awesome-content-image-adapter skillA
awesome-content-image-adapter is agent-read markdown (skill) from khasky/awesome-agent-skills: Adapts one finished image into the frame every platform shows it in, one file per platform slug, named so a post and its picture sit side by side. The platform list and each surface's frame shape come from awesome-content-campaign/references/platforms.md, so no file here restates them. Runs alone — a source image in, a folder of platform-ready PNGs out, opened on the machine — or as the third step of a content run, straight after the picture the user picked is handed over. The source artwork is .
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Content Image Adapter One picture, every platform's frame. The artwork does not change: no regeneration, no redraw, no restyle, no image service. What changes is the shape around it, and how the picture meets the edges of that shape. The platform list is not here. It is the canonical table in `awesome-content-campaign/references/platforms.md`, which is the single source of the vocabulary, and its `Image` column gives each surface's frame shape. This skill reads both and adds nothing to them; a platform that appears here and not there is a platform that does not exist. With that skill absent, the list and the frames are asked of the user rather than guessed. Bundled file (load on demand): - `references/geometry.md` — each frame shape's pixel target, how a picture is fitted into it, and what the result has to satisfy before it ships. Read it before fitting the first picture, once the target frames are known. ## Two modes, and the mode is not asked …
Read the whole file at its exact version.
How to install
mdr add khasky/awesome-agent-skills/awesome-content-image-adapter@git:20260918.de12e6bmdr add khasky/awesome-agent-skills/awesome-content-image-adapter@sha256:3ff00d2445bef926Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_lbmakoljrcdafuri)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260918.de12e6b latest | 2026-09-18 | de12e6b | 8,366 B | A | view · diff |
| git:20260918.18278a0 | 2026-09-18 | 18278a0 | 8,277 B | A | view · diff |
| git:20260918.73a7465 | 2026-09-18 | 73a7465 | 8,066 B | A | view · diff |
| git:20260918.6694ed7 | 2026-09-18 | 6694ed7 | 8,066 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8366 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
khasky/awesome-agent-skills · 10 stars · license MIT · pushed 2026-09-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lbmakoljrcdafuri GET https://markdownregistry.com/api/v1/resolve?ref=khasky/awesome-agent-skills/awesome-content-image-adapter GET https://markdownregistry.com/api/v1/blob/3ff00d2445bef926d127fe4f2cbc9559e2521e65388847b29231c06be8960d0e
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.