Real Skill packageSource verifiedClawHub registry

sogni-creative-agent-skill

CLI and agent skill for personal LoRAs, image, video, and music generation using Sogni AI's decentralized GPU network. Supports Pixal3D single- and multi-view image-to-GLB, BiRefNet background removal, Qwen3-TTS speech/voice cloning/design, MiniMax Music 3, SAM 3 object selection, promptless RTX VSR image upscaling through 16K, promptless FlashVSR video upscaling to 1080p/1440p, one-click image-folder loop reels, personas (named people with saved reference photos and voice clips), persistent memories, custom perso…

Identity and source

Publisher attributionSogni AIregistry owner unverified by skillvetai
Functional categoryVideo, Audio & Voiceautomatically inferred · 66% rule confidence
Package forminstruction with code55 recorded files
Canonical sourceClawHub registryclawhub:sogni-ai:sogni-creative-agent-skill
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/28/2026.claude/skills/sogni-creative-agent-skill

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/28/2026.agents/skills/sogni-creative-agent-skill

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/28/2026skills/sogni-creative-agent-skill

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @sogni-ai/sogni-creative-agent-skill
clawhub inspect @sogni-ai/sogni-creative-agent-skill --version 3.54.3

Security evidence

SkillVetAI static result: high signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
partial text content
Files
40 / 55 inspected as text
Checked
9/28/2026, 5:27:28 AM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
highInstructions or code access sensitive credential locationsREADME.md:361 · confidence 85%keychain) unless you've alread
1 High/Critical review queue entry
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
Open human review queue →
5 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
18 dependency and API indicators
  • api: api.sogni.ai
  • api: cdn.example.com
  • api: clawhub.ai
  • api: docs.bfl.ai
  • api: docs.sogni.ai
  • api: fal.ai
  • api: github.com
  • api: goose-docs.ai
  • api: hermes-agent.nousresearch.com
  • api: huggingface.co
  • api: img.shields.io
  • api: keepachangelog.com
  • api: platform.stability.ai
  • api: raw.githubusercontent.com
  • api: registry.npmjs.org
  • api: semver.org
  • api: www.krea.ai
  • api: www.npmjs.com
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
9/27/2026, 8:22:07 PM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:99aaf0ebe454bd6076ecc9e6cf3278dcf3cfaac507d3b31b016207fa1d07b179
Show up to 30 recorded paths
  • attribution.mjs
  • CHANGELOG.md
  • env.mjs
  • generated/creative-agent-runtime.mjs
  • host-launchers/claude-code.mjs
  • host-launchers/codex.mjs
  • host-launchers/goose.mjs
  • host-launchers/hermes.mjs
  • LICENSE
  • llm.txt
  • media-utilities.mjs
  • node-version-check.mjs
  • README.md
  • references/h3-video-loras.md
  • references/hosted-api.md
  • references/image-prompting.md
  • references/interactive-worlds.md
  • references/krea2-loras.md
  • references/long-jobs-and-queues.md
  • references/loop-maker.md
  • references/models.md
  • references/object-selection.md
  • references/openclaw-config.md
  • references/personal-loras.md
  • references/personas-memory.md
  • references/private-mature-video.md
  • references/seamless-tiling.md
  • references/video-editing.md
  • references/video-prompting.md
  • sam-segmentation.mjs

Source changelog

3.54.3: MiniMax H3 keyframes are now named in the prompt, the way MiniMax's own keyframe workflow does it. Update the intelligence client to 4.6.3 and the bundled runtime to creative agent 2.7.3, which write and check keyframe prompts in that format and state Sound to Video's real length (6 seconds renders 158 frames).