agentleFS
Faaz17Faaz17/Agents-and-Skills/skills/unity/new-script/SKILL.md

new-script

Skill1 starsChanged 2 months agoMITView on GitHub

Scaffold a new Unity C# script under unity/Assets/Scripts/ following the project's conventions (SerializeField, headers, no per-frame allocations), and explain exactly which GameObject to attach it to. Use when creating any new MonoBehaviour, ScriptableObject, or utility class.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create a new C# script that follows .claude/rules/tech_defaults.md exactly, and — because the user is a Unity beginner — always explain …

    line 8
  2. Distinctive:

    Ask (or infer from context): class name, feature area (Flood / Weather / XR / UI), and what it should do.

    line 12
  3. Very specific:

    Create the file at unity/Assets/Scripts/<Feature>/<ClassName>.cs.

    line 14
  4. Distinctive:

    Follow the template and conventions below.

    line 15
  5. Very specific:

    No magic numbers — extract to a serialized field or const.

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

/new-script — Unity C# Script Scaffold

Create a new C# script that follows .claude/rules/tech_defaults.md exactly, and — because the user is a Unity beginner — always explain where it goes and how to wire it up.

Steps

  1. Ask (or infer from context): class name, feature area (Flood / Weather / XR / UI), and what it should do.
  2. Confirm the Unity project exists (unity/Assets/ present). If not, stop — scripts have nowhere to live before Phase 0's Unity project is created.
  3. Create the file at unity/Assets/Scripts/<Feature>/<ClassName>.cs. Filename must match the class name.
  4. Follow the template and conventions below.
  5. Tell the user, step by step: which GameObject to attach it to, which Inspector fields to fill in, and what they should see when they press Play (the eye-verification step).

Template

using System.Collections;

using UnityEngine;

/// <summary>
/// One sentence: what this component does and what it attaches to.
/// </summary>
public class ClassName : MonoBehaviour
{
    [Header("Settings")]
    [SerializeField] private float exampleValue = 1f;

    [Header("References")]
    [SerializeField] private Transform exampleTarget;

    private void Awake()
    {
        // Cache components here — never GetComponent<X>() in Update().
    }

    private void Update()
    {
        // No allocations here: no `new`, no LINQ, no string concat, no Find().
    }
}

Convention checklist (enforce all of these)

  • [SerializeField] private for Inspector-exposed fields — never bare public fields.
  • PascalCase class/methods, camelCase fields. One class per file.
  • using groups: System / UnityEngine / third-party / project — blank-line separated.
  • [Header("...")] groups in the Inspector.
  • No magic numbers — extract to a serialized field or const.
  • Coroutines need using System.Collections; (IEnumerator, non-generic).
  • Event subscriptions in Awake()/OnEnable() get mirrored unsubscriptions in OnDestroy()/OnDisable().
  • Network calls (Phase 4): coroutine + UnityWebRequest, never blocking the main thread.

After creating

Remind the user: a script does nothing until attached to a GameObject — and the scene must be saved (Ctrl+S) afterwards.

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.