Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Superdesign Prompt Library

ASecurity

Query and retrieve Superdesign prompt-library entries (style prompts, layout prompts, and component prompts) from a local JSONL export. Use when you need reusable UI prompt building blocks or want to extract all prompts for a style/category/slug. Triggers: "superdesign", "design prompt", "prompt library", "style prompt", "layout prompt", "mosaic"

22 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentsgobash

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add lev-os/agents --skill superdesign-prompt-library --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Superdesign Prompt Library?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Superdesign Prompt Library
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/lev-os-superdesign-prompt-library/badge)](https://www.skillsdirectory.com/skills/lev-os-superdesign-prompt-library)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: superdesign-prompt-library
description: |
  Query and retrieve Superdesign prompt-library entries (style prompts, layout prompts, and component prompts)
  from a local JSONL export. Use when you need reusable UI prompt building blocks or want to extract all prompts
  for a style/category/slug.

  Triggers: "superdesign", "design prompt", "prompt library", "style prompt", "layout prompt", "mosaic"
skill_type: tool
category: process-design-prompts
version: 1.0.0
---

# Superdesign Prompt Library

Local exported prompt library with 355 entries.

## Data Files

- `references/superdesign-prompts.jsonl` - normalized prompt entries
- `references/summary.txt` - fetch metadata + counts

## Query Commands

### Find by slug/title/tag

```bash
rg -n "mosaic-grid-architecture-style|Mosaic Grid" ~/.agents/skills-db/design-ux/superdesign-prompt-library/references/superdesign-prompts.jsonl
```

```bash
jq -c 'select(.slug=="mosaic-grid-architecture-style")' ~/.agents/skills-db/design-ux/superdesign-prompt-library/references/superdesign-prompts.jsonl
```

### Extract only style prompts

```bash
jq -r 'select(.style_prompt!=null) | [.slug,.style_prompt] | @tsv' ~/.agents/skills-db/design-ux/superdesign-prompt-library/references/superdesign-prompts.jsonl
```

### Extract all layout prompts for one entry

```bash
jq -r 'select(.slug=="mosaic-grid-architecture-style") | .layout_prompts[]?.prompt' ~/.agents/skills-db/design-ux/superdesign-prompt-library/references/superdesign-prompts.jsonl
```

### Export flat prompt corpus

```bash
jq -r '[.summary_prompt,.style_prompt, (.layout_prompts[]?.prompt), (.special_component_prompts[]?.prompt)] | .[] | select(.!=null)' ~/.agents/skills-db/design-ux/superdesign-prompt-library/references/superdesign-prompts.jsonl > /tmp/superdesign-all-prompts.txt
```

## Record Shape

Each JSONL record contains:

- `id`, `slug`, `title`, `description`, `tags`
- `summary_prompt`
- `style_prompt`
- `layout_prompts[]` (`part`, `prompt`)
- `special_component_prompts[]` (`component`, `prompt`)
- `raw_prompt_json`
## Technique Map

- **rg + jq for slug/title/tag lookup** — Fast local search without loading full corpus; because 355 entries; grep beats parse-all.
- **jq select(.style_prompt!=null)** — Extract only style prompts; because layout/component prompts differ in structure.
- **jq for layout_prompts[]?.prompt** — Per-entry layout extraction; because nested structure needs explicit path.
- **Flat export to file** — summary_prompt, style_prompt, layout_prompts, component_prompts concatenated; because LLM ingestion often needs flat corpus.
- **Record shape awareness** — id, slug, title, description, tags, summary_prompt, style_prompt, layout_prompts, special_component_prompts; because query patterns depend on structure.

## Technique Notes

Data: references/superdesign-prompts.jsonl, references/summary.txt. Path: ~/.agents/skills-db/design-ux/superdesign-prompt-library/references/. Use jq -c for single record, jq -r for tab/newline output. Triggers: superdesign, design prompt, prompt library, mosaic.

---

## Prompt Architect Overlay

**Role Definition:** Superdesign prompt library query tool. Retrieves style, layout, and component prompts from local JSONL export. Provides reusable UI prompt building blocks.

**Input Contract:** Accepts slug, title, tag, or category query. Style/layout/component extraction request. "Extract all prompts for X" or "get prompts for style/category."

**Output Contract:** JSONL records or extracted prompt text. jq/rg command examples for self-service. Record structure (id, slug, style_prompt, layout_prompts, etc.). Flat export when requested.

**Edge Cases & Fallbacks:** If slug not found→suggest rg partial match or list available slugs. If structure unclear→show record shape. If path wrong→use ~/.agents/skills-db/design-ux/superdesign-prompt-library/references/.

Attribution

lev-oslev-os
View sourceMore from lev-os →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

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.

1023331 votes

Hyperplan

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', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

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.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →