Token导航 LogoToken导航

Agent Skill · 效率

nation-resilience-hook-video-gen(国家韧性挂钩视频生成)

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。

nation-resilience-hook-video-gen 是效率类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在效率类的 21,003 个 Skill 里排第 14,945。

总安装 3,246周安装 138GitHub Stars 1下载 1,137核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

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:nation-resilience-hook-video-gen(国家韧性挂钩视频生成)
来源仓库:https://github.com/zoucdr/nation-resilience-hook-video-gen
安装命令:
openclaw skills install nation-resilience-hook-video-gen
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install nation-resilience-hook-video-gen

这个 Skill 是做什么的

效率类 Skill 把重复的整理、汇总、转换工作交给助手完成,减少手工复制粘贴。

nation-resilience-hook-video-gen 创建垂直国家韧性主题短视频钩子,含地图动画与风险提示。适用于地理、安全或公共政策类内容创作与视觉化演示。使用定时英文屏幕文本与 WeryAI 接口生成动态画面。注意核对数据来源准确性,避免误导性信息传播。

适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install nation-resilience-hook-video-gen;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

nation-resilience-hook-video-gen 怎么安装?

在终端执行 openclaw skills install nation-resilience-hook-video-gen。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

nation-resilience-hook-video-gen 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

nation-resilience-hook-video-gen 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

nation-resilience-hook-video-gen 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

nation-resilience-hook-video-gen 用的人多吗?

公开数据是累计安装 3,246 次,近一周安装 138 次,下载 1,137 次,GitHub 1 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

nation-resilience-hook-video-gen 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理效率类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

效率类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
github

GitHub 代码协作 · OpenClaw

7,632,918545需要联网MIT-0通过
nano-pdf

Nano PDF 文档 · OpenClaw

4,249,476231需要联网MIT-0通过
auto-updater

自动更新程序 · OpenClaw

2,964,063386操作浏览器MIT-0通过
video-frames

视频帧 · OpenClaw

2,621,304112需要联网MIT-0通过
gemini

Gemini 助手 · OpenClaw

2,547,39648需要联网MIT-0有提醒
nation-resilience-hook-video-gen

国家韧性挂钩视频生成 · 本页

3,2461接触敏感数据MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
nation-resilience-hook-video-gen
version
1.0.0
description
Create vertical nation-resilience hooks with timed English on-screen text (WeryAI): map flashes, resource–geography–defense beats, risk twist. Use for geopolitics Shorts, atlas montage, or country-comparison tension. Use when the user asks for map-driven hooks or collapse-vs-risk angles. SEO: geopolitics hook video; nation resilience video.
tags
[geopolitics, maps, documentary, hooks, subtitles, short-video, video-gen]
metadata
{ "openclaw": { "emoji": "🗺️", "primaryEnv": "WERYAI_API_KEY", "paid": true, "network_required": true, "requires": { "env": ["WERYAI_API_KEY"], "bins": ["node"], "node": ">=18" } } }
user-invocable
true

Nation resilience hook (map + flashes + risk twist)

Template (timings assume duration 10; rescale proportionally for 5 or 15): 0–2s contrarian hook (“almost can’t collapse”); 2–8s three ultra-short on-screen beats (e.g. resources / geography / defense) synced to fast B-roll; 8–10s twist line that reframes the biggest risk (open-ended ellipsis allowed). English subtitles are burned in with explicit second windows—derived from the user’s country or theme unless they supply a final script. Default duration is 10 when unspecified.

Dependencies: WERYAI_API_KEY + Node.js 18+. scripts/video_gen.js + WERYAI_VIDEO_API.md under resources/ (assembly before run). No other Cursor skills required.

Prerequisites

  • WERYAI_API_KEY must be set before running video_gen.js.
  • Node.js 18+; prefer public https image URLs. If the assembled scripts/video_gen.js accepts local paths, review/verify the script and explicitly consent before local read-and-upload to WeryAI.
  • video_gen.js requires a non-empty model—pick a tier from Recommended models or an explicit model_key from the frozen tables.
  • Each wait run consumes credits.

Security, secrets, and API hosts

  • WERYAI_API_KEY: Secret; listed as requires.env / primaryEnv—never commit the value inside the package.
  • API hosts (fixed in video_gen.js): Video https://api.weryai.com; models registry https://api-growth-agent.weryai.com. No URL overrides documented—only the key is read from the environment.
  • Local image handling disclosure: Prefer public https image URLs. If the assembled scripts/video_gen.js supports local file paths, it may read a local image and upload it to WeryAI to obtain a public URL; require review / verification and explicit consent before using that path.
  • Higher assurance: Use a short-lived or isolated environment; review video_gen.js before production use. Verify whether the runtime can read local image files and upload them to WeryAI, and obtain explicit consent before using that path.

Prompt expansion (mandatory)

video_gen.js does not expand prompts. Build a full English production prompt that locks this template’s timeline.

When: Short user input (country name, region, or metaphorical “nation” topic). Exception: Finished long prompt within prompt_length_limit + user asks not to rewrite—still show full text in the confirmation table.

Always add:

  • Duration: Default 10 when unspecified; 5 or 15 when the user asks and the model allows.
  • Timeline scaling: If duration is 5 or 15, proportionally rescale every subtitle window; keep the same beat order (hook → three staccato labels → twist).
  • Locked caption windows (must follow this rhythm at duration 10):

- 0.0–2.0s — Hook: e.g. *THIS NATION ALMOST CAN’T COLLAPSE* (adapt to user topic). - 2.0–4.0s, 4.0–6.0s, 6.0–8.0s — Three single-focus lines (user-themed): e.g. *RESOURCES* / *GEOGRAPHY* / *DEFENSE* (swap labels to match brief). - 8.0–10.0s — Twist: e.g. *BUT THE REAL RISK IS…* (user fills the implied threat: debt, trust, demographics, etc.—keep ≤6 words on screen if possible).

  • Visuals: Animated map, hard cuts, data glitch overlays, military silhouettes / strategic geography without depicting real identifiable leaders as targets of hate; sub-bass tension if generate_audio is true.
  • Typography: Bold sans, white + black outline, lower third, short fades, no overlapping windows; English only on screen unless user requests otherwise.
  • Motion: Continuous—no static map shots longer than ~1s.
  • Negatives (Kling only): illegible text, watermark, garbled captions.

Confirmation: Pre-submit table includes the full expanded prompt.

Niche checklist

  • Hook must feel too bold to skip—not a textbook opener.
  • Middle three lines are labels, not paragraphs—match one visual beat each.
  • Twist is provocative but not a call to violence or hate.

### Example prompts are richness targets only.

Workflow

  1. Confirm text-to-video and/or image-to-video (optional multi-image only with SEEDANCE_2_0, ≤3 URLs).
  2. Collect brief (which country / abstract “nation” idea), optional image/images, tier or model_key.
  3. Expand prompt per above—author English lines from the brief unless user supplied a script.
  4. Validate JSON fields against frozen tables.
  5. Show confirmation table + full expanded prompt; wait for confirm.
  6. node scripts/video_gen.js wait --json '…'.
  7. Return [Video](url) links or errors—never wrap playable URLs in code fences.

CLI reference

~~~sh node scripts/video_gen.js wait --json '{"model":"KLING_V3_0_PRO","prompt":"…","duration":10,"aspect_ratio":"9:16","generate_audio":true,"negative_prompt":"illegible text, garbled captions, watermark"}' node scripts/video_gen.js wait --json '{"model":"SEEDANCE_2_0","prompt":"…","duration":10,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}' ~~~

Full reference: WERYAI_VIDEO_API.md.

Definition of done

Playable Video or clear failure. Submitted prompt includes explicit second-by-second caption windows for the full duration, matching this template’s beat order (scaled when duration is not 10), unless the user opted out with a finished prompt.

Boundaries (out of scope)

  • No guarantee of geopolitical accuracy—entertainment / opinion tone only; avoid incitement.
  • No separate SRT workflow; captions live inside the model prompt.
  • Do not use local image paths unless you have reviewed scripts/video_gen.js and explicitly consent to local read-and-upload to WeryAI; otherwise prefer public https URLs. Do not put secret key values in files.
  • Do not link shared ../references/ capability docs; use resources/WERYAI_VIDEO_API.md.
  • Do not send unsupported API fields; no negative_prompt on Seedance 2.0.
  • Multi-image only SEEDANCE_2_0, max 3 URLs.

Example prompts

  • Japan island supply lines—hook collapse impossible, three beats, twist: aging population
  • Abstract “digital nation” metaphor, same beat map, twist: attention fragmentation
  • Image: stylized map poster URL → animate with same subtitle schedule
  • Island nation energy imports—three beats then twist on grid vulnerability

Model and API constraints (frozen for this skill)

From node scripts/video_gen.js models --mode text_to_video and --mode image_to_video at authoring; re-run after upgrades.

Text-to-video

model_keydurationsaspect_ratiosresolutionsaudionegative_promptprompt limit
KLING_V3_0_PRO5, 10, 159:16, 1:1, 16:9*(omit resolution)*yesyes2000
KLING_V3_0_STA5, 10, 159:16, 1:1, 16:9*(omit resolution)*yesyes2000
SEEDANCE_2_05, 10, 159:16, 1:1, 16:9480p, 720pyesno2000

Image-to-video

model_keydurationsaspect_ratiosresolutionsaudionegative_promptimage slots
KLING_V3_0_PRO5, 10, 159:16, 16:9, 1:1*(omit)*yesyessingle image
KLING_V3_0_STA5, 10, 159:16, 16:9, 1:1*(omit)*yesyessingle image
SEEDANCE_2_05, 10, 159:16, 1:1, 16:9480p, 720pyesnoup to 3 images

Recommended models

Tiermodel_keyDefault duration
⭐ BestKLING_V3_0_PRO10
👍 GoodKLING_V3_0_STA10
⚡ FastSEEDANCE_2_010 (resolution: 720p)

Tier: unspecified → Best; “draft/quick” → Fast; “balanced” → Good.

Default parameters

FieldValue
aspect_ratio9:16
duration10
generate_audiotrue
resolution720p for Seedance only
negative_promptKling: illegible text, garbled captions, watermark, crowded subtitles

Text-to-video (primary)

User gives country / theme + optional tone. Expand with locked windows → confirm table → wait.

Image-to-video (optional)

Same subtitle schedule; motion activates map or still.

Tips

  • If the user names a real country, keep visuals symbolic (maps, icons)—avoid hostile targeting of groups.
  • Twist line works best as ellipsis to drive comments.
Packaged as nation-resilience-hook-video-gen.

平台分布

OpenClaw

77.03%
按下载量换算876

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

可疑

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills