Repository navigation
Add cloudinary-image-picker skill - #27
Draft
carlevison wants to merge 6 commits into
Draft
carlevison wants to merge 6 commits into
carlevison wants to merge 6 commits into
Conversation
Hackathon draft of a use-case skill that picks images for website slots from a Cloudinary product environment: discovers candidates (Visual Search, browse, or Search API on tags and captions), scores them, adapts near-misses with generative AI edits, generates new images when needed, and self-checks the rendered page. Marked internal while in progress. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Always ask for write permission before editing, generating, or saving - Treat empty Visual Search results as unavailable - Add a generation budget check using limits.addons_quota - Send accepted images with fixable flaws (logos, mismatched backgrounds) to step 6 - Guide resolution choice for wide slots - Self-check over local HTTP, not file://, at desktop and phone widths - Browse small scopes with contact sheets Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Record each aspect ratio a slot uses across breakpoints, and deliver a separate g_auto crop per ratio with picture/source instead of relying on CSS object-fit center cropping, which cut the subject out of a phone hero in testing. Check crops at desktop and phone width. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generate one reference image for a set of similar slots, then make the rest with image_to_image using it as the reference. In testing this kept product cards consistent and cost far less per image than text_to_image. Also tell agents to read used_by_request rather than assume a fixed cost. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Ask whether to label AI-generated and AI-edited images. If yes, upload the four AI label variants when missing, pick one per crop from the brightness and busyness of its bottom-right corner, and apply it as a conditional overlay on cld_ai_generated after the crop. Always save AI images with ai_generated=true so the flag is set, and mention the disclosure in alt text. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A 4K hero cost 19 Image Generation units in testing. Generate wide images at 2K instead, and when upscaling with e_upscale (always 4x), follow it with c_limit at the slot's minimum source size before saving. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Member
|
should this skill suggest installing and configuring the cloudinary mcp / plugin in order to get access to the account via OAUTH rather than requiring apikey/secret? |
Collaborator
Author
Thanks for asking, @ranrub . Yes, we can certainly do that. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds
cloudinary-image-picker, a new use-case skill built at the hackathon. It picks images for every image slot on a website from a Cloudinary product environment, and edits or generates images when nothing in the library fits.It triggers when an agent builds a website that needs images, fills empty or placeholder image slots, or refreshes existing images (for example, a seasonal hero).
What the skill does
image_to_image).c_limit, and makes matching sets from one reference image.ai_generated=true, and optionally adds a conditional "AI" label overlay, choosing one of four versions per crop.f_auto/q_auto, a 2xsrcset, and separateg_autocrops per breakpoint.Testing
Tested on a claimable cloud seeded with 80 random CC0 images from the demo account, in three scenarios:
Each run's findings fed back into the skill, from version 0.1.0 to 0.5.1.
Two scenarios weren't run, because the Image Generation quota ran out: a forced generation case, and a forced edit (generative fill and background replace) case.
Known limitations
image_to_imagevaried between runs (1 unit in one run, 6 in another), so the matching-set guidance may need apreference: economysetting.metadata.internal: trueis set, so the skill stays out of the default install until it's ready.🤖 Generated with Claude Code