pd-portfolio-review
llms.txt22 starsChanged 29 days agoMITView on GitHub
An AI agent skill that reviews UX, UI and product design portfolios the way a busy hiring reviewer would. Paste a portfolio URL; get a scored report with evidence tags, red flags and at most five prioritised fixes. Informed by UXfolio’s State of UX Portfolios 2026. Scoring weights are this skill’s own. MIT licence. This repository is a Bun monorepo: installable skill under skills/pd-portfolio-review/, landing site under apps/web/. Install (Node.js 22+): How to invoke after install: ask to review a…
In this repositoryOne other file it gives its agents.
- pd-portfolio-reviewSkill
The file
Files
# Product Designer Portfolio Review > An AI agent skill that reviews UX, UI and product design portfolios the way a busy hiring reviewer would. Paste a portfolio URL; get a scored report with evidence tags, red flags and at most five prioritised fixes. Informed by UXfolio’s State of UX Portfolios 2026. Scoring weights are this skill’s own. MIT licence. This repository is a Bun monorepo: installable skill under `skills/pd-portfolio-review/`, landing site under `apps/web/`. Install (Node.js 22+): ``` npx skills add leonardobetti/pd-portfolio-review@pd-portfolio-review ``` How to invoke after install: ask to review a portfolio and include the URL, or call `/pd-portfolio-review` (Claude Code / Cursor) or `$pd-portfolio-review` (Codex). Optional inputs: target role, site password. ## Skill (agents) - [SKILL.md](skills/pd-portfolio-review/SKILL.md): Full skill instructions — fetch URL, reviewer path, fairness rules, scoring, report shape - [Report template](skills/pd-portfolio-review/references/report-template.md): Required report sections and tone - [UXfolio 2026 reference](skills/pd-portfolio-review/references/uxfolio-2026.md): Checks, red flags and cited figures by chapter - [Evals README](skills/pd-portfolio-review/evals/README.md): How to run the 27 invented review cases - [Eval cases](skills/pd-portfolio-review/evals/cases.json): Structured eval prompts and expected behaviours ## Site - [Homepage](https://pd-portfolio-review.vercel.app/): Landing — install command, how it works, score, criteria, Claude.ai upload path, FAQ - [Site llms.txt](https://pd-portfolio-review.vercel.app/llms.txt): Same overview with absolute raw.githubusercontent.com links - [GitHub repository](https://github.com/leonardobetti/pd-portfolio-review): Source ## Optional - [hiring-manager-bar (MIT)](https://github.com/kemiljk/skills/tree/main/skills/hiring-manager-bar): Upstream principles this skill incorporates (Karl Koch) - [UXfolio State of UX Portfolios 2026](https://uxfol.io/state-of-ux-portfolios-2026): Research source (not affiliated) - [LICENSE](LICENSE): MIT
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

