Prompt iteration workflow for kid-friendly, realistic outputs. Use when tuning prompts, selecting styles, or when outputs look too similar to the original sketch.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add majiayu000/claude-skill-registry --skill sketch-prompt-lab --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Sketch Prompt Lab?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/majiayu000-sketch-prompt-lab)More formats (shields.io, HTML) on the badges page.
---
name: sketch-prompt-lab
description: Prompt iteration workflow for kid-friendly, realistic outputs. Use when tuning prompts, selecting styles, or when outputs look too similar to the original sketch.
---
# 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`
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.