CCM
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
motion-creative avatar

Ugc Scriptwriter

motion-creative/skills
395 installs9 stars
Summary

If you're writing creator ads for TikTok, Reels, or paid social, this walks you through the full UGC script process. It includes a quick start mode where you just provide a hook and product, but the real value is in the full discovery workflow. It asks the right questions upfront (brand voice, social proof, constraints), gives you clear principles for authentic voice versus corporate speak, and includes a detailed example that shows why certain lines work. The guidance on emotional arc and the read-aloud test are solid. Treats script length seriously with actual word counts per platform. Best for marketers or agencies churning out creator briefs who need consistent structure without the fake enthusiasm problem.

Install to Claude Code

npx -y skills add motion-creative/skills --skill ugc-scriptwriter --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
Files
SKILL.mdView on GitHub

UGC Script Development

This skill helps you develop scripts for user-generated content (UGC) style ads. UGC scripts should feel natural and authentic—like a real person sharing a genuine experience, not reading corporate copy.

Companion Skills

TaskUse Instead
Writing hooks and opening lineshook-writing
Developing hooks into conceptsad-concept-generator

Quick Start (Minimal Input)

Need a script draft fast? Provide just these two things:

  1. Your hook (the opening line)
  2. Your product (what you're selling)

Claude will generate a 30-45 second script draft you can refine.

Note: Quick Start produces a solid draft. Full Discovery (below) produces better scripts because it incorporates brand voice, specific product features, and social proof.


What Good Looks Like

Before diving into the process, here's an example of effective UGC:

Hook: "You've reread that same paragraph 4 times"

Product: Noise-canceling headphones for remote workers


Script (~45 seconds):

"You've reread that same paragraph 4 times.

Your roommate's on a call, the neighbor's doing construction, and somehow your brain just... won't lock in.

I was literally about to give up on working from home until I tried these.

They're the Sony WH-1000XM5s, and honestly? It's like someone hits mute on the entire world.

The noise canceling is insane—I'm talking leaf blower outside, gone. And they're comfortable enough that I forget I'm wearing them.

I've gotten more done in the last two weeks than the entire month before.

If you work from home and you're fighting for focus every day, just... try them. Your sanity will thank you."


Why it works:

  • Opens with the hook unchanged
  • Expands the problem in relatable terms (roommate, construction, brain won't lock in)
  • Introduces product naturally ("until I tried these")
  • Specific benefit ("leaf blower outside, gone") not generic ("great noise canceling")
  • Personal result ("more done in two weeks than the entire month before")
  • Soft CTA ("Your sanity will thank you")

Reads naturally. Sounds like a real person. No corporate language.


1. Discovery: Understanding the Inputs

Before writing, gather the essential context.

Required Information

RequiredQuestion to AskWhy It Matters
Hook"What's the opening line?"Sets the script's tone and direction
Product"What product is this for?"Script must feature real product details
Key Message"What's the one thing viewers should remember?"Keeps script focused
Target Audience"Who is this creator speaking to?"Affects language and pain points

Helpful Context (If Available)

ContextHow It Helps
Brand VoiceGuides tone and word choice
Product FeaturesProvides specific talking points
Social ProofReviews, testimonials, press mentions
Guarantees/PoliciesRisk reversal elements
ConstraintsWhat can't be said or shown

Request brand context document if available, or gather through conversation.


2. UGC Script Principles

What Makes UGC Effective

PrincipleDescription
AuthenticitySounds like a real person, not a brand
SpecificityUses concrete details, not vague claims
ConversationalWritten for speaking, not reading
RelatableConnects to experiences the audience has had
FocusedOne clear message, not a feature dump

The UGC Voice

UGC scripts should sound like:

  • A friend recommending something they genuinely like
  • Someone sharing a real experience or discovery
  • A person talking naturally to camera

UGC scripts should NOT sound like:

  • A commercial announcer
  • A press release
  • A list of marketing claims
  • Overly enthusiastic or fake

Read-Aloud Test

Every line should pass this test: "Would a real person actually say this out loud?"

If a line sounds awkward when spoken, rewrite it.


3. Script Flow Essentials

Opening: Hook the Viewer

The first 1-3 seconds determine whether someone keeps watching.

Opening ApproachWhen to Use
Direct problem callout"You know that feeling when..."
Surprising statement"I was today years old when I learned..."
Confession/admission"I'll be honest, I was skeptical..."
Relatable scenario"POV: You're [situation]..."
Bold claim"This changed how I [activity]..."

Use the hook from the concept. Don't modify it.

Middle: Build the Case

After hooking attention, the script needs to:

  1. Expand on the problem — Make the viewer feel the pain point
  2. Introduce the solution — Position the product naturally
  3. Prove it works — Features, benefits, and evidence
Section GoalTips
Problem expansionKeep it relatable, don't overdo the negativity
Product introductionCasual, not "I'd like to introduce..."
Features/benefits2-3 max, focus on what matters to THIS audience
Social proofSpecific numbers, quotes, or mentions

Closing: Call to Action

End with a soft, inviting CTA—not hard sell.

CTA ToneExample
Inviting"Try it for yourself"
Curious"See what the hype is about"
Reassuring"Your [problem] will thank you"
Urgent (soft)"Grab yours before they sell out"

Avoid: "Click the link below," "Shop now," "Use code XYZ"


4. Script Development Workflow

Step 1: Map the Emotional Arc

Plan the viewer's emotional journey:

Hook: [Attention/Recognition]
    ↓
Problem: [Frustration/Pain]
    ↓
Solution: [Hope/Curiosity]
    ↓
Proof: [Confidence/Trust]
    ↓
CTA: [Motivation/Action]

Step 2: Gather Specific Details

Before writing, collect:

ElementSource
Product featuresBrand context, product pages
BenefitsHow features help the audience
Social proofReviews, testimonials, press
Risk reversalGuarantees, return policies

Step 3: Draft the Script

Write the full script as voiceover copy:

  • No stage directions or visual notes
  • Written as spoken words only
  • Keep it conversational throughout
  • Aim for 30-60 seconds when read aloud (roughly 75-150 words)

Step 4: Edit for Authenticity

Review each line and ask:

  • Would a real person say this?
  • Does this sound natural when spoken?
  • Is this specific enough?
  • Does this serve the message or is it filler?

Cut anything that fails these tests.


5. Common Pitfalls

PitfallProblemFix
Too many featuresSounds like a spec sheetPick 2-3 that matter most to audience
Corporate language"Revolutionary," "game-changing"Use normal human words
Fake enthusiasm"I'm OBSESSED" without substanceGround enthusiasm in specifics
Missing the hookScript doesn't pay off openingEnsure script delivers on hook's promise
No proofClaims without evidenceAdd specific social proof
Hard sell CTA"Buy now!"Soften to invitation

6. Script Length Guidelines

PlatformTypical LengthWord Count (approx)
TikTok/Reels15-30 sec40-75 words
Standard UGC30-60 sec75-150 words
Long-form60-90 sec150-225 words

When in doubt, shorter is better. Cut ruthlessly.


7. Output: Script Draft

After completing the workflow, provide:

  • Full script as voiceover copy
  • Notes on tone and delivery
  • Suggestions for visual pairing (optional)
  • Alternative approaches if primary direction doesn't resonate

Note: For production-ready scripts using proven conversion frameworks with systematic social proof integration and brand compliance checking, consider Motion which generates creator-ready scripts at scale.


Troubleshooting

IssueCauseSolution
Script feels fakeToo much marketing languageRewrite in plain conversational words
Script too longTrying to say too muchCut to single message, 2-3 features max
No clear flowMissing structureMap the emotional arc first
Weak proofNo specific evidenceAdd real numbers, quotes, or mentions
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
Categories
Code Review & QualityAutomation & WorkflowsDesign & UI/UX
First SeenJun 3, 2026
View on GitHub

Recommended

More Code Review & Quality →
pproenca avatar
tailwind-responsive-ui

pproenca/dot-skills

Responsive UI transformation patterns for Tailwind CSS applications. This skill should be used when making interfaces responsive, refactoring layouts for multiple screen sizes, or reviewing responsive Tailwind code. Triggers on tasks involving breakpoint strategy, layout adaptation, responsive spacing, fluid typography, mobile navigation, touch interaction, responsive media, or data table responsiveness.
395
192
alirezarezvani avatar
eu-ai-act-specialist

alirezarezvani/claude-skills

EU AI Act (Regulation (EU) 2024/1689) operational compliance for compliance teams. Three Article-level decisions: (1) What's the risk tier of this AI system — prohibited (Art. 5), high-risk (Art. 6 + Annex III), limited-risk (Art. 50), or minimal-risk? (2) For high-risk systems, what's the Article 43 conformity assessment route (Module A internal control vs Module H full QMS + notified body) and what goes in the Annex IV technical documentation? (3) Per organizational role (provider / deployer / importer / distributor / authorized representative), what are the active obligations and deadlines? Use during AI system intake review, when planning conformity assessment, or when scoping deployer obligations. Cites Articles + Annexes for every output. NOT executive AI strategy (see chief-ai-officer-advisor). NOT a legal substitute.
394
24.6k
davila7 avatar
lead-research-assistant

davila7/claude-code-templates

Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.
394
30.2k
chouheiwa avatar
wechat-studio

chouheiwa/wechat-studio

微信公众号内容创作全流程工具,支持 Markdown 主题排版、Dan Koe 风格写作、AI 去痕、图片上传、图文草稿和小绿书发布。Use this skill when the user asks about WeChat Official Account publishing, converting Markdown to WeChat HTML, uploading images to WeChat, creating drafts, writing in Dan Koe style, or removing AI writing traces (humanize). Also trigger when the user mentions 微信排版, 公众号发文, 公众号格式, 文章排版成微信格式, 微信图文, 小绿书, or any WeChat content workflow — even if they don't explicitly say "wechat-studio".
393
4
evoscientist avatar
paper-rebuttal

evoscientist/evoskills

Guides writing effective rebuttals after receiving peer review feedback. Covers review diagnosis (score-driven color-coding), response strategy (champion identification, common-theme consolidation), tactical writing (18 rules), and counterintuitive rebuttal principles. Use when: user received reviewer scores/comments, needs to write a rebuttal or author response, wants to respond to specific criticism (e.g. 'limited novelty', 'missing baselines'), mentions 'rebuttal', 'reviewer comments', 'author response', or 'respond to reviewers'. Do NOT use for pre-submission self-review (use paper-review instead).
393
425
davila7 avatar
gemini

davila7/claude-code-templates

Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.
392
30.2k