@W-21860796 Adds media-management skill#211
Open
udaiarora wants to merge 4 commits intoforcedotcom:mainfrom
Open
@W-21860796 Adds media-management skill#211udaiarora wants to merge 4 commits intoforcedotcom:mainfrom
udaiarora wants to merge 4 commits intoforcedotcom:mainfrom
Conversation
| **2. Download the image:** | ||
| ```bash | ||
| mkdir -p "generatedimages" | ||
| curl -f -H "Authorization: Bearer $ACCESS_TOKEN" "$URL" -o "generatedimages/<responseId>.<outputFormat>" |
Contributor
There was a problem hiding this comment.
How are you expecting $ACCESS_TOKEN will be resolved? there is no explicit instructions.
| **2. Download the image:** | ||
| ```bash | ||
| mkdir -p "generatedimages" | ||
| curl -f -H "Authorization: Bearer $ACCESS_TOKEN" "$URL" -o "generatedimages/<responseId>.<outputFormat>" |
Contributor
There was a problem hiding this comment.
What happens if this curl command fails?
| If image generation fails or is not enabled, return the following URL as the image source — do not download it, do not save it locally: | ||
|
|
||
| ``` | ||
| https://cdn.scs.static.lightning.force.com/content/assets/d5222d4a11e6c2b735152d7eea824ce4/placeholder.svg |
Contributor
There was a problem hiding this comment.
I believe that since this workflow involves resolving the access token, downloading, error handling, and fetching from external APIs, it is a good use case for using scripts/ rather than mentioning everything in SKILL.md
Treat SKILL as a workflow only, and delegate the detailing to Script. It saves token as well.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
References: Contributing guide · Skill authoring guide · Agent Skills spec
What changed
Added a new skill that instructs the agent to generate images via an MCP create_image tool, with configurable parameters for model, size, quality, and format. If image generation is unavailable, it falls back to a single shared placeholder downloaded from a CDN.
Why
For use in vibes. See @W-21860796
Notes
Skills
Manual checklist
Description quality
Instructions
Context efficiency
templates/,examples/, ordocs/subdirectoriesAutomated checks
Enforced by CI (
npm run validate:skills) per the Agent Skills spec:SKILL.mdnamematches directory name;descriptionis present, ≥ 20 words, ≤ 1024 characters, and includes trigger language