agentleFS
YIMO691YIMO691/claude-skills-kit/.claude/skills/unity6-project/SKILL.md

unity6-project

Skill0 starsChanged 6 months agoMITView on GitHub

Unity 6 项目开发规则。Use when working on Unity 6 projects, Unity C# scripts, AI gameplay prototypes, NavMesh, Behavior/behavior trees, ML-Agents, Sentis/ONNX inference, Unity package setup, scenes, prefabs, tests, or Unity validation instructions.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read only what is needed:

    line 10
  2. Very specific:

    Use [SerializeField] private for Inspector parameters.

    line 30
  3. Distinctive:

    Put AI tuning values such as radius, speed, cooldown, and layer masks in Inspector.

    line 32
  4. Distinctive:

    Verify package names and versions from Package Manager, local manifest, or official docs.

    line 33
  5. Very specific:

    Do not commit Library/, Temp/, Logs/, training outputs, large generated assets, or user local settings.

    line 34
  6. Distinctive:

    Use Git LFS before committing large binary assets that must be versioned.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Unity 6 Project

First Reads

Read only what is needed:

  • CLAUDE.md for project rules.
  • README.md for setup and current scope.
  • ProjectSettings/ProjectVersion.txt for Unity version.
  • Packages/manifest.json when packages are involved.
  • project planning docs when milestones or learning goals matter.

Workflow

  1. Identify the active milestone or gameplay goal.
  2. State the smallest useful next step and acceptance check.
  3. Make scoped changes under the existing Unity project root.
  4. For scripts, prefer Assets/_Project/Scripts/ or the local project convention.
  5. For tests, prefer Assets/_Project/Tests/ or the local project convention.
  6. Explain Unity validation steps: scene, GameObject, components, Inspector values, Play/Test Runner checks.

Rules

  • Communicate in Chinese; keep C# identifiers in English.
  • Use [SerializeField] private for Inspector parameters.
  • Cache component references; avoid expensive lookup in Update().
  • Put AI tuning values such as radius, speed, cooldown, and layer masks in Inspector.
  • Verify package names and versions from Package Manager, local manifest, or official docs.
  • Do not commit Library/, Temp/, Logs/, training outputs, large generated assets, or user local settings.
  • Use Git LFS before committing large binary assets that must be versioned.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.