Repository navigation
Add a game artwork integration workflow and REA companion example - #15
Merged
Merged
Conversation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add
integrate-game-artto the existing canonical skills so an agent can turn a game's asset requirements into a budgeted generation plan, recover saved jobs, validate images, and import them without changing gameplay. REA investigation remains an optional companion reference. The runnable Relay garden example now includes an original DreamLayer environment and six matching game objects, generated in three completed operations for three credits.The workflow reuses the existing contracts, keeps collision dimensions independent of textures, and distinguishes reused outputs from paid generation. All three host copies and the downloadable skills package are synchronized. ClawHub source and client workflow tables route to the skill; no registry publication or indexing is claimed.
Validation: ten skills pass packaging/parity validation; nine existing Python tests passed for the workflow implementation; skill-creator validation passed. The refreshed commit was installed from GitHub with skills 1.7.2 into a clean Codex project, discovered by its skill listing, and compared byte for byte with the canonical skill and references. Other agent hosts were not exercised. The example passes eight Node tests, including 2,000 numeric artifact comparisons, ten asset digests, decoded transparency, and a complete public Chrome playthrough with patrols, pulse, win/replay and reduced motion.