agentleFS
jame581jame581/GodotPrompter/.claude/skills/authoring-godot-prompter-skills/SKILL.md

authoring-godot-prompter-skills

Skill965 starsChanged 27 days agoMITView on GitHub

Use when writing or editing a SKILL.md, a skill's references/*.md, or an agent definition in this repo — required frontmatter, section ordering, the GDScript-then-C# example convention, and C# parity exemptions.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every skill must start with YAML frontmatter:

    line 13
  2. Distinctive:

    When a section genuinely cannot have a C# counterpart, mark that section — never the whole skill:

    line 33
  3. Very specific:

    Run node scripts/validate-skills.mjs — it enforces frontmatter, cross-references, and the 16 KB size budget.

    line 60

≈ “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

Authoring GodotPrompter skills and agents

File format templates for this repo. See the root CLAUDE.md for the conventions and size budget that govern the content itself.

SKILL.md format

Every skill must start with YAML frontmatter:

---
name: skill-name
description: Use when [trigger] — [brief scope]
---

Followed by:

  1. Title and intro
  2. Related skills line: > **Related skills:** **skill-a** for X, **skill-b** for Y.
  3. Numbered sections with patterns and examples
  4. GDScript first, then C# equivalent (use gdscript and csharp language tags)
  5. Implementation checklist at the end

C# parity

The validator also checks C# parity inside references/*.md (csharp-parity-*-reference), so Pattern X moves stay enforced. Files that section by language (## C#, ## Dash (C#), ### … — C#) are checked file-level instead of per-section; a heading that merely mentions C# in prose is not a partition.

When a section genuinely cannot have a C# counterpart, mark that section — never the whole skill:

<!-- csharp-parity: n/a — C# is statically typed; there is no untyped alternative to contrast -->

It works in both SKILL.md and references/*.md. The reason is mandatory; omitting it is an error (checked on every marker, not only on sections missing C#), because an exemption that cannot say why is indistinguishable from an example nobody wrote. A reason may contain < and >, and a marker inside a fenced block is ignored, so a file can document the marker without exempting itself.

Do not reach for the two blunter tools instead: adding the skill to GDSCRIPT_ONLY_BY_DESIGN exempts every section in it, and renaming a heading to "… (GDScript)" trips the language-partition check and silently downgrades the entire file to a file-level check. Both hide real gaps in neighbouring sections.

A fenced ```gdscript block containing only comments is not a code example — it is prose in a fence, and it will be flagged as an unpaired GDScript block. Write it as prose or a bullet list.

Agent format

Agent definitions in agents/<name>.md use YAML frontmatter:

---
name: agent-name
description: |
  When to use, with <example> blocks.
model: inherit
---

Before you finish

Run node scripts/validate-skills.mjs — it enforces frontmatter, cross-references, and the 16 KB size budget.

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.