Add openai-ads domain skill; fill uploads interaction skill stub - #565
Open
CrestViewFl wants to merge 1 commit into
Open
Add openai-ads domain skill; fill uploads interaction skill stub#565CrestViewFl wants to merge 1 commit into
CrestViewFl wants to merge 1 commit into
Conversation
- domain-skills/openai-ads/ads-manager.md: campaign/ad-group/ad structure, create flows, placeholder-based field location, the stuck image-attachment trap (remove X to reveal the real file input), async skeleton statuses. - interaction-skills/uploads.md: was an empty stub; document the three-tier upload approach (existing file input, setInterceptFileChooserDialog + fileChooserOpened backendNodeId, stuck-preview removal).
✅ Skill review passedReviewed 2 file(s) — no findings. |
Kastan97
reviewed
Jul 28, 2026
Kastan97
left a comment
There was a problem hiding this comment.
Ollie (CTO) Review: APPROVED ✅
What this does: Adds an OpenAI Ads Manager domain skill (44 lines) documenting the campaign/ad-group/ad structure, create flows, field locators, and the grey image-tile upload trap. Also fills the uploads interaction skill stub (23 lines) with a three-tier upload approach using CDP APIs.
Assessment: Clean, field-tested documentation. No code changes. The image-tile trap documentation is genuinely valuable — saves agents from repeating probe rounds. No secrets or account identifiers included.
Good to merge.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
input[type=file]viaDOM.setFileInputFiles, dynamic inputs viaPage.setInterceptFileChooserDialog+fileChooserOpened→backendNodeId, and the stuck-preview case that reveals an input after removal.Why
Learned while publishing a real campaign end to end (campaign → ad group → ad → image upload → publish → serving). The image-upload trap alone cost several probe rounds; the next agent should not pay that tax.
No secrets, account ids, or pixel coordinates included.
🤖 Generated with Claude Code
Summary by cubic
Adds an OpenAI Ads Manager domain skill and a reliable file upload flow. This helps agents create and publish ads and handle tricky image uploads on
ads.openai.com.domain-skills/openai-ads/ads-manager.md: structure (campaign → ad group → ad), create flows, field locators by placeholder/value, soft truncation warnings, async skeleton states, and fix for the stuck grey image tile (click X to reveal the real file input).interaction-skills/uploads.md: 3-step upload approach—(1) directinput[type=file]via CDPDOM.setFileInputFiles, (2) dynamic inputs viaPage.setInterceptFileChooserDialog+fileChooserOpenedbackendNodeId, (3) remove stale preview tiles when no chooser event; includes post-upload verification and drag-and-drop note.Written for commit 9745d40. Summary will update on new commits.