skill-to-card

End-to-end workflow that creates a skill from a description and attached files, publishes it to Sundial as a private skill, generates a trading card (front + back with QR code), and sends it to a printer. Use when the user wants to create a skill and get a printed trading card, or says "skill to card", "create and print a skill card", "make me a skill with a card".

148 stars

Best use case

skill-to-card is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

End-to-end workflow that creates a skill from a description and attached files, publishes it to Sundial as a private skill, generates a trading card (front + back with QR code), and sends it to a printer. Use when the user wants to create a skill and get a printed trading card, or says "skill to card", "create and print a skill card", "make me a skill with a card".

Teams using skill-to-card should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/skill-to-card/SKILL.md --create-dirs "https://raw.githubusercontent.com/sundial-org/skills/main/skills/skill-to-card/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/skill-to-card/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How skill-to-card Compares

Feature / Agentskill-to-cardStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

End-to-end workflow that creates a skill from a description and attached files, publishes it to Sundial as a private skill, generates a trading card (front + back with QR code), and sends it to a printer. Use when the user wants to create a skill and get a printed trading card, or says "skill to card", "create and print a skill card", "make me a skill with a card".

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Skill-to-Card Pipeline

Creates a skill, publishes it privately to Sundial, generates a trading card, and prints it.

## Step 1: Create the Skill

Gather from the user: what the skill should do, concrete usage examples, and any attached files/context.

Read [references/skill-creation-guide.md](references/skill-creation-guide.md) for the full skill creation spec — anatomy, frontmatter rules, body writing guidelines, and design patterns. Follow it exactly.

Use a YAML-safe frontmatter description format for long text:
```yaml
---
name: skill-name
description: >-
  What the skill does and when to use it. Trigger phrases include:
  "example one", "example two", "example three".
---
```

Validate frontmatter before push:
```bash
npx -y -p gray-matter node -e '
const fs = require("fs");
const matter = require("gray-matter");
const file = process.argv[1];
const src = fs.readFileSync(file, "utf8");
const { data } = matter(src);
if (!data.name || !data.description) {
  throw new Error("SKILL.md frontmatter must include name + description");
}
console.log("Frontmatter OK");
' /absolute/path/to/skill-dir/SKILL.md
```

## Step 2: Publish to Sundial (Private)

1. Authenticate via env var (preferred) or interactive login:
   ```bash
   # Option A: env var (no interactive login needed)
   export SUNDIAL_TOKEN="your-token-here"
   # Option B: interactive
   npx sundial-hub auth login
   ```

2. Push as private. Use an **absolute path** to the skill directory. Categories are **space-separated** (not comma-separated):
   ```bash
   npx sundial-hub push /absolute/path/to/skill-dir \
     --version 1.0.0 \
     --changelog "Initial release" \
     --visibility private \
     --categories creative writing
   ```

   Valid categories (pick 1-3): `product`, `research`, `outreach`, `marketing`, `admin`, `health`, `creative`, `financial`, `learning`, `community`, `coding`, `writing`, `other`.

   The push output looks like:
   ```
   ✔ Created skill-name v1 on the hub
   View on hub: https://www.sundialhub.com/AUTHOR/SKILL_NAME
   Push complete!
   Skill page: https://www.sundialhub.com/AUTHOR/SKILL_NAME
   ```
   Parse the author and skill name from this output.

   **Important**: There is no `info` or `show --json` command. Do NOT try `npx sundial-hub info` — it doesn't exist.

3. After push, fetch generated metadata (including `use_cases`) via the API:
   ```bash
   curl -s "https://www.sundialhub.com/api/hub/skills/by-author-name/AUTHOR/SKILL_NAME" \
     -H "Authorization: Bearer $SUNDIAL_TOKEN" | python3 -m json.tool
   ```
   The response JSON has this structure:
   ```json
   {
     "skill": {
       "name": "skill-name",
       "author": "author-name",
       "description": "...",
       "use_cases": [
         {"title": "Power Name", "desc": "What it does", "icon": "emoji"},
         ...
       ]
     }
   }
   ```
   `use_cases` are generated server-side from the skill content. Extract them for the card's Powers.
   For cards, do **not** pass all use cases:
   - Keep only **2 or 3** total powers
   - If 3+ exist, use the first 3
   - If only 2 exist, use both
   - Never pass more than 3 `--powers` arguments

## Step 3: Generate Trading Card

Use the bundled script to generate both front and back. You **MUST** pass `--reference-front` and `--reference-back` explicitly — do NOT rely on defaults, they won't resolve correctly.

First, locate the template files bundled with this skill:
- `templates/reference-front.jpg` — the canonical front card style (cartoon/anime, warm golden)
- `templates/reference-back.png` — the canonical back card with QR code area

Then run:

```bash
uv run SKILL_DIR/scripts/generate_single_card.py \
  --name "Skill Display Name" \
  --author "author-name" \
  --slug "author/skill-name" \
  --reference-front SKILL_DIR/templates/reference-front.jpg \
  --reference-back SKILL_DIR/templates/reference-back.png \
  --character "vivid character description matching the skill's theme — a person or creature with visual elements that represent what the skill does, wearing themed attire, dynamic pose" \
  --powers "emoji **Power Title** -- Power description" \
  --powers "emoji **Power Title** -- Power description" \
  --powers "emoji **Power Title** -- Power description" \
  --rarity Common \
  --qr-url "https://sundialhub.com/author/skill-name" \
  --side both \
  --output-dir /tmp/trading-cards/skill-name
```

Where `SKILL_DIR` is the absolute path to this skill-to-card directory. Use absolute paths for all file arguments.

### Card data mapping
- **name**: Skill display name (title case)
- **author**: From API response `skill.author`
- **slug**: `author/skill-name`
- **powers**: Map only the selected 2-3 card use cases to: `"{icon} **{title}** -- {desc}"`. Pass each as a separate `--powers` argument (2 or 3 total).
- **character**: Invent a vivid fantasy character matching the skill's theme. Include appearance, outfit with skill-themed elements, pose, and expression.
- **rarity**: New skills default to Common.
- **url**: `https://sundialhub.com/{slug}` — used for QR code on card back

### Requirements
- `GEMINI_API_KEY` env var must be set
- Templates are bundled at `templates/reference-front.jpg` and `templates/reference-back.png`

## Step 4: Print the Card

> **Printer connection TBD**

```bash
# Placeholder — replace with actual printer command when connected
# print-card --front /tmp/trading-cards/{name}-common.png \
#            --back /tmp/trading-cards/{name}-common-back.png \
#            --printer PRINTER_NAME
echo "Card images saved to /tmp/trading-cards/{skill-name}/"
```

Show the user the generated card images and inform them where the files are saved.

Related Skills

cs448b-visualization

148
from sundial-org/skills

Data visualization design based on Stanford CS448B. Use for: (1) choosing chart types, (2) selecting visual encodings, (3) critiquing visualizations, (4) building D3.js visualizations, (5) designing interactions/animations, (6) choosing colors, (7) visualizing networks, (8) visualizing text. Covers Bertin, Mackinlay, Cleveland & McGill.

training-data-curation

148
from sundial-org/skills

Guidelines for creating high-quality datasets for LLM post-training (SFT/DPO/RLHF). Use when preparing data for fine-tuning, evaluating data quality, or designing data collection strategies.

tinker

148
from sundial-org/skills

Fine-tune LLMs using the Tinker API. Covers supervised fine-tuning, reinforcement learning, LoRA training, vision-language models, and both high-level Cookbook patterns and low-level API usage.

tinker-training-cost

148
from sundial-org/skills

Calculate training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.

skill

148
from sundial-org/skills

Find, install, create, improve, and publish AI agent skills through the Sundial ecosystem. Use when the user wants to find or search for skills, install a skill, create a new skill, improve or evaluate an existing skill, or publish a skill to Sundial Hub. Trigger phrases include "find a skill", "install skill", "create a skill", "make a skill", "improve this skill", "evaluate skill", "publish skill", "push skill", "search for skills".

project-referee

148
from sundial-org/skills

Critiques ML conference papers with reviewer-style feedback. Use when users want to anticipate reviewer concerns, identify weaknesses, check claim-evidence gaps, or find missing citations.

neuro-symbolic-reasoning

148
from sundial-org/skills

Neuro-symbolic AI combining LLMs with symbolic solvers. Use when exploring neuro-symbolic approaches (ideation, no code) or implementing solver integrations (code).

icml-reviewer

148
from sundial-org/skills

Paper reviewer that evaluates machine learning research projects following official ICML reviewer guidelines. Provides comprehensive reviews with actionable feedback across all key dimensions: claims/evidence, relation to prior work, originality, significance, clarity, and reproducibility. Also provides formative feedback on incomplete drafts, proposals, and research code repositories. MANDATORY TRIGGERS: review paper, ICML review, paper review, evaluate paper, research paper feedback, ML paper review, conference review, academic review, paper critique, NeurIPS review, ICLR review, project proposal, research proposal, paper draft, early feedback, incomplete paper, work in progress, WIP review, review repo, review codebase, research project review

cs-research-methodology

148
from sundial-org/skills

Conduct a literature review and develop a CS research proposal. Use when asked to review a research area, find gaps in existing work, and propose a novel research contribution. The output is a research proposal identifying an assumption to challenge (the "bit flip") and how to validate it.

commit-splitter

148
from sundial-org/skills

Split large sets of uncommitted changes into logical, well-organized commits. Use when the user has many uncommitted changes and wants structured commits, or proactively suggest when detecting a large diff that would benefit from splitting.

codex

148
from sundial-org/skills

Run OpenAI's Codex CLI agent in non-interactive mode using `codex exec`. Use when delegating coding tasks to Codex, running Codex in scripts/automation, or when needing a second agent to work on a task in parallel.

ai-co-scientist

148
from sundial-org/skills

Transform Claude Code into an AI Scientist that orchestrates research workflows using tree-based hypothesis exploration. Triggers on "research project", "scientific experiment", "run experiments", "AI scientist", "tree search experimentation", "systematic study".