Social media kit
Creative AI skills for Xainflow — reusable workflows for image, video, and brand content generation
npx -y skills add xainflow/skills --skill social-media-kitAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Generate a set of images optimized for multiple social media platforms from a single concept or image. Creates variations for Instagram, TikTok, stories, and web banners.
SKILL.md
1.1 KB, 160 tokens by cl100k_base, as published. Nobody here has run it
Social Media Kit
Create a multi-platform content workflow from a single concept or image.
Inputs
Ask the user for their concept (text prompt) or source image, and which platforms they need content for.
Workflow structure
Create a workflow with platform-specific variations:
- Instagram feed post (1:1)
- Instagram/TikTok story (9:16)
- Web banner / Twitter header (16:9)
- Pinterest pin (2:3)
Each variation should adapt the composition for the target format, not just crop. Use the default-model from the frontmatter.
Organization
Save outputs to the output-folder specified above. Create it if it does not exist.
Before executing
Show a summary with platforms, total images, and credit cost. Ask for confirmation.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most social media skills give in 160 tokens
Counted across 489 of the 492 authors here whose files we hold, read 2026-08-07
- Adapt formats and tone to each platformin 26 of 489, across 14 files
- Build content around three to five pillarsin 25 of 489, across 13 files
- Read product marketing context before asking questionsin 23 of 489, across 13 files
- Respond to all comments on your postsin 21 of 489, across 9 files
- Use the output flag to specify an output directoryin 14 of 489, across 4 files
- Generate output logo images with white backgroundin 13 of 489, across 4 files
- Fix failing generation scripts directlyin 13 of 489, across 4 files
- Ask user about HTML preview after logo generationin 12 of 489, across 3 files
- Run the download script with a URLin 12 of 489, across 3 files
- Implement exponential backoff for 429 responsesin 12 of 489, across 3 files
- Write the hook firstin 12 of 489, across 7 files
- Include a single clear call to actionin 12 of 489, across 9 files
Said here and by no other author read
- ask user for concept or source image
- adapt composition for target format
- use default-model from frontmatter
- show summary before executing
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.