# Higgsfield Cartoon

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-pixelab-ch-higgsfield-skills-03-cartoon`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [pixelab-ch](https://agentstack.voostack.com/s/pixelab-ch)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [pixelab-ch](https://github.com/pixelab-ch)
- **Source:** https://github.com/pixelab-ch/higgsfield-skills/tree/main/skills/03-cartoon

## Install

```sh
agentstack add skill-pixelab-ch-higgsfield-skills-03-cartoon
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Higgsfield Cartoon Skill

## What this skill does

Crafts production-ready cartoon and animation video prompts and routes them to the best
Higgsfield model for stylized animated output. On request, it assembles the full
parameter set, surfaces the credit cost, and — after explicit user confirmation —
generates the asset via the opt-in generation flow.

Whether crafting whimsical character animations, dynamic action sequences, or minimalist
motion graphics, this skill provides frameworks, templates, and creative guidance
drawing on 15+ animation style encyclopedias, the 12 core animation principles, hook
frameworks, and worked example prompts.

---

## Model routing

### Primary and fallback video models

| | wan2_7 (primary) | seedance_2_0 (fallback) |
|---|---|---|
| **Rationale** | Clean stylized output for cartoon and animation styles | Use only when primary is unavailable, or user needs genre tags / shorter minimum |
| **Resolution** | `720p`, `1080p` | `480p`, `720p`, `1080p` (def `720p`) |
| **Aspect ratios** | `16:9`, `9:16`, `1:1`, `4:3`, `3:4` | `auto`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` |
| **Duration** | 2–15 s (continuous range) — **minimum 2 s** | 4–15 s (continuous range) — minimum 4 s |
| **Tunable params** | None beyond resolution and aspect | `mode` {`std`,`fast`}, `genre` {`auto`,`action`,`horror`,`comedy`,`noir`,`drama`,`epic`} |
| **Media roles** | `start_image`, `end_image`, `audio` | `image`, `start_image`, `end_image`, `video`, `audio` |

**Routing rule:** Use `wan2_7` by default. Only fall back to `seedance_2_0` when (1) the
primary model is unavailable, or (2) the user explicitly accepts seedance_2_0's
constraints after being told what they give up: minimum clip duration becomes 4 s
(cannot generate 2-3 s clips). Gain: `genre` tag for comedy/drama bias, and `image`/
`video` media roles. If the user has not been informed of these trade-offs, stay on
`wan2_7` and let them decide — never switch silently.

**MODEL-06 directive:** If a parameter is rejected at generation time, call
`higgsfield:models_explore` with the target model name to re-verify the live schema.
Full parameter tables: [references/model-specs.md](references/model-specs.md).

### Per-platform quick rule

Vertical `9:16` for TikTok / Reels / Shorts; `16:9` for YouTube and LinkedIn; `1:1`
for Instagram feed. wan2_7's 2-second minimum suits ultra-short social hooks. Full
per-platform table: [references/model-specs.md](references/model-specs.md).

---

## Prompt-building workflow

1. **Gather intent** — Confirm with the user: cartoon style (Disney, Cartoon Network,
   flat vector, Ghibli, pixel art, etc.), character/subject, tone (comedic, whimsical,
   dramatic), target platform, aspect ratio, and desired duration.

2. **Select model** — Apply the routing table above. Choose `wan2_7` by default;
   select `seedance_2_0` only when a routing trigger applies.

3. **Build the prompt** — Use the craft principles in the references below:
   - Opening hook (2-second cartoon attention-capture technique) from
     [references/hooks.md](references/hooks.md)
   - Art style, animation principles, color palette, character design from
     [references/animation-craft.md](references/animation-craft.md)
   - Worked example prompts by style from
     [references/examples.md](references/examples.md)

4. **Present for review** — Show the assembled prompt and all parameters to the user for
   review and refinement **before** any generation call. The user must approve the prompt
   text, model, aspect ratio, and duration.

---

## Opt-in generation

Generation costs Higgsfield credits and requires explicit user confirmation before any
generate call is made. This skill never auto-generates.

**Full step-by-step flow** (confirmation gate, balance/cost surface,
generate → poll → display):
[`../../shared/generation-flow.md`](../../shared/generation-flow.md)

**This skill's primary model:** `wan2_7`

**Media upload:** Conditional — only when the user supplies a `start_image`, `end_image`,
or `audio` reference. This skill is NOT a mandatory-I2V skill; T2V is the default path.
When the user provides a reference file, run the `higgsfield:media_upload` →
`higgsfield:media_confirm` atomic pair before generating.

**Tool signatures:** [`../../shared/mcp-tools.md`](../../shared/mcp-tools.md)

---

## Reference materials

| File | Contents |
|---|---|
| [references/model-specs.md](references/model-specs.md) | Per-model parameter tables, aspect ratios, durations, routing rationale, and re-verify directive for wan2_7 and seedance_2_0 |
| [references/animation-craft.md](references/animation-craft.md) | 15+ art style encyclopedia, 12 animation principles in prompt language, character design principles, color palettes (8+), line-work styles, background approaches, character animation keywords, transition and effect library |
| [references/hooks.md](references/hooks.md) | 2-second hook framework with 10+ cartoon hook techniques, prompt integration phrases, hook selection guide by tone, and advanced hook-stacking guidance |
| [references/examples.md](references/examples.md) | Master prompt template, 5 full production-quality cartoon example prompts (Warner Bros. action, Ghibli peaceful, flat vector explainer, retro rubber hose, comedy skit), style deployment guide, and common-mistakes fix table |

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [pixelab-ch](https://github.com/pixelab-ch)
- **Source:** [pixelab-ch/higgsfield-skills](https://github.com/pixelab-ch/higgsfield-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-pixelab-ch-higgsfield-skills-03-cartoon
- Seller: https://agentstack.voostack.com/s/pixelab-ch
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.