Source: https://docs.sogni.ai/more-superapps/creative-agent-skill/

# Creative Agent Skill

The Sogni Creative Agent Skill plugs the Sogni Supernet into the agent runtime you already use — Claude Code, [OpenClaw](https://github.com/OpenClaw/OpenClaw), [Hermes Agent](https://hermes-agent.nousresearch.com/), [Manus AI](https://manus.im/), and others. It ships as a Node CLI (`sogni-agent`), a `SKILL.md` source any skill-aware agent can load, and a published OpenClaw plugin.

### [#](https://docs.sogni.ai/more-superapps/creative-agent-skill/#npm-sogni-aisogni-creative-agent-skill)[npm: @sogni-ai/sogni-creative-agent-skill →](https://www.npmjs.com/package/@sogni-ai/sogni-creative-agent-skill)

![Creative Agent Skill rendering an image in a chat](https://docs.sogni.ai/more-superapps/creative-agent-skill/assets/hero.jpg)

## [#](https://docs.sogni.ai/more-superapps/creative-agent-skill/#what-it-does)What it does

-   **Image generation and editing.** Quality presets (`-Q fast|hq|pro`) pick the right model/steps/size; [Krea 2 Turbo](https://www.sogni.ai/models/krea-2-turbo), Z-Image Turbo, Chroma, Qwen Image Edit 2511 Lightning, and `gpt-image-2` are first-class.
-   **Video generation.** Text-to-video, image-to-video, reference-to-video, sound-to-video, audio-to-video, video-to-video, and animate workflows — auto-routed across LTX-2.3, WAN 2.2, [Seedance 2.0](https://www.sogni.ai/models/seedance-2-0) / Fast / Mini, and [HappyHorse 1.1](https://www.sogni.ai/models/happyhorse-1-1) with native dialogue and audio.
-   **Music.** Direct instrumental or full-song generation with lyrics, BPM, key, and time-signature controls.
-   **Hosted creative workflows.** `/v1/chat/completions` with Sogni creative-agent tools and `/v1/creative-agent/workflows` durable workflows including a storyboard-video preset.
-   **Durable chat and replays.** `--durable-chat` maps to `/v1/chat/runs` and streams de-duplicated per-job progress, ETA, and result lines from hosted run events. `--list-replays`, `--get-replay`, and `--ingest-replay` expose redacted Sogni Intelligence RunRecords for debugging.
-   **Personas, memory, personality.** Saved reference photos and voice clips (`--persona`), persistent preferences (`--memory-set`), and per-agent personality (`--personality-set`) survive across sessions at `~/.config/sogni/`.
-   **Per-skill loading.** Hosts can load the root `SKILL.md` or focused `skills/*.md` manifests for image, video, music, media analysis, persona/memory, app settings, composition planning, session control, and asset-reference management.
-   **Token auto-fallback.** `--token-type auto` tries free Spark first and falls back to SOGNI when Spark runs out.

## [#](https://docs.sogni.ai/more-superapps/creative-agent-skill/#full-reference)Full reference

Install steps (Node CLI, Claude Code plugin, OpenClaw), credentials setup, the complete command catalog, hosted API modes, persona/memory schemas, sizing rules, and troubleshooting live on the canonical reference:

**→ [Sogni Creative Agent Skill (full reference)](https://docs.sogni.ai/sogni-intelligence/creative-agent-skill/)**

## [#](https://docs.sogni.ai/more-superapps/creative-agent-skill/#see-also)See also

-   [Sogni n8n Plugin](https://docs.sogni.ai/more-superapps/n8n-plugin/) — the same Sogni capabilities for n8n workflows.
-   [Sogni Voice](https://docs.sogni.ai/more-superapps/voice/) — local TTS/STT that pairs naturally with agent runtimes.
-   [Sogni Intelligence](https://docs.sogni.ai/sogni-intelligence/introduction/) — the LLM platform behind `--api-chat`.
-   [Sogni Client SDK](https://docs.sogni.ai/sogni-sdk/) — the underlying SDK.
-   [Source on GitHub](https://github.com/Sogni-AI/sogni-creative-agent-skill)