agentleFS
Marky-TeamMarky-Team/marky-skills/skills/create-post-from-image/SKILL.md

create-post-from-image

Skill5 starsChanged 4 months agoApache-2.0View on GitHub

Turn one image from your Marky library into several ready-to-review social posts through the API. Use this when you have a strong photo or graphic (a product shot, a professional photo, a branded design) and want to get maximum mileage out of it with multiple captions and angles. Picks a library image and creates several draft posts that all use it. Reads auth and endpoints from the marky-api skill. Also triggers on "make posts from this photo", "use this image for a post", "what can I do with this picture". To design a new image instead, see create-post-graphic.

  • Sends data out

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Marky wants your feedback: If anything breaks or is confusing while you run this skill — and again once you finish — send Marky a quick …

    line 21
  2. Distinctive:

    If the image is on the user's computer and not in the library yet, upload it first:

    line 38
  3. Distinctive:

    Keep each one genuinely different.

    line 59

≈ “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

Posts From Library Image

Got one great image? Get several posts out of it. This skill takes a single image from your library and creates a handful of draft posts, each with its own caption and angle, all using that image.

Read the marky-api skill first for the base URL, your mk_live_ key, and the full endpoint list. Everything below uses https://api.mymarky.ai/api and the header Authorization: Bearer mk_live_YOUR_KEY.

Marky wants your feedback. If anything breaks or is confusing while you run this skill — and again once you finish — send Marky a quick note with the submit_feedback MCP tool. See the "Marky wants your feedback" section in the marky-api skill for when and how.

Step 1 — find the workspace and pick an image

curl https://api.mymarky.ai/api/workspaces \
  -H "Authorization: Bearer mk_live_YOUR_KEY"

# Browse your media library and pick one image.
curl "https://api.mymarky.ai/api/businesses/BIZ_ID/library" \
  -H "Authorization: Bearer mk_live_YOUR_KEY"

Show the user the options and let them choose. Grab the chosen item's image URL (its original_url) to attach to each post. (To find a specific image fast, use GET /businesses/BIZ_ID/library/search?query=....)

If the image is on the user's computer and not in the library yet, upload it first:

curl -X POST "https://api.mymarky.ai/api/businesses/BIZ_ID/media" \
  -H "Authorization: Bearer mk_live_YOUR_KEY" \
  -F "file=@/path/to/photo.jpg"

The upload response includes the original_url to use below.

Step 2 — write several angles

Decide how many posts (5 is a good default) and write a distinct caption for each. Same image, different angle:

  • A benefit-led caption (what the customer gets).
  • A story or behind-the-scenes caption.
  • A question hook that invites replies.
  • A direct call-to-action caption.
  • A short, punchy caption.

Keep each one genuinely different. The image is shared, the words should not be.

Step 3 — create the draft posts

For each caption, create a post with status NEW (a draft) using the same image URL:

curl -X POST https://api.mymarky.ai/api/businesses/BIZ_ID/posts \
  -H "Authorization: Bearer mk_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "caption": "Angle 1 caption goes here.",
    "media_urls": ["ORIGINAL_URL_OF_THE_IMAGE"],
    "restrict_publish_to": ["instagram", "facebook", "linkedIn"],
    "status": "NEW"
  }'

Repeat for each angle. Image posts can target every platform except TikTok (which needs video).

Step 4 — review and hand off

List the new drafts so the user can review them:

curl "https://api.mymarky.ai/api/businesses/BIZ_ID/posts?status=NEW" \
  -H "Authorization: Bearer mk_live_YOUR_KEY"

Show the set and ask which to keep. To schedule the keepers, use the schedule-posts skill, or schedule directly with POST /businesses/BIZ_ID/posts/POST_ID/schedule.

Tips

  • This is perfect for evergreen visuals: a hero product shot, a team photo, a signature graphic. One asset, a week of posts.
  • Space the posts out so the same image does not show up two days in a row.
  • Pair with the review-performance skill to find which of your images already perform, then repurpose those.

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.