Skip to content

RandallLiuXin/GodotMaker / skills/core/gm-asset

gm-asset

Verified

Asset stage manager. Reads current-tag ASSETS.md gaps, accepts user-provided assets, plans visual production units, dispatches asset-producer subagents, collects validated Asset Skill results, updates ASSETS.md directly, and emits minimal worker runtime snapshots from that one authority. Explicit invocation only - use /gm-asset.

references/asset-curation.md

View on GitHub
# Asset Curation Reference

Curation chooses visual candidates; it does not create a runtime authority.
The only runtime handoff is the validated Asset Skill result registered directly
into the matching rows of `ASSETS.md`.

## Curation records

Store optional candidate reports under `.godotmaker/asset-generation/curation/`.
Record candidate IDs, source images, selection state (`candidate`, `selected`,
`variant`, or `rejected`), and brief notes. Keep these reports as production
evidence only; no consumer resolves them.

## ASSETS.md handoff

Mark rows `generated` only when one complete request-owned output set has:

1. A passed result with every declared output present exactly once.
2. A matching `ASSETS.md` row for every logical output.
3. Existing project-local output files; runtime resources also load as their
   declared Godot type.
4. Curation that is selected when the family requires curation.

Use `tools/asset_result_registration.py` for the atomic update. If any output
is missing, duplicated, unknown, or invalid, leave every row unchanged.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexUnverifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall