Quick Install

Each system is a .md file. Copy it to ~/.claude/commands/ once — then invoke it by name in any Claude Code session.

Product AI System
cp product-ai-system/product-ai-system.md ~/.claude/commands/product-ai-system.md
Portfolio AI System
cp portfolio-ai-system/portfolio-ai-system.md ~/.claude/commands/portfolio-ai-system.md

Live Systems

Product AI System
For designers, PMs, and engineers  ·  v3.0  ·  16-phase cycle
Live

Takes a product problem — vague idea, named feature, or draft PRD — and moves it through a 16-phase cycle to execution-ready output. The system doesn't agree with your framing. It challenges assumptions, generates competing hypotheses, stress-tests solutions, detects gaps, heals itself, learns from your input, and repeats until all critical gaps are resolved.

Includes a self-evolution mode — the system turns inward, detects drift, and fixes its own logic. And a self-learning mode — after every run, it asks what it got wrong and converts your answers into permanent improvements.

Define Issue Diagnose Define Goal Self Inquiry Hypothesis Generate Solution Challenge Self Test Gap Detection Self Healing Self Study 4-Perspective Test Execution Readiness ✦ Self-Evolution ✦ Self-Learning
/product-ai-system run [problem] Full 16-phase cycle — raw problem to execution plan
/product-ai-system evolve Self-evolution loop — challenge, test, detect gaps, fix
/product-ai-system learn [feedback] Learning loop — convert user input into permanent system improvements
/product-ai-system feature-update [feature] Re-align system after a feature changes scope or flow
Portfolio AI System
For designers and PMs applying at Staff / Principal level
Live

Evaluates a portfolio the way a hiring manager actually reads it — not "looks good," but a structured pass across positioning, content signal density, UX, mobile, and copy quality. Runs a 7-step audit and produces exact before/after rewrites. Includes a hiring simulation that gives you a verdict from four perspectives: Recruiter, Hiring Manager, Design Leader, and AI/Product Leader.

Modular skills can be run independently — hire simulation only, mobile QA only, full-site consistency scan, or execution mode that applies all fixes directly to files.

Define Intent Diagnose Issues Goal Alignment Hiring Simulation UX / QA / Mobile Rewrite Execution Plan
/portfolio-ai-system audit [portfolio] Full 7-step audit — positioning, hiring sim, UX, rewrites, execution plan
/portfolio-ai-system scan-site [site] Full cross-page audit — consistency, system-level issues, top 10 fixes
/portfolio-ai-system scan-site + execution [site] Cross-page audit + apply all fixes page-by-page
/portfolio-ai-system content-strategy [portfolio] Define what to say, what to remove, signal hierarchy, tone
/portfolio-ai-system strategy-check [site] Validate site against its defined strategy — alignment score, gaps, top fixes
/portfolio-ai-system learn-site [pages] Extract consistency baseline — positioning, tone, structure, CTA patterns
/portfolio-ai-system consistency-check [page] Check a new or changed page against the established site patterns
/portfolio-ai-system rewrite [section] Rewrite a specific section — headline, CTA, copy block
/hiring-simulation-skill [portfolio] Hiring simulation only — 4-perspective verdicts
/mobile-qa-skill [page] Mobile QA — 375px layout, overflow, tap targets checklist
/portfolio-execution-skill [audit output] Apply all audit fixes directly to files — produces change log
+
More systems coming
Each new system follows the same pattern: a system-name.md skill file, optional modular skills in skills/, optional named workflows in workflows/. Add a card here with the same structure — title, description, commands, install, download.