` · `from CV generate homepage` · `aris-homepage` · `PhD personal site` · `GitHub Pages homepage`.

**Do NOT use for**: portfolio sites needing image galleries; newsletter-funnel sites needing audience metrics; pure blog sites (use Jekyll/Hugo); tenured-faculty pages with student/teaching as top-level sections (use [academicpages](https://academicpages.github.io/)).

## Public demo

A real-world dogfood example: **https://wanshuiyin.github.io/** — homepage generated by this skill from a CV + the maintainer's previous manual page. Use it as a style and capability reference; **do not copy any names, affiliations, advisors, awards, paper titles, or filenames into your own examples or tests** (see *Privacy* below).

## Quick start

> This repo ships **no installer** — there is no `aris-homepage` executable on any platform. Every invocation is `python <path>/aris_homepage.py`, and the path is relative to wherever you are standing (note the `cd ./site` below). On Windows also read [`WINDOWS_en.md`](WINDOWS_en.md) / [`WINDOWS.md`](WINDOWS.md).

```bash
# Step 1 — bootstrap workspace from CV
python tools/aris_homepage.py init --from-cv ./cv.pdf --out ./site
cd ./site

# Step 2 — calling LLM agent (Claude / your agent) reads .aris-homepage/EXTRACTION_HANDOFF.md,
#          then writes the extraction JSON to .aris-homepage/extraction.json.
#          This step is NOT automated by the CLI — it's a designed handoff so the agent
#          can use richer context (manual homepage URL, asset folder, your judgement).

# Step 3 — persist the extracted JSON into editable source files
#          (we cd'd into ./site above, so the script is one level up now)
python ../tools/aris_homepage.py finalize

# Step 4 — review + tweak
$EDITOR profile.yml publications.bib bio.md news.md EXTRACTION_REVIEW.md

Report a problem