Token导航 LogoToken导航

Agent Skill · 研究检索

video-caption-creation(视频字幕创作)

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。

video-caption-creation 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为权限未标注;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 57,638。

总安装 428周安装 18GitHub Stars 4下载 150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
unknown

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:video-caption-creation(视频字幕创作)
来源仓库:https://github.com/cdeistopened/opened-vault
仓库路径:skills/video-caption-creation
安装命令:
npx skills add https://github.com/cdeistopened/opened-vault --skill video-caption-creation
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/cdeistopened/opened-vault --skill video-caption-creation

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

为短视频创建吸引人的屏幕文字和字幕,提升用户停留率和互动率。适用于社交媒体内容制作、视频营销和教育视频优化场景。使用时需遵循互补性原则,使屏幕文字与音频形成信息增量。通过 GitHub 安装,支持主流宿主环境,建议核对平台发布规范。

video-caption-creation 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/video-caption-creation

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 Codex、Claude、Cursor、Gemini CLI;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 npx skills add https://github.com/cdeistopened/opened-vault --skill video-captio…;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

    权限没有明确标注,第一次使用时只给一个无关紧要的任务,观察它到底读了哪些文件和网络。

常见问题

6 条

video-caption-creation 怎么安装?

在终端执行 npx skills add https://github.com/cdeistopened/opened-vault --skill video-caption-creation。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

video-caption-creation 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。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。

video-caption-creation 需要什么权限?

权限级别没有明确标注。第一次使用时建议只给无关紧要的任务,观察它实际读写了哪些内容。

video-caption-creation 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

video-caption-creation 用的人多吗?

公开数据是累计安装 428 次,近一周安装 18 次,下载 150 次,GitHub 4 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。

video-caption-creation 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

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 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 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
video-caption-creation

视频字幕创作 · 本页

4284权限未标注未明确有提醒

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

Video Caption & On-Screen Hook Writer (v2)

On-screen text is the #1 visual element in short-form video. It does the PRIMARY work of stopping a scroll. A viewer sees the text and decides in <1 second whether to stop. This skill creates the text that makes them stop.

Previous version: SKILL_v1_archive.md (basic Triple Word Score, retired Feb 2026)


The Complementarity Principle

The central insight: On-screen text should NOT label or repeat the audio. It should ADD context that makes the audio land harder. The gap between what you read and what you hear creates curiosity.

This works exactly like title + thumbnail on YouTube: together they create a fuller picture than either alone. Andrew Muto: *"You read the title, and then the thumbnail is offering you a little extra."*

Bad (labeling): On-screen says "Kids know." → Audio is about teacher dissatisfaction. Vague label, no gap.

Good (complementary): On-screen says "A kindergartner can tell" → Audio reveals that 55% of teachers want to quit, and every morning a five-year-old walks into a classroom and senses it. The childlike framing + the adult data = productive tension.

The 6 Complementarity Patterns

PatternOn-Screen Text DoesAudio DoesWhy It Works
Question → AnswerAsks a questionDelivers the answerOpen loop the viewer must close
Problem → SolutionNames a pain pointProvides the fixViewer self-identifies, stays for relief
Framework → ContentNames a strategy/conceptExplains what it means"What IS that?" curiosity
Credential → InsightEstablishes authorityDelivers the revelationTrust signal makes content land harder
Teaser → PayoffHints at what's comingCompletes the thoughtNarrative tension drives completion
Reframe → EvidenceChallenges an assumptionProvides the proofCognitive dissonance demands resolution

How Complementarity Works in Practice

Audio says: *"If we think that our public system's path to victory will be to trap families, you've lost the argument."*

The text should NOT repeat "you've lost the argument" or "trap families" as a label. Instead, it adds a new layer:

  • Question → Answer: "Schools trap families?" - opens a loop the audio closes
  • Reframe → Evidence: "You're defunding yourself" - adds a provocative angle the audio then explains
  • Credential → Insight: "CEO of 80 microschools explains why..." - trust signal that makes the bold claim land harder

Audio says: *"In a big school, kids just feel lost. So they retreat to the screen. Then we ban the screen, and they're like, I'm still lost."*

Good complementarity adds a new frame:

  • "Why phone bans don't work" - reframes around the cultural conversation
  • "80 schools. Zero phone problems." - credential that implies they solved it
  • "In a big school, kids just feel lost. So they retreat to the screen. Then we ban the screen, and they're like - I'm still lost." - sometimes the FULL quote IS the hook (see Length Variety below)

The First-3-Words Test

The first 3 words someone reads do 80% of the work. Before finalizing any hook, check:

What are the first 3 words?

  • "A kindergartner can" → Curiosity (can what?)
  • "Schools trap families" → Shock (they do?)
  • "55% of teachers" → Specificity (tells me this is data)
  • "Why phone bans" → Promise (I'm about to learn something)

Weak first 3 words:

  • "Here's what happens" → Generic, could be anything
  • "Check this out" → Zero information
  • "In this clip" → Meta, breaks immersion
  • "You need to" → Commanding without earning attention

Front-load the punch. Move the most surprising, specific, or provocative word as close to position 1 as possible.


Length Variety (Critical)

Every set of 3-4 hook options MUST include different lengths. This is non-negotiable. If all your hooks are 3-5 word punchy phrases, you're in a rut.

LengthWord CountWhen It WorksExample
Punchy2-4 wordsStats, named frameworks, provocative labels"Homework is a scam"
Statement5-8 wordsReframes, challenges, credential leads"His parents almost cut off his entire career"
Narrative9-15 wordsStory setups, scenario hooks, before/after"I tried every AI tool so you don't have to"
Full quote15+ wordsWhen the quote itself IS the hook (rare, powerful)"Kids learn to walk at different ages... so why do we make every kid learn algebra at the same age?"

The trap: AI defaults to short and punchy because it pattern-matches "hook = headline." Fight this. Some of the best-performing on-screen text is conversational and long.


Proven Hook Library

These are original examples from research into viral short-form content. They're organized by format/archetype. Preserve the originals - they have more texture than anything we'd rewrite. Use framework fitting at runtime to adapt them to specific content.

Results and Transformation

FrameworkProven ExampleLever
"How I [result]""How I hit 100k views in 7 days"Social proof + utility
"[Before] vs [After]""My $10M company vs my first $100 sale"Rags-to-riches narrative
"The one [niche] tip that changed everything""The one lighting tip that fixed my videos"High-ROI promise
"I did [action] so you don't have to""I tried every AI tool so you don't have to"Utility + time-saving
"How to [goal] with zero [pain point]""How to build an app with zero coding"Barrier removal

Curiosity Gap and Contrarian

FrameworkProven ExampleLever
"Stop doing [action] if you want [result]""Stop doing bench press if you want chest growth"Pattern interrupt + urgency
"You've been [action] wrong your whole life""You've been folding your shirts all wrong"Challenges assumptions
"What they don't want you to know about [topic]""What banks don't want you to know about debt"Forbidden knowledge
"Everyone is wrong about [topic]""Everyone is wrong about passive income"Cognitive dissonance
"This mistake cost me [amount]""This one mistake cost me $2,300"Financial stakes

Authority and "Secret"

FrameworkProven ExampleLever
"No one talks about this in [industry]""No one talks about this in the creator economy"Exclusivity
"I probably shouldn't share this, but...""I probably shouldn't share this airline loophole"Insider access
"The biggest secret about [topic]""The biggest secret about starting a business"Curiosity gap
"3 [tools/things] that feel illegal to know""3 AI tools that feel illegal to know"Rule-breaking novelty
"I wish I knew this [time] ago""I wish I knew this before I turned 30"Wisdom through regret

Question and Relatability

FrameworkProven ExampleLever
"If you're a [identity], watch this""If you're a SaaS founder, watch this"Self-identification
"Do you struggle with [problem]?""Do you struggle with falling asleep?"Pain point
"Can you guess what happens if you [action]?""Can you guess what happens if you quit sugar?"Suspense
"Are you making this mistake in [action]?""Are you making this mistake in your morning routine?"Fear of error
"If you've ever...""If you've ever unbuttoned your jeans at dinner..."Hyper-specificity

Education/Parenting Originals (from Andrew Muto research)

These are proven hooks from education creators - closer to our audience:

Short punchy:

  • "Homework is a scam"
  • "Your kid's C+ is fine"
  • "Your ADHD kid isn't broken"

Statement length:

  • "Screen time isn't the problem. Boredom is."
  • "Neurodivergent kids aren't the problem. The system is."
  • "5 Signs Your Kid Doesn't Actually Hate Math"

Narrative length:

  • "Kids don't hate math. They hate how it's taught."
  • "Edison was kicked out of school for being 'too curious'"
  • "They said homeschooled kids won't socialize. Have you met public schoolers?"
  • "His kids skipped school for 100 days. Here's what happened."
  • "Finland banned homework below age 10. Now they're #1 in education."

Full quote / conversational:

  • "My kids socialize with humans of all ages, not just 24 kids born the same year"
  • "Kids learn to walk at different ages... so why do we make every kid learn algebra at the same age?"
  • "Things I don't explain to strangers anymore: Why my kids aren't in school"

Podcast Clip Archetypes (from research report)

ArchetypeRoleTriggerExample
The TeacherProvide fast, actionable valueUtility + expertise"3 ways to make your next video go viral"
The InvestigatorReveal a hidden truthExclusivity + FOMO"No one's talking about this - but it changes everything"
The ContrarianChallenge popular beliefCognitive dissonance"Hashtags don't actually help your reach. Here's why"
The FortunetellerHint at transformationAspiration + reward"Here's what happened when I quit caffeine for 30 days"
The ExperimenterShare trial resultsCuriosity + relatability"I posted 3 times a day for a week. Here's what happened"

Framework Fitting at Runtime

The Proven Hook Library above contains TEMPLATES. When generating hooks for a specific clip, use framework fitting:

  1. Read the clip transcript - find the hookable moment
  2. Scan the library - which framework fits this moment?
  3. Adapt the framework to the specific content, preserving the format's proven structure
  4. Vary the length - each set of 3-4 options should span at least 2 different length categories

Example: If the clip is about a microschool founder who discovered mixed-age classrooms work:

  • Punchy: "The Trojan horse classroom" (Named Framework)
  • Statement: "Teachers hate this. Then something flips." (Curiosity Gap)
  • Narrative: "She put 3 grades in one room. Teachers hated it. Then something flipped." (Fortuneteller)
  • Full quote: "The mixed-age classroom can be a Trojan horse to introduce a totally different way of teaching." (when the quote itself is gold)

Podcast Clip On-Screen Hook Workflow

This is the step-by-step process for generating hooks from podcast transcript clips. Used by the podcast-production skill at Step 4.

Step 1: Identify the Hookable Moment

Scan the clip transcript for one of these triggers (SURP framework):

  • Surprising fact or statistic ("55% of teachers want to leave")
  • Unexpected quote or bold statement ("you've lost the argument")
  • Relatable problem ("kids feel lost, so they retreat to the screen")
  • Provocative opinion ("our path to victory will be to trap families")

The hookable moment is usually NOT the first sentence of the clip. Find the single line that would make someone stop scrolling if they saw it as a headline.

Step 2: Determine the Complementarity Pattern

Ask: What would ADD the most to what the viewer hears?

If the audio...Best patternOn-screen text should...
Makes a bold claimReframe → EvidenceChallenge the assumption the claim disproves
Tells a storyTeaser → PayoffHint at the ending without revealing it
Cites data/statsQuestion → AnswerAsk the question the stat answers
Introduces a frameworkFramework → ContentName the framework
Gives adviceProblem → SolutionName the problem the advice solves
Shares credentialsCredential → InsightLead with the credential

Step 3: Generate 3-4 Hook Options

For each clip, write 3-4 options with LENGTH VARIETY. Each set should span at least 2 different length categories (punchy, statement, narrative, full quote).

Scan the Proven Hook Library for a matching framework. Adapt the framework to this specific content while preserving the format's proven structure.

Step 4: Apply Quality Gates

For each option, check:

  • First-3-Words Test: First 3 words carry the punch?
  • McDonald's Test: Someone at McDonald's understands instantly?
  • Scroll Test: Would I personally stop scrolling?
  • Gap Test: Text + audio create a gap, not a repeat?
  • Grandmother Test: My grandmother gets what this is about?

Step 5: Mark Recommended Pick

Select one recommended option and explain WHY in one sentence. The rationale should reference the complementarity - how the text and audio work together.


Identifying Hookable Moments in Transcripts

When scanning a full transcript (before clips are selected), look for:

Tier 1: Almost always hookable

  • Specific statistics ("55% of teachers want to leave")
  • Named concepts or frameworks the speaker coined
  • Moments that contradict popular belief
  • Emotional peaks (speaker's voice changes, pace quickens)
  • Universal pain points ("every parent knows...")

Tier 2: Often hookable

  • Personal confessions or vulnerable moments
  • "I should probably not say this, but..."
  • Origin stories (how they started, what went wrong)
  • Direct statements that take a side

Tier 3: Rarely hookable (avoid)

  • Agreement moments ("yeah, totally, I think so too")
  • Background context / scene-setting
  • Nuanced, heavily-caveated statements
  • Inside baseball (jargon-heavy industry talk)

The whole transcript matters. The strongest moment might be at minute 48. Don't mine just the first half.


The Triple Word Score System

Four signals must align so algorithms AND humans immediately know "this is for me":

1. Audio Transcript (MOST IMPORTANT)

  • What the speaker says out loud - algorithms auto-transcribe this
  • Topic words must appear in first 10 seconds
  • Core terminology repeated naturally throughout

2. On-Screen Text Hook

  • Visual overlay using complementarity principle (above)
  • NOT a repetition of the audio - an addition to it
  • Lead with topic words in the hook

3. Caption Copy

  • Post description with topic-relevant keywords
  • Opens with a topic-relevant phrase
  • Provides context the algorithm needs

4. Strategic Hashtags

  • 10-12 total (optimal range)
  • Broad → Mid → Specific → Niche → Audience → Platform
  • Example: #Education #Parenting #Homeschool #Microschools #SchoolChoice #HomeschoolMom #Shorts

When all four align, the algorithm recognizes the topic immediately and serves it to the right people.


Caption Writing

Short-Form Platforms (Same Caption Everywhere)

Applies to: YouTube Shorts, Instagram Reels, TikTok, Facebook Reels

One caption per clip. Don't write platform-specific versions (waste of time, same audience).

Format:

[Verbatim quote or key insight from clip - 1-2 sentences]
[Context: who the speaker is and why it matters - 1 sentence]

#Hashtags (10-12)

Optional X Variant: Shorter, more conversational. Include @handles. Drop the context sentence.

Caption Quality Check

  • Opens with the strongest line from the clip
  • Includes guest name and title
  • Hashtags span broad to niche
  • Under 150 characters for the hook portion
  • No emojis in body (rare exceptions for social captions)

Output Format

When this skill is invoked (standalone or from podcast-production), produce this per clip:

### [Clip Name]

**Timestamp range:** [MM:SS-MM:SS]

**On-screen hook options:**
1. "[Hook text]" *
2. "[Hook text]"
3. "[Hook text]"
4. "[Hook text]"

(* = recommended pick. List 3-4 options. Star goes on the strongest.)

**Caption (FB, TikTok, IG, LinkedIn):**
[Caption text]

**X variant:**
[Shorter caption with @handles]

Keep it clean. No category labels, no rationale paragraphs. The hooks should speak for themselves. Use the complementarity principle and quality gates internally when generating, but the output is just the options with a star.


Sub-Agent Prompt Template

When podcast-production invokes this skill at Step 4, use this prompt:

You are generating on-screen text hooks for podcast clips.

Episode: [Guest Name]
Working directory: [path to prep/]

Read the following files:
- SOURCE.md (full transcript for context)
- EDITOR_HANDOFF.md (clips already selected in Sections 3 & 4)

For EACH clip in Sections 3 and 4, generate 3-4 on-screen hook options.
Mark the recommended pick with an asterisk (*).

Output format per clip:
1. "Hook text" *
2. "Hook text"
3. "Hook text"
4. "Hook text"

No category labels. No rationale paragraphs. Just the options with a star.

Internal rules (apply these but don't show them in output):
- On-screen text ADDS to audio, never repeats it (Complementarity Principle)
- Apply the First-3-Words Test to every option
- Apply McDonald's Test (instantly understandable)
- VARY THE LENGTH across options: at least one short punchy (2-5 words), one statement (6-8 words), and one narrative or full-quote (9+ words). Do NOT default to all short punchy hooks.
- Scan the Proven Hook Library in the skill for matching frameworks
- Framework fit the proven templates to the specific content

Write the hooks directly into the EDITOR_HANDOFF.md clip sections.

Exemplar Channels (Study These)

Podcast Clip Masters

  • Diary of a CEO (@doac.clips) - Animated text, credential leads, emotional transitions. Opens with guest in chair + text hook. Text builds anticipation without giving away payoff.
  • My First Million (clips channel) - Entrepreneurship hooks, "how to" + numbers format
  • Huberman Lab (Essentials) - Dense science distilled to protocols. Direct promise hooks.
  • Lex Fridman Clips - Topic-based text overlays for philosophical conversations

Education/Parenting Creators

  • Dr. Becky Kennedy (@drbeckyatgoodinside, 3M) - Named strategy hooks ("The REPAIR Strategy"), problem → solution format
  • Big Little Feelings (@biglittlefeelings, 3.6M) - "When your toddler refuses to..." pain point hooks
  • Busy Toddler (@busytoddler, 2.4M) - Action-oriented "This LEGO hack will..."
  • @thatcalteacherlife (508K) - Working parents + homeschool
  • @deal_family (352K) - Second-gen homeschool mom
  • @littlefenders (132K) - "Redefining learning + parenting / Educating kids with AI / Unschooling / ADHD Mom"

Key Patterns from Top Performers

  1. Text = Question, Audio = Answer (Dr. Becky)
  2. Text = Named Framework, Audio = Explanation (Dr. Becky)
  3. Text = Credential, Audio = Insight (DOAC)
  4. Text = Problem, Audio = Solution (Big Little Feelings)
  5. Text = Teaser, Audio = Payoff (DOAC)

Common Mistakes

  • All hooks the same length: The #1 mistake. If every option is 3-5 word punchy headlines, you haven't explored the full range. Mix punchy with narrative with full-quote.
  • Labeling instead of complementing: "Kids know." is a label. "A kindergartner can tell" is a hook.
  • Giving away the payoff in text: If the text reveals the full insight, there's no reason to watch.
  • Generic first 3 words: "Here's what happens" could be anything. "55% of teachers" is specific.
  • Only one hook per clip: Always generate 3-4. The first idea is rarely the best.
  • Rewriting proven templates instead of adapting them: The original examples have texture. Framework fit them to your content at runtime - don't pre-sanitize the library.
  • Hooks that need the clip to make sense: The hook must work for a silent, scrolling viewer who hasn't heard a word yet.
  • Fancy vocabulary: "Pedagogical paradigm shift" fails the McDonald's test. "Schools are broken" passes.

Related Skills

  • podcast-production - Invokes this skill at Step 4 (on-screen hook generation)
  • short-form-video - Full production workflow (this skill handles text only)
  • text-content - For text-only social posts (LinkedIn, X, not video)
  • youtube-title-creator - Title + thumbnail (same complementarity principle, different application)
  • cold-open-creator - Cold opens use [SWOOSH] transitions, not hooks

Research References

  • Short-Form Video Text Hook Strategies.md - Comprehensive report on hook psychology, typography, retention
  • Andrew Muto notes: Studio/_archive/Archive/Andrew Muto/ - Complementarity, McDonald's test, 15-min rule, hook categories
  • Podcast-production skill improvement notes: Studio/Podcast Studio/Amar-Kumar/prep/SKILL_IMPROVEMENT_NOTES.md

*Rewritten Feb 6, 2026 after Amar Kumar podcast session. Incorporates complementarity principle, first-3-words test, 6 hook categories, SURP framework, and worked examples from real clips.*

平台分布

Codex

34.58%
按下载量换算52

Claude

30.31%
按下载量换算45

Cursor

18.39%
按下载量换算28

Gemini CLI

9.25%
按下载量换算14

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

权限未标注

当前来源未能明确判断权限范围,默认进入异常复核队列。

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