Delegate independent tasks to specialized agents working concurrently with isolated context.
Team Group Photo
This skill should be used when the user asks to "create team photo", "generate group portrait", "make team banner", "pixel art team image", "group shot with multiple people", or needs a composite pixel art image featuring multiple team members arranged together.
SKILL.md
Full skill instructions
Team Group Photo
Generate pixel art team group portraits featuring multiple characters arranged in a composition, each maintaining likeness to their individual reference photos.
Key Insight: Transfer, Don't Describe
DO NOT describe faces in your prompt. The more you describe facial features, the more the model will GENERATE new faces instead of TRANSFERRING likeness from the input images.
Instead:
- Provide all reference images as
--inputflags - Use a simple prompt that instructs TRANSFER of likeness
- Include the background image as another input
Usage
Use the generate-image skill script directly:
cd ${CLAUDE_PLUGIN_ROOT}/skills/generate-image && bun run scripts/generate.ts \
"Pixel art team group portrait. Arrange left to right: [Name1], [Name2], [Name3], [etc], [Mascot]. Transfer exact likeness from each input reference. Use the background image exactly. Uniform pixel art style. No text. No border." \
--input /path/to/person1.png \
--input /path/to/person2.png \
--input /path/to/person3.png \
--input /path/to/mascot.jpg \
--input /path/to/background.png \
--aspect 21:9 \
--size 2K \
--output /path/to/output.png
Example: B Open Team (Light Mode)
cd ${CLAUDE_PLUGIN_ROOT}/skills/generate-image && bun run scripts/generate.ts \
"Pixel art team group portrait. Arrange left to right: Kurt, Luke, David, Jason, Dan, Root mascot. Transfer exact likeness from each input reference. Use the watercolor sky background exactly. Uniform pixel art style. No text. No border." \
--input /path/to/team/kurt.png \
--input /path/to/team/luke.png \
--input /path/to/team/david.jpg \
--input /path/to/team/jason.png \
--input /path/to/team/dan.png \
--input /path/to/team/root.jpg \
--input /path/to/bg-light.png \
--aspect 21:9 \
--size 2K \
--output /path/to/team-group-light.png
Example: B Open Team (Dark Mode)
cd ${CLAUDE_PLUGIN_ROOT}/skills/generate-image && bun run scripts/generate.ts \
"Pixel art team group portrait. Arrange left to right: Kurt, Luke, David, Jason, Dan, Root mascot. Transfer exact likeness from each input reference. Use the night mountain scene background exactly. Uniform pixel art style. No text. No border." \
--input /path/to/team/kurt.png \
--input /path/to/team/luke.png \
--input /path/to/team/david.jpg \
--input /path/to/team/jason.png \
--input /path/to/team/dan.png \
--input /path/to/team/root.jpg \
--input /path/to/bg-dark.png \
--aspect 21:9 \
--size 2K \
--output /path/to/team-group-dark.png
What NOT to Do
BAD - Describing faces causes model to generate instead of transfer:
## CHARACTER LINEUP (Left to Right)
1. **KURT** (leftmost, front)
- Bald head
- Brown/auburn full beard
- Dark navy suit jacket with tie
- Friendly smile
2. **LUKE** (slightly behind Kurt)
- Dark curly/wavy hair
- Dark beard and goatee
- Pink button-up shirt
This approach tells the model WHAT to generate, causing it to create generic faces matching the description rather than transferring likeness from the actual input photos.
GOOD - Simple transfer instruction:
"Transfer exact likeness from each input reference"
Let the input images speak for themselves. The model will extract the likeness directly from the photos.
Light vs Dark Variants
For theme-aware websites, generate both variants:
- Light mode: Use bright/day background image as input
- Dark mode: Use dark/night background image as input
Same character references, different background input.
Options Reference
--input <path>- Reference image (up to 14 total: 5 humans, 6 objects)--aspect <ratio>- 1:1, 16:9, 9:16, 4:3, 3:4, 21:9--size <1K|2K|4K>- Image resolution--output <path>- Output file path
Troubleshooting
Faces don't match references
- Remove ALL facial descriptions from your prompt
- Ensure each reference image is included as
--input - Use simpler prompt focused on "transfer" language
Background doesn't match reference
- Include background image as an
--input - Say "Use the background image exactly" in prompt
- Don't describe the background, just reference it
Mascot rendered incorrectly
- Include mascot reference as
--input - Name the mascot in the arrangement list
- If still wrong, add brief note: "Root is a yellow frog with banana on head"
Style inconsistent across characters
- Add "Uniform pixel art style" to prompt
- Use same reference style for all character inputs
- Generate at 2K for better detail consistency
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
