메뉴
Modular prompt card system for AI agents with meta prompts, role cards, and workflow cards.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Open local review artifacts in Xiaoer Omia when users ask to open, preview, inspect, or review a file.
Run a measured improvement loop for a skill by defining a yes/no checklist, capturing a baseline, scoring candidate outputs, and logging each iteration's keep/revert decision. Use when a skill works inconsistently and you want evidence-driven iteration instead of random prompt edits.
Build a static HTML report site from CSV, JSON, Markdown, or HTML inputs. Use when the user wants to turn existing data into a human-readable site, generate a data showcase page, create a static report website, or optionally publish the built site.
Add offline multilingual support to static HTML, small web projects, or reports by extracting text into tokens, maintaining language dictionaries, applying translated outputs, and optionally embedding a local language switcher. Use when the user asks for bilingual support, tokenizing Chinese copy, offline language switching, or i18n for reports and lightweight sites.
Unified entrypoint for Obsidian note operations such as cleanup, merge, lint/fix, meeting archive, daily rollover, and docs sync. Use when the user wants one command surface over an existing notes-tools repo instead of calling many atomic scripts by hand.
Test, tune, and regression-check LLM system prompts with a golden dataset. Use when the user wants to optimize a prompt, run prompt regression tests, manage `cases.yaml`, compare expected vs actual outputs, or follow a TDD workflow for prompts.
| name | prompt-cards |
| description | Modular prompt card system for AI agents with meta prompts, role cards, and workflow cards. |
| version | 1.0.0 |
| author | Vivi |
| tags | ["prompts","ai-agents","workflow","design"] |
| platforms | ["all"] |
| dependencies | [] |
Enhance AI agents with specialized capabilities through loadable prompt cards.
# Browse available cards
find . -name "*.md" -not -path "./templates/*" -not -name "SKILL.md" -not -name "README.md"
# Load a card into your AI agent
cat meta/frontend-aesthetics.md
# Combine cards
cat meta/frontend-aesthetics.md roles/pop-art-web-generator.md
| Card | File | Purpose |
|---|---|---|
| Frontend Aesthetics Guide | meta/frontend-aesthetics.md | Anti-AI-slop design principles, high-density layouts |
| Card | File | Purpose |
|---|---|---|
| Pop Art Web Generator | roles/pop-art-web-generator.md | Generate pop art style web pages with 4-color system |
| Card | File | Purpose |
|---|---|---|
| Prompt Co-Pilot | workflows/prompt-copilot.md | 3-phase collaborative prompt creation (30-60 min) |
| AgoraRead | workflows/agoraread.md | Structured content analysis and synthesis |
| Type | Behavior | Stackable | Duration |
|---|---|---|---|
| Meta | Modifies how the AI thinks | Yes (up to 5) | Persistent |
| Role | Transforms personality/capability | No (one at a time) | Until switched |
| Workflow | Structured multi-phase process | No (one at a time) | 30-90 min |
Direct loading (AI agents):
cat roles/pop-art-web-generator.md | your-ai-agent
Programmatic (developers):
with open('meta/frontend-aesthetics.md') as f:
card = f.read()
system_prompt = base_prompt + "\n\n" + card
Copy-paste (manual):
cat workflows/prompt-copilot.md
# Paste into your AI chat
Meta + Role: frontend-aesthetics + pop-art-web-generator = styled pop art with anti-slop principles
Meta + Workflow: frontend-aesthetics + prompt-copilot = design-aware prompt engineering
cp templates/card-template.md meta/my-card.md
Card frontmatter:
---
name: card-name
type: meta|role|workflow
description: What this card does
version: 1.0.0
---
Guidelines:
prompt-cards/
├── meta/ # Stackable behavior modifiers
│ └── frontend-aesthetics.md
├── roles/ # Exclusive personality cards
│ └── pop-art-web-generator.md
├── workflows/ # Time-bound processes
│ ├── agoraread.md
│ └── prompt-copilot.md
├── templates/
│ └── card-template.md # Template for new cards
├── SKILL.md
└── README.md
Card not affecting behavior? Ensure it's loaded into context. Role cards are exclusive — loading a new one replaces the previous.
Conflicting cards? Meta prompts stack; roles don't. Remove the conflicting role card.