.claude/skills/p-video-2-pro-referenceRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Use when someone wants one cinematic clip that locks a subject from references — a product still, character, clip, or voice — using image or video references plus optional audio kept as the soundtrack or used as guidance. Not for text-only generation, 1080p, or drafts.
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/p-video-2-pro-referenceRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/p-video-2-pro-referenceRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/p-video-2-pro-referenceRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
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 @pruna-ai/p-video-2-pro-referenceclawhub inspect @pruna-ai/p-video-2-pro-reference --version 1.0.15This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
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.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:6e194735e1b4f9822e5e739cbe7d02b1eb33fe581978fd1c80824b518f3bb418skill-card.mdskill.manifest.jsonSKILL.md- Expanded guidance for crafting prompts: detail how to assign roles to each reference asset and specify what each contributes (identity, style, motion, voice). - Clarified prerequisites, agent behavior, and response patterns, including when to offer or require additional input before proceeding. - Updated skill boundary and "When NOT to use" sections to direct use to the most suitable skill for different generation scenarios. - Refined prompt fidelity checks, emphasizing the need for role assignment clarity and fresh, specific prompting that respects user intent and reference roles. - Added explicit instructions for handling `keep_audio`, free axes, and batch/multi-scene requests.