agentleFS
ShiningPlagueShiningPlague/shiningplague-studio/skills/setup-engine/SKILL.md

setup-engine

Skill0 starsChanged 4 months agoMITView on GitHub

Use when setting up the engine for a new project or reconfiguring engine settings. Populates technical-preferences.md, validates project.godot, and ensures engine reference docs exist. ShiningPlague-adopted: full implementation with engine-version validation and autoload registry coverage check.

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use soak-test, team-live-ops and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • lilangMaxSkill

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 8 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 8 projects that use this

  • +1 more from lilangMax

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Read project.godot → config/features for engine version

    line 29
  2. Very specific:

    If docs/engine-reference/<engine>/VERSION.md is absent, offer to create the folder and seed VERSION.md with: engine name, exact pinned …

    line 41
  3. Distinctive:

    If the designer declines, say so plainly and move on.

    line 49
  4. Very specific:

    Read .claude/docs/technical-preferences.md.

    line 53
  5. Distinctive:

    Check that the expected directory structure exists:

    line 64
  6. Very specific:

    Read project.godot autoloads section

    line 70
  7. Distinctive:

    After initial setup, re-run only if the engine version changes or project.godot drifts.

    line 78

“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “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

Setup Engine

🌱 ShiningPlague-adopted. Originally Donchitos (barebones stub); battle-tested on a shipped Godot project. Upstream was a pointer-only file; this version is the full implementation — engine version validation, technical-preferences.md check, project structure check, autoload coverage.

Engine configuration and validation for {{ENGINE_VERSION}}. Run at project setup; this skill formalises the process for reproducibility.

If an artifact named here is absent: say so plainly in one line, skip that step, and continue. Never invent the file to satisfy a checklist, and never fail a close because an optional artifact was never created.

Procedure

1. Verify Engine Version

  • Read project.godot → config/features for engine version
  • Cross-check .claude/docs/technical-preferences.md → engine version field
  • Cross-check docs/engine-reference/<engine>/VERSION.md if the project has one (see step 2 -- the template never ships this library)
  • Flag any version mismatches

2. Establish the engine reference library

docs/engine-reference/<engine>/ is the project's pinned-version knowledge base: what the engine actually does in the version this project ships on, which beats a model's training data whenever the two disagree. The template never ships it -- it is engine- and version-specific, so it can only be written per project.

  • If docs/engine-reference/<engine>/VERSION.md is absent, offer to create the folder and seed VERSION.md with: engine name, exact pinned version, the release date, and a one-line note on which parts of that version post-date the model's training data.
  • Offer three companion notes alongside it, created empty and filled in as the project hits each issue: deprecated-apis.md, breaking-changes.md, current-best-practices.md. A modules/ subfolder holds per-domain notes under docs/engine-reference/<engine>/modules/, added the same way.
  • If the designer declines, say so plainly and move on. The library is optional: every skill and agent that reads it must degrade when it is absent.

3. Validate technical-preferences.md

Read .claude/docs/technical-preferences.md. All fields must be populated:

  • Engine + version
  • Language (GDScript)
  • Architecture patterns (singleton autoloads, signals, resources)
  • Naming conventions
  • Testing approach
  • Performance targets

Flag any blank fields.

4. Validate Project Structure

Check that the expected directory structure exists:

  • src/ (scripts), scenes/ (tscn), data/ (JSON content)
  • data/_schemas/ (schemas), addons/ (editor plugins)
  • docs/ (documentation), production/ (PM state)

5. Validate Autoloads

  • Read project.godot autoloads section
  • Cross-check each against data/_schemas/system_registry.json
  • Flag any autoload not in registry (registry coverage check)

6. Output

Report: engine health status, any mismatches or missing config.

Re-Run Guidance

After initial setup, re-run only if the engine version changes or project.godot drifts.

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.