Infini-AI-Lab

Iterate Centroids Score — Design skill for Claude Code

Design community

Run the long-horizon centroid-score kernel iterate loop autonomously — design 4 variants, JIT-compile, benchmark, generate reports, analyse, repeat.

How to install Iterate Centroids Score

Installs to ~/.claude/commands/infini-ai-lab-vortex_torch-iterate_centroids_score.md

Terminal
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/Infini-AI-Lab/vortex_torch/HEAD/.claude/commands/iterate_centroids_score.md -o ~/.claude/commands/infini-ai-lab-vortex_torch-iterate_centroids_score.md

Restart Claude Code, or start a new session, for it to be picked up.

What Iterate Centroids Score does


description: Run the long-horizon centroid-score kernel iterate loop autonomously — design 4 variants, JIT-compile, benchmark, generate reports, analyse, repeat. Stops after --max-iterations batches (default 3). argument-hint: [--max-iterations ] [--q ] [--num-gpus ]

You are now running the **centroid-score kernel iterate loop** autonomously. Do not ask for confirmation between steps; execute each step in sequence and loop until the iteration budget is reached.

Unlike `/iterat

Alternatives in Design

  • Module CSS — Compile module CSS assets or fix Tailwind prefix issues 407 ★
  • Component Docs — Auto-generate component documentation from Figma — props, variants, usage guidelines, spacing specs, and code 309 ★
  • Design Bench — Run the ABC benchmark — reference URL → design-blind brief → render arms A/B/C → blind judge → scorecard with 117 ★

Full documentation available on GitHub

View Source Repository