Communitygithub.com

majiayu000/claude-skill-registry

Produce video scripts and clipping plans for TikTok, YouTube Shorts, Instagram Reels, and long-form YouTube. Generates hook-first scripts optimized for each platform's algorithm, plus a clipping plan to extract short-form from long-form content. Use when "video script", "TikTok script", "YouTube script", "Reels script", "Shorts script", "video content", "clipping plan", "video ideas", or any request to create video content for social platforms.

What is claude-skill-registry?

claude-skill-registry is a Claude Code agent skill that produce video scripts and clipping plans for TikTok, YouTube Shorts, Instagram Reels, and long-form YouTube. Generates hook-first scripts optimized for each platform's algorithm, plus a clipping plan to extract short-form from long-form content. Use when "video script", "TikTok script", "YouTube script", "Reels script", "Shorts script", "video content", "clipping plan", "video ideas", or any request to create video content for social platforms.

Works with✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/majiayu000/claude-skill-registry/tree/HEAD/skills/other/kai-video

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

/kai-video — shootable scripts and a defensible clip list

Kai root note: knowledge/, harness/, and scripts/ paths in this skill live in the Kai install, not the user's project. Resolve them against the first ancestor directory of this SKILL.md that contains a knowledge/ folder (the Kai plugin root, ~/.claude/kai, or the kai-cmo-harness repo). MARKETING.md, memory/, and any output files live in the current project. If a referenced scripts/ command is not available in this install, say so, skip it, and continue with the file-based guidance — never fabricate its output.

Objective

Scripts someone can shoot without asking a follow-up question, and — where long-form source exists — a clipping plan naming which moments become short-form, at which timestamps, and why. Hook-first and platform-specific: the first three seconds decide whether the rest of the work matters.

Done when

Work type social-post — floor E5/C2/O3 (harness/eco-floors.yaml), contract harness/skill-contracts/social-post.yaml.

  • E5 — the video is live and a non-actor read the public permalink back against the approved script and cut. A script file in workspace/ is E1; approval of the exact script is E3. This skill reaches the artifact; publishing is a separate, approved step.
  • C2 — four_us_score at 10/16 and banned_word_check clean on the script copy, plus the per-script bar below.
  • O3 — reach, engagement rate, profile clicks, and link clicks read from platform insights at 7 days, against a baseline recorded before publish.

Per-script bar: hook lands in the first 3 seconds (no intros, no "hey guys", no logo animation) · one idea per short-form video · zero banned words and zero AI slop · a CTA that closes naturally rather than being bolted on · visual direction included, not words alone · length appropriate to the platform.

Constraints

  • Read MARKETING.md from the project root before asking the user anything. If it does not exist, build it from the codebase — CLAUDE.md, README.md, PROJECT.md, package.json, landing pages, email/ad/analytics config — using the template from /kai-email-system, and confirm the draft.
  • Know these before scripting: topic, target platforms, format (talking head, screen recording, b-roll, animation), length band (15–60s short-form or 5–15min long-form), goal, and any existing content to adapt from.
  • Load the platform guide before writing for that platform — the algorithms differ and the pacing rules are not transferable.
  • Every clip row carries a source timestamp or file locator. If the source is a guest, customer, podcast, or third-party show, mark approval status before export and follow harness/references/transcript-video-research-rules.md.
  • Clip plans are dry runs. Publishing or upload requires human approval.
  • Vary the hook formula across videos. Repeating one formula across a slate trains the audience to skip.

Context

NeedLoad
Video content mechanicsknowledge/playbooks/video-content-creation.md
TikTokknowledge/channels/tiktok-algorithm.md
YouTube (Shorts and long-form)knowledge/channels/youtube.md
Instagram Reelsknowledge/channels/instagram.md
Clipping long-form into short-formknowledge/playbooks/video-clipping-automation-workflow.md
Any transcript, caption, podcast, webinar, or third-party sourceharness/references/transcript-video-research-rules.md
Product, ICP, voice, channelsMARKETING.md (project root)

Short-form script (15–60s) carries: platform, length, format, HOOK (0–3s, pattern interrupt — question, bold claim, or visual surprise), BODY (3–45s, one idea and one takeaway with bracketed visual direction), CTA (last 3–5s), timestamped on-screen text overlays, 3–5 platform-appropriate hashtags, and a trending-audio suggestion or "original audio".

Long-form script (5–15min) carries: HOOK (0–30s previewing the payoff), INTRO (30s–1min: context, credibility, structure promise), three content sections with visual direction, RECAP + CTA, chapter timestamps, and a thumbnail concept (3–5 words of title text, expression, key visual).

Hook formulas — rotate across a slate:

TypeFormulaExample
Question"Did you know [surprising fact]?""Did you know 73% of leads call after hours?"
Bold claim"[Contrarian statement]""Cold email is dead. Here's what replaced it."
Problem"If you're struggling with [X]...""If your landing page converts under 3%..."
Result"We went from [bad] to [good] in [time]""We went from 2% to 11% conversion in 3 weeks"
List"[Number] [things] that [outcome]""5 emails every SaaS needs on day one"

Clip scoring — score every candidate before scripting it, 1–5 per factor:

FactorQuestion
HookDo the first 3 seconds create a clear reason to keep watching?
Standalone clarityCan the viewer understand the moment without the full source?
ProofDoes it include a concrete example, result, quote, or demo moment?
TensionDoes it contain contrast, surprise, objection, stakes, or a reveal?
Source safetyIs the claim attributable and cleared for use?

Clips scoring 18/25 or higher are production candidates. Lower scores go to workspace/video/clipping-plan/_kill-list.md with the reason.

Output goes to workspace/video/: _video-plan.md, short-form/ (per-platform scripts), long-form/, clipping-plan/clips-from-[source].md, _quality-report.md.

Escalate when

  • Source footage rights, guest approval, or customer permission for a clip is unconfirmed.
  • A claim in the script needs a number that has no source.
  • The requested length or format conflicts with the platform's current norms in the loaded channel guide.
  • The user wants the video rendered rather than scripted — that is /kai-video-production.
  • Anything would be uploaded or published before human approval.

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

majiayu000/claude-skill-registry

Builds, edit or validate Agent Skill through conversational discovery. Use when the user requests to "Create an Agent", "Optimize an Agent" or "Edit an Agent".

majiayu000/claude-skill-registry

Edit existing BMAD agents while maintaining compliance

majiayu000/claude-skill-registry

Edit existing BMAD agents while maintaining compliance

majiayu000/claude-skill-registry

Edit existing BMAD modules while maintaining coherence

majiayu000/claude-skill-registry

Edit existing BMAD modules while maintaining coherence

majiayu000/claude-skill-registry

Analyzes current state and user query to answer BMad questions or recommend the next workflow or agent. Use when user says what should I do next, what do I do now, or asks a question about BMad

majiayu000/claude-skill-registry

Build AI agents with Google ADK Python (Agent Development Kit). Use for multi-agent systems, workflow agents (sequential/parallel/loop), Vertex AI deployment, tool integration, human-in-the-loop.

majiayu000/claude-skill-registry

Build AI agents with Google ADK Python (Agent Development Kit). Use for multi-agent systems, workflow agents (sequential/parallel/loop), Vertex AI deployment, tool integration, human-in-the-loop.

majiayu000/claude-skill-registry

Portfolio allocation and rebalancing optimizer. Manages asset allocation across stocks/cash/bonds, performs periodic rebalancing, and ensures diversification according to market regime and risk tolerance.

majiayu000/claude-skill-registry

Create a hilarious and ultra-realistic video of an anthropomorphic animal acting like a human vlogger in a real-world setting.

majiayu000/claude-skill-registry

Speech-to-text transcription and translation via OpenAI Audio API -- models, response formats, timestamps, prompting, streaming, chunking, and diarization

majiayu000/claude-skill-registry

BlockRun works with Claude Code and Google Antigravity.

majiayu000/claude-skill-registry

This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.

majiayu000/claude-skill-registry

小省导购员数字人带货版即梦视频提示词生成系统,基于四大智能体协同(提示词生成师、质量管控师、知识库运维师、跨环节适配师),按照"主体+运动+场景+(镜头语言+光影+氛围)"公式输出中英文双版提示词,适配5s短视频。确保人物一致性、视觉连贯性、情绪连贯性,支持知识库智能复用和跨工具适配(Suno音乐、AI绘画),为数字人带货视频提供高质量提示词生成服务。

majiayu000/claude-skill-registry

Upload and manage files using Google Gemini File API via scripts/. Use for uploading images, audio, video, PDFs, and other files for use with Gemini models. Supports file upload, status checking, and file management. Triggers on "upload file", "file API", "upload image", "upload PDF", "upload video", "file management".

majiayu000/claude-skill-registry

CRITICAL: Use for MolyKit AI chat toolkit. Triggers on: BotClient, OpenAI, SSE streaming, AI chat, molykit, PlatformSend, spawn(), ThreadToken, cross-platform async, Chat widget, Messages, PromptInput, Avatar, LLM

majiayu000/claude-skill-registry

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

majiayu000/claude-skill-registry

Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4), videos (Veo 3). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.

majiayu000/claude-skill-registry

Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4), videos (Veo 3). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.

majiayu000/claude-skill-registry

Skill for discovering and researching autonomous AI agents, tools, and ecosystems using the AgentFolio directory.

Related Skills