pixtuoid: Skill for Claude Code

beautify-decoration (v1)

A repo-specific iteration loop for visually redesigning a decoration in pixtuoid. Follow this when the user says "beautify X" or "make Y look better" — it short-circuits several rebuild traps and visual-design dead ends that aren't obvious from the codebase alone.

When to use

• Redesigning an existing decoration sprite (pantry, lounge, meeting, cubicle decor)
• Adding a new fixture (pendant lamp, water cooler, chalkboard, etc.)
• User says "items look too small / don't read like X / blend together"
• After making sprite edits and "I don't see any change"

The visual-iteration loop

1. Edit sprite OR layout
   ↓
2. cargo build --release --example snapshot
   ↓
3. ./target/release/examples/snapshot --cols 192 --rows 80 /tmp/snap.png
   ↓
4. .venv/bin/python3 scripts/crop-snapshot.py /tmp/snap.png --scale 3 -q <quadrant>
   (or skip the quadrant guessing: snapshot --crop-furniture pantry|couch|vending|
   printer|meeting|sofa|chair|island|snackshelf|desk OR --crop-agent <label> renders a 40x24-cell window
   already centered on the target — no Python step)
   ↓
5. Read the cropped PNG → self-critique → back to step 1
   ↓
6. When happy, send to user with SendUserFile and short caption
   ↓
7. cargo build --release --workspace    ← rebuild the LIVE binary too
   ↓
8. Commit with iteration history (which designs were tried, why rejected)

The user is the final judge of "does it look like a fridge / coffee machine / etc." — but you should self-critique before sending. Three iterations of self-critique before bothering the user.

Step 7 is mandatory. cargo build --release --example snapshot does NOT rebuild the main binary. Users testing with ./target/release/pixtuoid run won't see sprite changes until the workspace is rebuilt. Forgetting this step is how "I changed the sprite but nothing happened in the live TUI" bugs get filed.

Step 8 is mandatory. Commit messages for sprite changes must include the iteration count and a one-line rationale for each rejected attempt. Future editors need to know which alternatives were explored — otherwise they'll re-try the same dead-end designs (the seated_sleeping sprite went through 4 iterations before reading correctly at scale).