以 AI 机器人身份加入视频会议,提供语音、虚拟形象与屏幕共享四种模式。
设计与多媒体
Agentic Video Production Reviewer
试用Review AI video production packages for creative consistency, asset provenance, platform metadata, disclosure wording, and publishing readiness. Use when a u...
它能做什么
Use this skill to review an AI video production package before a human-controlled publish step. The skill is instruction-only and should produce a readiness verdict, not operate accounts or upload media.
技能文档
Agentic Video Production Reviewer
Use this skill to review an AI video production package before a human-controlled publish step. The skill is instruction-only and should produce a readiness verdict, not operate accounts or upload media.
Review Workflow
- Confirm the target platform, audience, video file, title, description, thumbnail, captions, and disclosure requirements.
- Check that character, setting, music, prompt, source-asset, and generated-asset provenance are documented.
- Verify platform metadata for policy-sensitive claims, attribution, affiliate disclosure, copyright risk, and audience settings.
- Confirm that private local paths, account names, unpublished prompts, and production notes are not present in client-facing copy.
- Separate creative quality notes from release blockers.
- Return a release verdict:
ready,ready_with_notes,blocked, ordo_not_publish.
Boundaries
- Do not upload, publish, schedule, delete, monetize, or modify any video.
- Do not operate logged-in YouTube, TikTok, browser, or creator-studio sessions.
- Do not request credentials, cookies, account recovery steps, billing access, or private analytics.
- Do not expose internal production notes, local paths, private prompts, or unredacted source-asset links in client-facing output.
Output Shape
Return:
Package: files and metadata reviewed.Creative: consistency and quality findings.Policy: disclosure, copyright, platform, and audience risks.Public surface: client-facing wording issues.Verification: checks still needed before manual publish.Verdict: one ofready,ready_with_notes,blocked, ordo_not_publish.
相关技能
诊断生产力系统反复失效的根因,给出最小干预——容量测算、瓶颈定位、可靠的本地记录。
在本地磁盘以分类纯 Markdown 文件保存需要长期留存的事实,与智能体内置记忆并存。
从 AdMapix API 拉取广告创意、应用、榜单和收入预估等数据,原样返回结构化 JSON。
把自然语言描述转为结构化 JSON,并由 mcp-diagram-generator MCP 服务生成 Draw.io、Mermaid 或 Excalidraw 图表文件。
编写、调试与调优 Playwright 测试,涵盖定位器策略、追踪诊断与 CI 友好的超时配置。
zack-dev-cm 的更多技能
浏览全部技能OpenClaw CWS Publisher is a public ClawHub Chrome Web Store publisher skill. Use it when the user says "chrome web store publisher", "extension release publi...
SOTA Agent is a public ClawHub SOTA-campaign skill for CV and DS work. Use it when the user says "sota agent", "state of the art benchmark scouting", or want...
Use when studying or normalizing Chinese lesson transcript/subtitle inputs with bundled public lesson data, learner docs, local export bundles, and pilot-fir...
OpenClaw YouTube Publisher is a public ClawHub YouTube publishing skill. Use it when the user says "youtube creator ops", "youtube publisher", "YouTube Studi...
Build source-backed research claim ledgers from drafts, literature matrices, notes, citation lists, PDFs, source packets, or reviewer comments. Use when the...
Install, wire, audit, and harden AgentMemory for AI coding agents and project workspaces. Use when Codex needs to adopt rohitg00/agentmemory, configure Codex...