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
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Multi Channel Bundle

PicsArt/gen-ai-skills
75 installs4 starsMIT
Summary

Replaces Picsart's two redundant campaign and launch kit skills with a single entry point that branches into mode-specific references. You feed it a brief, pick your channels (LinkedIn, Instagram, email, landing page, ads, reels), and it batch-generates a folder structure with correctly sized assets for each. The mode references handle the channel matrix and manifest templates so you're not building JSON by hand. Most useful when you need consistent hero-plus-variants across five or six formats at once and want to avoid the aspect ratio drift that happens when you regenerate per channel. If you only need ad variants or pitch slides, the other Picsart skills are more targeted.

Install to Claude Code

npx -y skills add PicsArt/gen-ai-skills --skill multi-channel-bundle --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
AI notepad for back-to-back meetings
AI notepad for back-to-back meetings
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Email for Agents: Free tier availableEmail for Agents: Free tier available
Email for Agents: Free tier available
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
AI notepad for back-to-back meetings
AI notepad for back-to-back meetings
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Email for Agents: Free tier availableEmail for Agents: Free tier available
Email for Agents: Free tier available
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Files
SKILL.mdView on GitHub

Multi-Channel Bundle

Produce a coordinated set of assets — hero, social variants, OG image, reel, optionally audio — for a single push: a marketing campaign or a product launch. Replaces two near-identical skills (campaign-kit, launch-kit) with one entry point and two mode references that differ only in scale, naming, and channel mix.

Input: the brief (campaign or launch). Output: a folder per channel with on-brand, on-format assets ready to ship.

When to Use

ModeTrigger phrasesReference
campaign"campaign kit", "multi-channel campaign assets", "LinkedIn + IG + email + LP + ads in one go"references/modes/campaign.md
launch"launch kit", "product launch assets", "launch day social + reel + soundtrack"references/modes/launch.md

If the user wants pitch-deck slides for an agency client, that's agency-pitch-mockups. If they want N ad variants from one hero (no other channels), that's marketer-ad-variant-factory.

Prerequisites

Picsart gen-ai CLI installed and authenticated:

curl -fsSL https://picsart.com/gen-ai-cli/install.sh | bash
gen-ai login
gen-ai whoami

Per-mode setup (channel matrix, copy alignment, motion source, audio licensing) lives inside each mode reference.

How to Run

  1. Identify the mode from the user's request using the table above.
  2. Load the corresponding mode reference: Read references/modes/<mode>.md.
  3. Follow the per-mode procedure — confirm channels, build the manifest, batch-generate.
  4. Return here only when switching modes.

Quick Reference

# Bundle generation is always a batch run
gen-ai batch --manifest manifest.json --output bundle/

# Estimate before committing
gen-ai pricing --manifest manifest.json

Manifest templates per mode live in the mode references.

Procedure

Shared outer loop:

  1. Scope — confirm: which channels, hero asset, copy lock state, motion (reel) required yes/no, audio required yes/no, deadline.
  2. Manifest — assemble a JSON manifest covering every required channel and format.
  3. Estimate — gen-ai pricing --manifest manifest.json. Surface the total.
  4. Generate — gen-ai batch. Stream progress.
  5. Compose — if a reel is in scope, hand the clips to gen-ai-use for assembly.
  6. Package — drop into bundle/<run>/<channel>/. Optionally zip via agency-client-handoff.

Pitfalls

  • Aspect ratios drift. Bake all required ratios (1:1, 4:5, 9:16, 16:9, 1200×630) into the manifest up front; don't fix per-channel afterward.
  • Copy lock matters. If copy isn't locked, treat the run as a draft; mark outputs in filenames (<channel>-DRAFT-...).
  • Audio licensing. Launch reels with soundtracks need licensed tracks; document the source in the manifest.
  • Mode-specific pitfalls live in the mode references.

Verification

# Confirm one folder per channel exists with expected file counts
find bundle/<run> -type d -maxdepth 1
ls -1 bundle/<run>/<channel>/ | wc -l

See also

  • agency-pitch-mockups — pitch-deck slide variant (different output type)
  • marketer-ad-variant-factory — ad-only fan-out
  • product-photo-studio — product-photo transforms feeding into a bundle
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
AI notepad for back-to-back meetings
AI notepad for back-to-back meetings
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Email for Agents: Free tier availableEmail for Agents: Free tier available
Email for Agents: Free tier available
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Categories
Code Review & QualityAI & Agent BuildingRelease Management
First SeenJul 6, 2026
View on GitHub

Recommended

More Code Review & Quality →
thermo-nuclear-code-quality-review

cursor/plugins

thermo nuclear code quality review
6.2k
2.3k
clojure-review

metabase/metabase

Review Clojure and ClojureScript code changes for compliance with Metabase coding standards, style violations, and code quality issues. Use when reviewing pull requests or diffs containing Clojure/ClojureScript code.
45.8k
typescript-review

metabase/metabase

Review TypeScript and JavaScript code changes for compliance with Metabase coding standards, style violations, and code quality issues. Use when reviewing pull requests or diffs containing TypeScript/JavaScript code.
45.8k
checking-code-quality

telagod/code-abyss

Checks code quality metrics including complexity, duplication, naming conventions, and function length. Use when running quality gates, reviewing code smells, or checking lint rules. Automatically triggered on complex modules or post-refactor.
224
review-and-refactor

github/awesome-copilot

Automated code review and refactoring against project-specific coding guidelines and instructions.
10.7k
36.5k
ponytail-review

DietrichGebert/ponytail

Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Complements correctness-focused review, this one only hunts complexity.
326
19.3k