video-agent-skills

Use this skill when the user asks for video critique, production feedback, or scene-by-scene notes on a local video file.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "video-agent-skills" with this command: npx skills add dunctk/video-agent-skills/dunctk-video-agent-skills-video-agent-skills

Video Agent Skills

When to use

Use this skill when the user asks for video critique, production feedback, or scene-by-scene notes on a local video file.

Requirements

  • A Gemini API key must be available as GEMINI_API_KEY or GOOGLE_API_KEY .

  • The video file path must be accessible on disk.

If the key is not set, ask the user to set it (or use ~/.config/video-agent-skills/.env ). Do not proceed without a key.

Command

Run the bundled binary in this skill folder:

{skill_dir} is the absolute path to this skill folder

{skill_dir}/bin/video-agent-skills feedback
-video "{video_path}"
-prompt "{optional_user_prompt}"

Harshness tiers (optional):

{skill_dir}/bin/video-agent-skills feedback
-video "{video_path}"
-tone nice

For reverse-engineering the likely prompt used to make a video:

{skill_dir}/bin/video-agent-skills reverse
-video "{video_path}"
-prompt "{optional_user_prompt}"

Notes:

  • Omit -prompt if the user did not provide custom guidance.

  • You can pass -model or -api-key if the user specifies them.

  • Use -tone only for feedback . For reverse , it is ignored.

  • On Windows, the binary name ends with .exe .

Output handling

Return the tool output directly to the user. If the tool reports missing API keys or file errors, surface the error and ask the user to resolve it.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

klaviyo

Klaviyo API integration with managed OAuth. Access profiles, lists, segments, campaigns, flows, events, metrics, templates, catalogs, and webhooks. Use this skill when users want to manage email marketing, customer data, or integrate with Klaviyo workflows. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).

Archived SourceRecently Updated
Automation

lifelog

生活记录自动化系统。自动识别消息中的日期(今天/昨天/前天/具体日期),使用 SubAgent 智能判断,记录到 Notion 对应日期,支持补录标记。 适用于:(1) 用户分享日常生活点滴时自动记录;(2) 定时自动汇总分析并填充情绪、事件、位置、人员字段

Archived SourceRecently Updated
Automation

unified-self-improving

统一自我进化系统,整合 self-improving-agent、self-improving、mulch 三个技能的优势,提供结构化日志、三层存储、自动升级、模式检测、命名空间隔离和 token 高效的 JSONL 格式支持。

Archived SourceRecently Updated
Automation

create-telegram-agent

Create a new Telegram agent in OpenClaw with proper configuration. Use when user wants to create a new Telegram bot agent, including setting up agent workspace, Telegram binding, and bot token configuration. Requires user confirmation before modifying openclaw.json.

Archived SourceRecently Updated