Token导航 LogoToken导航

Agent Skill · 效率

hidden-truth-reveal-video-gen(隐藏的真相揭露视频生成)

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。

hidden-truth-reveal-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 11,042。

总安装 4,820周安装 195GitHub Stars 公开资料未说明下载 1,513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:hidden-truth-reveal-video-gen(隐藏的真相揭露视频生成)
来源仓库:https://github.com/zoucdr/hidden-truth-reveal-video-gen
安装命令:
openclaw skills install hidden-truth-reveal-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 hidden-truth-reveal-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。

生成对比式揭露视频,支持供应链前后对比与定时字幕合成输出 MP4。适用于产品溯源、质量对比或社会议题可视化表达类内容创作需求。输入文本提示与素材路径后可自动生成脚本化剪辑片段。需准备符合版权要求的图片/视频素材,避免使用受保护人物肖像。输出分辨率与时长受限于平台处理能力,商业用途请提前审核内容合规性。

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 hidden-truth-reveal-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

hidden-truth-reveal-video-gen 怎么安装?

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

hidden-truth-reveal-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。

hidden-truth-reveal-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。

hidden-truth-reveal-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。

hidden-truth-reveal-video-gen 用的人多吗?

公开数据是累计安装 4,820 次,近一周安装 195 次,下载 1,513 次。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。

hidden-truth-reveal-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
hidden-truth-reveal-video-gen

隐藏的真相揭露视频生成 · 本页

4,820—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
hidden-truth-reveal-video-gen
version
1.0.0
description
Create vertical reveal shorts: polished product vs harsh origin, one-line verdict, timed English captions (WeryAI). Use for supply-chain shock, contrast edits, or ‘99% don’t know’ hooks. Use when the user asks where everyday goods come from. SEO: hidden truth video; contrast reveal video.
tags
[reveal, contrast, supply-chain, consumer, 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

Hidden truth reveal (polished → brutal → one line)

Template (seconds below assume duration 10; rescale for 5 or 15): 0–3s hook: *what you use daily comes from here* (user’s X); 3–8s stark contrast montage (sleek product ↔ labor, factory, waste, or source environment—non-gore, suggestive not graphic); 8–10s one-line summary that lands the thesis. English subtitles with explicit second windows. Default duration is 10 when unspecified.

Dependencies: WERYAI_API_KEY + Node.js 18+. {baseDir}/scripts/video_gen.js + WERYAI_VIDEO_API.md under {baseDir}/resources/. No other Cursor skills required.

Prerequisites

  • WERYAI_API_KEY must be set; Node 18+; https images only.
  • Non-empty model in JSON; pick from Recommended models or frozen tables.
  • Each wait consumes credits.

Security, secrets, and API hosts

  • WERYAI_API_KEY: Secret; requires.env / primaryEnv—never commit values.
  • API hosts: video_gen.js uses https://api.weryai.com (tasks) and https://api-growth-agent.weryai.com (models list).
  • Run in an isolated environment when possible.

Prompt expansion (mandatory)

  • Duration: Default 10; 5 or 15 when the user asks and the model allows.
  • Timeline scaling: Rescale 0–3 / 3–5 / 5–7 / 7–10 proportionally when duration ≠ 10; keep the four-beat order.

Locked caption rhythm (example for duration 10):

  • 0.0–3.0s — Hook naming the daily X (user-supplied): e.g. *YOUR DAILY X COMES FROM HERE* (keep ≤6 words per line).
  • 3.0–5.0s — Polished beat label: e.g. *SHELF PERFECT*.
  • 5.0–7.0s — Harsh beat label: e.g. *HIDDEN COST*.
  • 7.0–10.0s — One-line verdict (user-themed): e.g. *THAT’S THE TRUTH* (customize to topic).

Visuals: Hard cuts; high contrast lighting; hands / machines / environments—avoid graphic gore or identifiable real people in exploitative frames. Motion every beat.

Typography: Bold sans, white + black outline, lower third, fades; English only on screen unless user opts out.

Audio: Tension bed / impact whoosh if generate_audio true—no named tracks.

Negatives (Kling): illegible captions, watermark, muddy text.

Exception: User supplies finished long prompt + no rewrite—still show full text in confirmation.

Confirmation: Full expanded prompt in the table.

Niche checklist

  • Contrast must read in silent skim—image does half the work.
  • Middle beats are two emotional temperatures, not a lecture.

Examples below are targets only.

Workflow

  1. Text and/or image-to-video (multi-image only SEEDANCE_2_0, ≤3 URLs).
  2. Collect product or topic X, optional reference image, tier.
  3. Expand with locked windows + visuals; translate user Chinese brief to English on-screen lines unless they request another language.
  4. Validate fields vs frozen tables.
  5. Confirmation table + full prompt → user confirm.
  6. node {baseDir}/scripts/video_gen.js wait --json '…'.
  7. Return [Video](url); no code fences around links.

CLI reference

~~~sh node {baseDir}/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, watermark, garbled captions"}' node {baseDir}/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

Video or clear error. prompt contains timed English subtitle block matching the four-beat order, with second ranges scaled to duration (or user’s approved variant).

Boundaries (out of scope)

  • Not a journalism fact-check; opinion / hook tone—user responsible for claims.
  • No gore; no harassment of real individuals.
  • Captions only via prompt; no NLE export spec.
  • Use resources/WERYAI_VIDEO_API.md for CLI; no negative_prompt on Seedance.
  • Multi-image only SEEDANCE_2_0, max 3.

Example prompts

  • Coffee cup: shelf glamour vs harvest-labor montage, verdict line about price to growers
  • Smartphone: polished device vs mine/e-waste suggestion, one-line kicker
  • Image URL of sneakers → same four-window subtitle schedule
  • Fast fashion haul vs factory floor suggestion—verdict about true cost

Model and API constraints (frozen for this skill)

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)

Default parameters

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

Text-to-video (primary)

Collect X → expand four-window captions → confirm → wait.

Image-to-video (optional)

Product still → motion + same schedule.

Tips

  • If claims are sensitive, soften to “what they don’t show” rhetoric.
  • Verdict line should fit one breath.
Packaged as hidden-truth-reveal-video-gen.

平台分布

OpenClaw

84.49%
按下载量换算1,278

安全审计

VirusTotal

通过

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