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

Enterprise Press Batch

PicsArt/gen-ai-skills
74 installs4 starsMIT
Summary

Built for comms and PR teams shipping embargoed press releases to wire services like AP, Reuters, and Getty. Takes your source photos (hero images, executive headshots, product shots) and produces the full matrix of deliverables: wire packs at 4K with TIFF exports, web resolutions in sRGB, print specs at 300dpi, and social crops. The workflow is embargo-first, everything lands in a locked Drive folder until lift, and it handles the annoying stuff that gets assets rejected: wire-service filename conventions, EXIF/IPTC rights metadata stamping, resolution requirements per outlet, and watermarking drafts but never finals. One smart constraint: never AI-generate executive faces, only enhance real photography. Good for product launches and leadership announcements where you need 40+ derivatives delivered correctly on deadline.

Install to Claude Code

npx -y skills add PicsArt/gen-ai-skills --skill enterprise-press-batch --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

Enterprise Press Batch

Produce full press-release asset bundles — hero, executive headshots, product shots, event-ready horizontal and vertical crops — with embargo controls, wire-service naming conventions, EXIF rights metadata, and multi-resolution exports. Built for comms / PR teams shipping to Reuters, AP, Getty, and corporate newsrooms under embargo.


When to Use

  • Product launch, earnings announcement, exec change, crisis response — assets needed across wire + web + print + social in parallel
  • Embargoed announcement requiring strict asset handling until lift
  • Multi-publication distribution where each wire has different resolution + EXIF requirements
  • Executive headshot refresh across a leadership team (consistent lighting, backgrounds, crops)
  • Event kits: pre-event (concept), during-event (placeholder + real), post-event (recap)

Do not use for: social-only launches (use gen-ai-workflows launch-kit), single-asset news posts.


Prerequisites

Before the batch runs:

  1. Release type + embargo — announcement date/time, embargo lift, distribution list. Embargoed runs must write to a locked Drive folder.
  2. Asset scope — which of: 1 hero, N exec headshots, M product shots, event horizontal, event vertical, social derivatives. Count per type.
  3. Distribution targets — wire service specs (AP: 3000px long edge JPEG, Getty: TIFF, Reuters: sRGB embedded). Determines resolution + format per pack.
  4. Rights metadata — credit line, copyright owner, usage rights, caption, contact. Written to EXIF/IPTC.
  5. Approval chain — legal, comms lead, exec approval for headshots? Who signs off before embargo pack ships?
  6. Audit trail — does the archive need the original brief + manifest + results for seven years (SOX-adjacent)?

How to Run

Six steps. Embargo handling is non-negotiable.

  1. Scope the bundle — write the deliverable matrix: asset × pack (wire / web / print / social) × resolution. Costs scale by cells, not by source images.
  2. Generate / ingest sources — AI-generated heroes via gen-ai generate; real executive photography ingested via gen-ai upload. Enhance with topaz-upscale-image if source resolution is below print spec.
  3. Embargo lock — create a restricted archive location. Everything until lift lands here. Never ship intermediate drafts.
  4. Batch exports — one manifest per pack (wire / web / print / social), each with the correct resolution, format, and color profile. Watermark drafts; never watermark final approved wire assets.
  5. Stamp EXIF / IPTC — rights, credit, caption, embargo notice injected on every file. Use exiftool as a post-batch step.
  6. Deliver — at embargo lift, promote from the locked folder to the public press-kit URL. Archive the manifest + results.json + checksum manifest for the audit trail.

Quick Reference

Each pack is its own manifest so wire / print / web / social can run in parallel with correct specs.

{
  "defaults": {
    "model": "topaz-upscale-image"
  },
  "metadata": {
    "release": "2026-04-LAUNCH",
    "embargo_lift": "2026-04-22T13:00:00Z",
    "brand_system_version": "brand.md@sha:a4f1c9",
    "approver": "comms-lead@company.com",
    "audit_id": "PRESS-2026-04-LAUNCH",
    "distribution": ["AP", "Reuters", "Getty", "corporate-newsroom"],
    "rights": {
      "credit": "Company Inc.",
      "copyright": "(c) 2026 Company Inc.",
      "usage": "Editorial use in connection with 2026 launch coverage only."
    }
  },
  "jobs": [
    {
      "id": "hero-16x9-wire",
      "imageUrls": ["./sources/hero-master.png"],
      "prompt": "4x upscale, sharpen, retain color profile",
      "aspectRatio": "16:9"
    },
    {
      "id": "exec-ceo-headshot-3x4-wire",
      "imageUrls": ["./sources/ceo-raw.jpg"],
      "prompt": "Editorial portrait enhance, studio light preserved"
    }
  ]
}

Filename convention (wire-service friendly): {release-id}_{asset-type}_{subject}_{aspect}_{resolution}.{ext} → 2026-04-LAUNCH_hero_product_16x9_4k.jpg. Survives rebranding; matches Reuters/Getty ingest patterns.


Quick Reference

Sub-taskModelNotes
Hero concept (AI-generated)flux-2-pro / gemini-3-pro-imageCommercial-safe, editorial fidelity
Exec headshot enhance (real photo)topaz-upscale-imagePreserves identity; no hallucination
Background cleanup on real photopicsart-change-bgStudio backdrop substitution
Background removal for transparent packpicsart-remove-bgSocial + overlay-ready PNG
Product shot from angle libraryflux-kontext-proEdit-mode, product-accuracy preserve
Event B-roll from single stillkling-v3-pro (i2v)For broadcast packs only

Never use fully-generative models on named executives or real products without explicit legal sign-off. Use enhance/edit-only models. Confirm licensing per account with gen-ai models info.


Procedure

  • Embargo-first workflow. Locked Drive folder from minute one. No assets leave it until lift.
  • Never AI-generate a real executive's face. Enhance / upscale real photography only. Legal + reputational risk otherwise.
  • Watermark drafts, never watermark approved finals. Wires reject watermarked assets.
  • Wire-service naming convention is the contract. {release}_{type}_{subject}_{aspect}_{res}. Do not deviate.
  • Stamp EXIF/IPTC before delivery. Credit, copyright, caption, embargo notice. exiftool pass is non-negotiable.
  • Resolution matters. Print = 300dpi, 4k long edge min. Web = 2400px long edge, sRGB. Social = per-platform. Export once per spec; don't downscale at publish time.
  • Checksum the delivery. SHA256 manifest shipped alongside the pack so newsrooms can verify integrity.
  • Multi-resolution from a single master. Render the hero at max quality once, derive downward. Never upscale a JPEG.
  • Brand-gate the AI-generated portions with brand.md (see enterprise-brand-governor).

Pitfalls

  • Embargo leak via public Drive folder — assets land in the default gen-ai-cli folder, which may be broadly accessible. Always --drive-folder to a restricted path.
  • AI-generated executive faces — never acceptable. Use real photography + enhance.
  • Watermark on approved wire asset — auto-rejected by AP / Reuters ingest. Separate draft vs. final pipelines.
  • Missing EXIF rights — Getty will reject; Reuters will strip your credit. Always stamp.
  • Wrong color profile — print pack needs CMYK or at least embedded sRGB. Validate with exiftool -ColorSpace.
  • One manifest per pack, not per release — trying to run all 44 deliverables in one batch mixes resolution specs and you get wrong sizes somewhere. Pack per manifest.

Verification

Run gen-ai whoami to confirm authentication, then re-run the failed command with --debug.

Commands

# Generate the hero
gen-ai generate --model flux-2-pro --prompt "$HERO_PROMPT" \
  --aspect-ratio 16:9 --resolution 4k \
  --save-to-drive --drive-folder "Press-2026-04-LAUNCH"

# Enhance exec headshots to print spec
gen-ai batch run exec-headshots.json \
  --concurrency 3 --output ./runs/press-2026-04-execs

# Export the multi-resolution packs
gen-ai batch run press-packs.json \
  --concurrency 5 --output ./runs/press-2026-04-packs

# Post-process: stamp rights metadata (exiftool)
exiftool -overwrite_original \
  -Credit="Company Inc." \
  -Copyright="(c) 2026 Company Inc. All rights reserved." \
  -Caption-Abstract="$CAPTION" \
  -By-line="Company Inc. Press Office" \
  ./runs/press-2026-04-packs/*.jpg

Cost & time

Assumes one release: 1 hero + 4 exec headshots + 6 product shots × 4 packs each (wire / print / web / social).

ComponentCreditsWall time
1 hero (flux-2-pro, 4k)~10~2 min
4 exec enhances (topaz, 4x)~40~5 min
6 product edits (flux-kontext-pro)~30~8 min
Multi-res derivatives + EXIF + Drive0~8 min
Total per release~80~25 min

Crisis-response same-asset-set in <60 min is achievable with this pipeline; physical shoots cannot.


See also

  • enterprise-brand-governor — brand.md gating for AI-generated portions
  • enterprise-pinned-registry — lock models so pre-embargo renders match final
  • product-photo-studio — adjacent batch pattern (reshoot mode)
  • multi-channel-bundle — launch and campaign bundle patterns
  • gen-ai-use — CLI reference
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
AI & Agent BuildingAutomation & Workflows
First SeenJul 6, 2026
View on GitHub

Recommended

More AI & Agent Building →
agent-memory-mcp

sickn33/antigravity-awesome-skills

agent memory mcp
1.2k
43.1k
agent-memory-mcp

davila7/claude-code-templates

agent memory mcp
569
29.4k
llm-application-dev-langchain-agent

sickn33/antigravity-awesome-skills

llm application dev langchain agent
306
39.4k
llm-application-dev

moizibnyousaf/ai-agent-skills

Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
1.1k
ai-prompt-engineering-safety-review

github/awesome-copilot

Comprehensive safety analysis and improvement framework for AI prompts with detailed assessment methodologies.
9.8k
36.5k
emblem-ai-prompt-examples

emblemcompany/agent-skills

emblem ai prompt examples
8.8k
12