agentleFS
Sign inStart free
claudiocebpazclaudiocebpaz/blotato-opencode/.claude/skills/visual-producer/SKILL.md

visual-producer

Skill2 starsChanged 4 months agoMITView on GitHub

Generates the visual media for a post using Blotato's template API (carousels, images, infographics, AI videos). Use when a post needs an image, carousel, or video. Picks a template, injects the brand's colors/fonts, calls Blotato, polls, and returns media URLs.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Save the rendered assets in the repo (mandatory): Don't leave the visual only in the scratchpad or only as a Blotato CDN URL.

    line 41
  2. Very specific:

    If the user already has their own image/URL, pass it as imageSource/mediaSource (no credits spent).

    line 55
  3. Very specific:

    Don't invent template IDs: use the ones from the catalog, or discover them with python scripts/blotato.py templates.

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

visual-producer (Blotato generates)

Project-specific extension. The official Blotato pack (content-coach, brand-brief, post-writer, post-grader, post-scheduler, repurpose, viral-hooks) does NOT include visual generation via API. This skill fills that gap: it's the one that makes Blotato generate the carousels, images, infographics, and videos that post-scheduler later schedules. It's invoked between writing and scheduling, when the piece carries media.

You are the bridge to Blotato's creative engine. You pick the template and assemble the inputs; Blotato renders. You return the media URLs ready for the post.

Context you load

  1. _base/templates.md (catalog + inputs + default image model).
  2. branding.md (brand colors, font, logo, aspect ratio).

Process

  1. Pick the template based on the piece:
    • Carousel with a message (LinkedIn/IG) → Image Slideshow with text (5903b592...) or Tutorial Carousel (2491f97b...).
    • Carousel of pure images (IG) → Instagram Carousel Slideshow (53cfec04...).
    • Quote → Quote Card (9f4e66cd...).
    • Stat/infographic → infographics family (07a5b5c5...).
    • Faceless reel → AI Story Video with voice (5903fe43...).
  2. Inject the brand's branding into the inputs (backgroundColor, textColor, borderColor, font, profileImage, aspectRatio). See the mapping in templates.md.
  3. Pick the image model based on priority/cost (default fal-ai/imagen4/preview/fast = 7 credits).
  4. Generate and poll with the client:
    python scripts/blotato.py visual --template <ID> --inputs '<JSON>'
    The script creates (POST /videos/from-templates), polls (GET /videos/creations/:id) until done, and returns imageUrls (carousel/image) or mediaUrl (video).
  5. Save the rendered assets in the repo (mandatory). Don't leave the visual only in the scratchpad or only as a Blotato CDN URL. Copy the rendered files to posts/assets/<slug>/ (slide1.png…slideN.png for a carousel, image.png/video.mp4 for a single piece). If the carousel was assembled with a local render, also save the source HTML in posts/<slug>.carousel.html. Reason: the CDN URL is external and can go down; the repo must keep the bytes (see "Saving convention" in CLAUDE.md).
  6. Return the Blotato URLs AND the local paths to the orchestrator. The orchestrator writes in the draft's frontmatter: media_urls (Blotato URLs, used by post-scheduler) and local_media (the repo paths, for the permanent archive).

Rules

  • Confirm the estimated cost if the carousel uses an expensive model (credits = number of images × cost/model).
  • LinkedIn carousel = document from 2-10 images, no video.
  • Instagram always requires media (this agent provides it).
  • If the user already has their own image/URL, pass it as imageSource/mediaSource (no credits spent).
  • Don't invent template IDs: use the ones from the catalog, or discover them with python scripts/blotato.py templates.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free