Token导航 LogoToken导航TokenDH.com
前端设计操作浏览器github未标认证来源可访问许可证需确认审计通过

hackathon-demo-video黑客马拉松演示视频

Agent Skill

用于辅助视频生成、动画合成、脚本化剪辑或 Remotion 等视频项目开发。它适合让 Agent 组织镜头、生成素材说明、维护合成代码或排查渲染问题。使用时需要确认分辨率、时长、素材路径和导出格式;涉及外部素材、人物肖像或商业发布时,应先核对版权授权和内容审核要求。

总安装

504

周安装

21

GitHub Stars

1

下载量

168
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:hackathon-demo-video(黑客马拉松演示视频)
来源仓库:https://github.com/bernieweb3/hackathon-ai-devkit
仓库路径:skills/hackathon-demo-video
安装命令:
npx skills add https://github.com/bernieweb3/hackathon-ai-devkit --skill hackathon-demo-video
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/bernieweb3/hackathon-ai-devkit --skill hackathon-demo-video

简介

用于辅助视频生成、动画合成和 Remotion 项目开发,支持镜头组织与素材说明。

  • 适合让 Agent 维护合成代码、排查渲染问题或生成演示视频脚本。
  • 使用时需确认分辨率、时长、素材路径和导出格式,避免版权风险。
  • 安装方式:通过 GitHub 仓库安装,命令为 npx skills add https://github.com/bernieweb3/hackathon-ai-devkit --skill hackathon-demo-video。
  • 注意:涉及人物肖像或商业发布时,应先核对授权与内容审核要求。

SKILL.md

hackathon-demo-video

Goal

Produce a structured script and shot list for a hackathon demo video that showcases the project's core value within a strict time limit.


Trigger Conditions

Use this skill when:

  • The MVP demo flow is implemented and stable
  • A demo video must be recorded for submission or as a live-demo fallback
  • The wow moment timing and placement in the video need to be optimized
  • The recording environment must be checked and locked before recording begins
  • Invoked during Phase 6; run in parallel with hackathon-pitchdeck after code freeze

Inputs

InputTypeRequiredDescription
project_titlestringYesName of the project
taglinestringYesOne-sentence description
mvp_demo_flowobject[]YesDemo steps from hackathon-scope-cutter
wow_factorstringYesThe single most impressive moment
video_duration_secondsintegerYesTarget video length in seconds
demo_environmentstringNoWhere the demo runs (e.g., web browser, mobile, CLI)
voiceoverbooleanNoWhether the video includes voiceover (default: true)

Outputs

OutputDescription
scriptTime-coded narration script
shot_listWhat is shown on screen at each moment
wow_moment_timestampWhen in the video the wow factor hits
recording_checklistPre-recording setup and validation steps
fallback_planWhat to do if live demo fails during recording

Rules

  1. The first 5 seconds must state the problem or hook — no introductions.
  2. wow_factor must appear before the 60% mark of video_duration_seconds.
  3. Every mvp_demo_flow step must map to at least one shot.
  4. Narration sentences must be under 15 words each.
  5. Reserve the final 10% of video time for a summary and call-to-action.
  6. recording_checklist must include at least: notifications off, test data ready, screen resolution set.
  7. fallback_plan must be a static slide or pre-recorded segment, never "we'll skip this part."

Output Format

wow_moment_timestamp: <seconds>

script:
  - timestamp_start: <seconds>
    timestamp_end: <seconds>
    narration: "<spoken words>"

shot_list:
  - timestamp_start: <seconds>
    timestamp_end: <seconds>
    screen_content: "<what is visible>"
    action: "<what the presenter does>"

recording_checklist:
  - "<item>"

fallback_plan:
  trigger: "<condition>"
  action: "<what to do>"

Example

Input:

project_title: "AnchorAI"
tagline: "An AI companion that remembers your emotional journey."
wow_factor: "AI recalls emotional context from 3 days ago and adapts tone in real time"
video_duration_seconds: 120
demo_environment: "web browser"
voiceover: true
mvp_demo_flow:
  - step: 1
    action: "User types 'I'm overwhelmed today'"
    outcome: "AI responds empathetically"
  - step: 2
    action: "User mentions recurring work stress"
    outcome: "AI references last week's conversation"
  - step: 3
    action: "User expresses hopelessness"
    outcome: "Crisis resource card appears"

Output:

wow_moment_timestamp: 45

script:
  - timestamp_start: 0
    timestamp_end: 8
    narration: "40% of college students live with anxiety. Most wait 6 weeks for help."
  - timestamp_start: 8
    timestamp_end: 15
    narration: "AnchorAI is always available — and it remembers you."
  - timestamp_start: 15
    timestamp_end: 45
    narration: "Watch what happens when a student checks in after a hard week."
  - timestamp_start: 45
    timestamp_end: 70
    narration: "AnchorAI recalls last week's conversation — without being told."
  - timestamp_start: 70
    timestamp_end: 95
    narration: "When a student signals distress, AnchorAI responds with care and resources."
  - timestamp_start: 95
    timestamp_end: 120
    narration: "No waitlist. No starting over. AnchorAI — always there."

shot_list:
  - timestamp_start: 0
    timestamp_end: 8
    screen_content: "Stat card: '40% of students report anxiety. Average wait: 6 weeks.'"
    action: "Hold on stat card"
  - timestamp_start: 15
    timestamp_end: 45
    screen_content: "Chat interface — user types message"
    action: "Type 'I'm feeling overwhelmed again this week'"
  - timestamp_start: 45
    timestamp_end: 70
    screen_content: "AI response references 'last week's exam stress you mentioned'"
    action: "Scroll to highlight the memory reference in the AI response"
  - timestamp_start: 70
    timestamp_end: 95
    screen_content: "User types hopelessness message; crisis card slides in below response"
    action: "Type message; pause on crisis card appearing"

recording_checklist:
  - "Notifications disabled on OS and browser"
  - "Demo account pre-loaded with 1 prior session in Redis"
  - "Screen resolution set to 1920×1080; browser zoom 125%"
  - "Test data: prior session summary contains 'exam stress' phrase"
  - "Run full demo flow once before recording"

fallback_plan:
  trigger: "OpenAI API fails to respond during recording"
  action: "Use pre-recorded screen capture of the memory recall exchange as an overlay segment"

Context Files

Knowledge Base

  • knowledge/hackathon-demo-psychology.md
  • knowledge/hackathon-demo-patterns.md
  • knowledge/hackathon-pitch-strategy.md

Templates

  • templates/demo-script-template.md

Playbooks

  • playbooks/hackathon-workflow.md

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

38.63%
按下载量换算65

Claude

30.44%
按下载量换算51

Cursor

17.5%
按下载量换算29

Gemini CLI

10.12%
按下载量换算17

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills