sketch-prompt-lab
Prompt iteration workflow for kid-friendly, realistic outputs. Use when tuning prompts, selecting styles, or when outputs look too similar to the original sketch.
npx skills add majiayu000/claude-skill-registry --skill sketch-prompt-lab --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Sketch Prompt Lab ## Overview Guide prompt iteration for friendly, realistic outputs while keeping the child’s intent and avoiding unsafe themes. ## Workflow ### 1) Start with a preset Pick the closest preset from `references/prompt-recipes.md` and keep the safety language intact. ### 2) Adjust one dimension at a time - **Realism**: “storybook-realistic” → “more realistic textures and lighting.” - **Color**: “bright cheerful colors” → “soft pastel colors.” - **Background**: “simple background” → “cozy bedroom or park.” ### 3) Avoid overfitting to the original If the output matches the sketch too closely, add: - “Use the sketch as inspiration, but create a new, finished illustration.” - “Refine shapes and add realistic textures.” ### 4) Enforce guardrails - Keep “friendly, safe, no weapons.” - Keep prompts under the configured length limits. ## References - `references/prompt-recipes.md`
- Overview
- Workflow
- 1) Start with a preset
- 2) Adjust one dimension at a time
- 3) Avoid overfitting to the original
- 4) Enforce guardrails
- References
What does the sketch-prompt-lab skill do?
Prompt iteration workflow for kid-friendly, realistic outputs. Use when tuning prompts, selecting styles, or when outputs look too similar to the original sketch.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill sketch-prompt-lab --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.