Skills
Social image and meme creation
for Claude Code and Cursor
anycap-social-meme-workflows is an installable skill that teaches Claude Code, Cursor, Codex, and similar coding agents how to produce meme-style images, captioned photos, and social visuals as part of an automated content workflow. Without this skill, an agent tasked with creating social content cannot efficiently combine AI image generation with structured text overlay, does not know the right prompt patterns for meme formats, and cannot batch-produce visual variations for A/B testing across platforms. With the skill installed, the agent uses AnyCap image generation to create a base visual, then applies local text overlay to produce the captioned or annotated format typical of viral social content. The workflow supports single-image production, variation batches, and format-specific output sizing for platforms such as Twitter/X, Instagram, and LinkedIn. This skill is useful for social media teams, content marketers, developer advocates, and any team running automated content pipelines where visual assets need to be produced at volume without manual design tools. The skill is compatible with Claude Code, Cursor, and Codex.
Install time
< 5 min
Supported agents
Claude Code · Cursor · Codex
Platform
macOS · Linux · Windows
Install this skill
npx -y skills add anycap-ai/anycap -s 'anycap-social-meme-workflows' -g -y
How the workflow changes after install
BEFORE
Agent generates one image at a time with no format awareness or text overlay. Human must use a separate design tool to add captions or resize for platforms.
AFTER
Agent generates a base visual, applies structured text overlay in meme format, produces platform-specific sizes, and can batch variations for A/B testing — all in one run.
- 1
Receive theme or source image
User provides a meme concept, caption idea, topic, or an existing image to restyle.
- 2
Generate base visual
Agent calls `anycap image generate` with a prompt optimized for the meme format — composition, style, and focal point aligned with the caption placement.
- 3
Apply text overlay
Agent applies the caption text in the standard meme format using local text overlay tools. Font, size, and placement follow platform conventions.
- 4
Produce platform sizes
Agent resizes and crops the output for Twitter/X (1200×675), Instagram square (1080×1080), Instagram story (1080×1920), and LinkedIn (1200×627).
- 5
Generate variation batch (optional)
Agent produces 3–5 caption variations on the same base image for A/B testing across posts.
SAMPLE OUTPUT
Meme batch complete: "launch day announcement"
├── Base image: generated (1600×900, AI)
├── Caption variants: 4
└── Platform exports:
├── twitter-x.png 1200×675
├── instagram-square.png 1080×1080
├── instagram-story.png 1080×1920
└── linkedin.png 1200×627Capabilities used by this skill
Supported agents
Frequently asked questions
- What does this skill do that direct prompting doesn't?
- Direct prompting gives one image with no format or text overlay awareness. This skill adds structured caption overlay, platform-specific sizing, and variation batching — turning Claude into a social content production pipeline.
- Which social platforms does it support?
- Twitter/X, Instagram (square and story), and LinkedIn by default. Custom dimensions can be specified in the brief.
- Can I use my own source image?
- Yes. Provide a source image and the agent applies text overlay and styling on top. Or give a description and the agent generates the base image first.
- Do I need an AnyCap account?
- Yes. Install the CLI and run `anycap login` before your first session.