Skills

Unity Agent Workflows

Use for AI-assisted Unity work that needs live repo discovery, project-derived routing...

Install

npx skills add hashgraph-online/awesome-codex-plugins --skill unity-agent-workflows -g -a claude-code -y
Category
Design
Updated
3d ago
License
MIT
Context cost
Mediumabout 3,000 tokens
Runs scripts
No, instructions only

What it does

Use for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first content changes, validation, cleanup proof, or durable workflow rules. Best when agents must prove the actual folder/module/scene/prefab/runtime owner before editing, especially runtime UI, generated assets, code graphs, tutorial/state flows, guided selection/action flows, overlay/dim source-bound mistakes, coordinate conversions, focus/highlight/marker/HUD alignment, predictive lead aiming, ballistic trajectories, spatial IoU verification, or repeated "fix still not visible" failures.

Unity Agent Workflows

AI contract for Unity work. Keep answers compact, but never remove exact paths, object/class names, commands, errors, validation, rollback notes, or proof requirements.

Core Loop

  1. No proof, no edit.
  2. Treat this injected SKILL.md as authoritative; do not search for its own path unless missing or asked for diagnostics.
  3. Read live project instructions narrowly: AGENTS.md if present, git status --short, and existing UNITY_STRUCTURE.md plus only the focused map that matches the task when available. Read README.md, architecture docs, .agents/*, or repo-local agent files only when the task cites them, needs architecture/new-file/asmdef/routing decisions, or maps are missing/stale.
  4. Run git status --short; preserve unrelated dirty files.
  5. If user says only $unity-agent-workflows. Teach, run Teach.
  6. Derive only relevant live structure before architecture claims: folders, namespaces, .asmdef, scenes/prefabs, bootstraps, graphs, docs, UNITY_STRUCTURE*.
  7. Classify task with Task Gate, then load required references before edits.
  8. Inspect real owner files; never start from memory, nearest-name guessing, semantic similarity, or screenshot proximity alone.
  9. Fill useful Routing Card fields for structure, visible output, state flow, multi-agent, or hub changes.
  10. Patch the smallest proven owner/artifact.
  11. Validate, sync mirrors if package skill files changed, then close out with proof.

Task Gate

Read the whole SKILL.md on GitHub

More in Design