character-bundle

Solid

Produce one standalone character or skin SpriteFrames resource from a canonical reference and explicitly timed action frames.

AI & Automation 495 stars 43 forks Updated today NOASSERTION

Install

View on GitHub

Quality Score: 81/100

Stars 20%
90
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Character Bundle Use this skill for a player character, enemy, NPC, summon, boss, or other recurring creature identity. It produces one `SpriteFrames` resource for one actor or skin, containing every required named body action. Read `../_shared/asset-skill-contract.md` before accepting a request. First validate the shared request/result shape with `tools/asset_skill_contract_check.py`, then validate this family contract with `tools/asset_animated_bundle_contract_check.py --kind request`. For final runtime handoff, call the same checker with `--request <request.json> --result <result.json>`; a result-only check cannot prove it belongs to this request. Final handoff accepts only `validation.passed: true` with explicit passing `L0` through `L4` evidence. The family checker is the callable enforcement for the `spec` rules below; the shared checker alone intentionally validates only cross-family shape. ## Standalone boundary Accept only an asset request. Do not read or require `/gm-asset`, tags, stage state, `ASSETS.md`, generated manifests, stable entries, worker dispatch, or any other registration state. Return the shared asset result directly; a caller may register it separately. ## Request and action contract The request has `asset_type: "character-bundle"`. Its `spec` must contain: - `required_actions`: a non-empty, duplicate-free ordered list of action names. - `actions`: one object for each required action, with exactly the same names. - Each action has `name`, `fr...

Details

Author
RandallLiuXin
Repository
RandallLiuXin/GodotMaker
Created
3 months ago
Last Updated
today
Language
Python
License
NOASSERTION

Similar Skills

Semantically similar based on skill content — not just same category