think-x-actually-y-video-gen（认为 x 实际上是 y 视频生成） Skills下载安装命令和教程

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：think-x-actually-y-video-gen（认为 x 实际上是 y 视频生成）
来源仓库：https://github.com/zoucdr/think-x-actually-y-video-gen
安装命令：
openclaw skills install think-x-actually-y-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 think-x-actually-y-video-gen

简介

创建垂直三屏揭穿类短视频，含定时英文字幕与热门模板支持。

适用于心态阶梯、认知反差等内容创意视频制作。
基于 WeryAI 技术生成三个片段，强化观点冲击力与传播力。
安装命令：openclaw skills install think-x-actually-y-video-gen。
涉及外部素材使用时需确认版权合规，避免肖像权争议。

SKILL.md

name: think-x-actually-y-video-gen
version: 1.0.1
description: Create vertical three-beat debunks: you think X, actually Y, but Z—timed English captions on three segments (WeryAI). Use for mindset ladders, hot-take templates, or layered arguments. Use when the user wants think/actually/but structure. SEO: think X actually Y video; debunk template video.
tags: [debunk, mindset, template, 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

You think X, actually Y (three-beat ladder)

Template (segment lengths assume duration 10 → 30% / 30% / 40%; rescale for 5 or 15): Beat 1 *YOU THINK {X}*; Beat 2 *ACTUALLY: IT’S {Y}*; Beat 3 *BUT WHAT REALLY DECIDES IS {Z}* — X / Y / Z come from the user’s brief (you compress each to ≤6 words for on-screen legibility). Hard cuts and kinetic energy between beats. English subtitles with exact windows. Default duration is 10 when unspecified.

Dependencies: WERYAI_API_KEY + Node.js 18+. scripts/video_gen.js + WERYAI_VIDEO_API.md. No other Cursor skills required.

Prerequisites

WERYAI_API_KEY must be set; Node 18+. Prefer public https image URLs; if the assembled scripts/video_gen.js supports local file paths, review/verify the script and explicitly consent before local read-and-upload to WeryAI.
Non-empty model in every submit-* / wait JSON.
Each successful task submission may consume credits; re-submit creates new paid tasks.

Security, secrets, and API hosts

WERYAI_API_KEY: Secret; never commit.
API hosts fixed in video_gen.js.
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: Prefer a short-lived or isolated environment; review scripts/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.

Pre-submit gate (mandatory)

⚠️ No paid submit without explicit user confirmation. Do not call submit-text, submit-image, submit-multi-image, or wait until the user has explicitly approved the parameter table (including full expanded prompt with X / Y / Z filled and timed caption windows). Never infer consent from silence or vague “continue.” Explicit means clear intent such as confirm / go / approved / yes, generate (or equivalent).

Parameter confirmation table (before any submit): model, duration, aspect_ratio, resolution (Seedance only), generate_audio, negative_prompt (Kling only), image / images (if used), and the entire expanded prompt (not a summary).

Prompt expansion (mandatory)

Duration: Default 10; 5 or 15 when allowed and requested.
Timeline scaling: Keep 30% / 30% / 40% of total runtime for the three beats (adjust seconds in the written prompt); or another explicit split the user approves.

User must supply (or approve) X, Y, Z concepts—if they only give a topic, propose three beats in the confirmation table before submit.

Visuals: Three distinct looks per beat (e.g. office runner → chess flip → neon brain schematic); arrows reversing, color grade shift each beat; motion throughout.

Typography: Bold sans, outline, lower third; ALL CAPS optional for punch—keep lines short.

Negatives (Kling): illegible text, watermark.

Confirmation: The full prompt including filled X/Y/Z inside the timed block appears only in the pre-submit table; see ## Pre-submit gate (mandatory) — wait for explicit approval before submit-* or wait.

Niche checklist

Avoid demeaning groups; critique ideas, not people.
If user’s Z is vague, default to SKILL / LUCK / COGNITION style abstractions they confirm.

Workflow

Choose path: text-to-video, single image, or multi-image (SEEDANCE_2_0 only, ≤3 URLs).
Extract or draft X, Y, Z; if the user only gave a topic, propose three beats and get their OK on concepts before expanding the full cinematic prompt.
Expand prompt (mandatory): Build the full production prompt (three distinct looks, motion, timed English captions per beat, negatives for Kling). Validate length against prompt_length_limit for the chosen model.
Pre-submit gate: Show the parameter confirmation table with the complete expanded prompt. Stop until the user explicitly confirms or requests edits.
Submit (async, default): After explicit confirmation, run submit-text, submit-image, or submit-multi-image (same JSON shape as wait; see WERYAI_VIDEO_API.md). Do not start a long blocking wait in the same turn unless the user already asked to block until the video is ready.
Immediate notify: On successful accept (e.g. taskId / batchId returned), immediately tell the user the id(s), short status (e.g. queued), and ask whether to continue with status polling or wait (block-until-done).
Continue (user-driven): Only after they agree, poll status --task-id <id> at reasonable intervals or run wait --json '…' with the same payload — per user choice.
Return results: [Video](url) when URLs exist; otherwise explain errorCode / errorMessage. Never wrap playable links in code fences.

CLI reference

After confirmation — async submit, then status (user opts in to polling):

~~~sh node scripts/video_gen.js submit-text --json '{"model":"KLING_V3_0_PRO","prompt":"…","duration":10,"aspect_ratio":"9:16","generate_audio":true,"negative_prompt":"illegible text, watermark, garbled captions"}' node scripts/video_gen.js submit-image --json '{"model":"SEEDANCE_2_0","prompt":"…","image":"https://…","duration":10,"aspect_ratio":"9:16","resolution":"720p","generate_audio":true}' node scripts/video_gen.js status --task-id <TASK_ID> ~~~

Block until done — only if the user explicitly chose wait:

~~~sh 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 (submit-multi-image, stdout fields, errors): WERYAI_VIDEO_API.md.

Definition of done

Video or a clear error. Pre-submit: full expanded prompt with three non-overlapping time ranges (scaled to duration) and concrete English for each beat was explicitly user-confirmed before submit. After submit: user was notified with task id(s) and chose status vs blocking wait. Playable URLs must be [label](url) only — not inside code blocks.

Boundaries (out of scope)

Not financial or medical advice—rhetorical template only.
resources/WERYAI_VIDEO_API.md for CLI; no negative_prompt on Seedance.
Multi-image only SEEDANCE_2_0, max 3.

Example prompts

X effort success, Y choices, Z cognition—office to chess to abstract mind
X cheap price, Y hidden fees, Z trust—ecommerce vibes
Product hero image URL → three-beat reversal with same windows
X free time, Y discipline, Z identity—gym / calendar / mirror visual metaphors

Model and API constraints (frozen for this skill)

Text-to-video

model_key	durations	aspect_ratios	resolutions	audio	negative_prompt	prompt limit
KLING_V3_0_PRO	5, 10, 15	9:16, 1:1, 16:9	(omit)	yes	yes	2000
KLING_V3_0_STA	5, 10, 15	9:16, 1:1, 16:9	(omit)	yes	yes	2000
SEEDANCE_2_0	5, 10, 15	9:16, 1:1, 16:9	480p, 720p	yes	no	2000

Image-to-video

model_key	durations	aspect_ratios	resolutions	audio	negative_prompt	image slots
KLING_V3_0_PRO	5, 10, 15	9:16, 16:9, 1:1	(omit)	yes	yes	single `image`
KLING_V3_0_STA	5, 10, 15	9:16, 16:9, 1:1	(omit)	yes	yes	single `image`
SEEDANCE_2_0	5, 10, 15	9:16, 1:1, 16:9	480p, 720p	yes	no	up to 3 `images`

Recommended models

Tier	model_key	Default duration
⭐ Best	KLING_V3_0_PRO	10
👍 Good	KLING_V3_0_STA	10
⚡ Fast	SEEDANCE_2_0	10 (`resolution`: 720p)

Default parameters

Field	Value
aspect_ratio	9:16
duration	10
generate_audio	true
resolution	720p (Seedance)
negative_prompt	Kling: `illegible text, garbled captions, watermark`

Text-to-video (primary)

Lock X/Y/Z with user → expand timed caption block → pre-submit table → submit-text → notify task id → user picks status or wait.

Image-to-video (optional)

Single hero → three visual skins across beats → submit-image (or submit-multi-image for Seedance, ≤3) → same notify → user-driven polling as above.

Tips

Translate Chinese user input to English captions unless they specify on-screen language.
Z lands best when it feels one level meta above Y.

Packaged as think-x-actually-y-video-gen.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

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

补充不同宿主或平台的使用分布数据

能力 5

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

OpenClaw

93.94%

按下载量换算1,263

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API；具体网络访问范围需要结合源码和 README 复核。

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 warning/failed 结果，不能写成本站确认安全。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

GitHub 仓库

github.com

/zoucdr/think-x-actually-y-video-gen

SKILL.md 来源

clawhub.ai

/zoucdr/think-x-actually-y-video-gen

继续浏览同类 Skills

更多效率 Skills（21,003）返回 Skills 目录

上一个 Skill

think-plan（思考计划）

think-plan 用于补充效率相关能力，适合在 OpenClaw 中需要让 Agent 承接效率相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。

下一个 Skill

thinkific（thinkific 效率）

thinkific 用于补充效率相关能力，适合在 OpenClaw 中需要让 Agent 承接效率相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。