agentsclimarketplace

010104 skill creator

Skill natuleadan/skills/skills/010104-skill-creator

Multi-domain agent skills collection for AI coding agents (Claude, Cursor, Copilot, OpenCode, and more). Covers programming, biology, cooking, and future domains. Installable via npx skills add.

Install
npx -y skills add natuleadan/skills --skill 010104-skill-creator

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Creates AI agent skills from scratch — SKILL.md frontmatter, directory structure, progressive disclosure, evals, and distribution.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.3 KB, as published. Nobody here has run it

Skill Creator Guide

This skill teaches you how to create, test, package, and distribute AI agent skills following the standard Agent Skills format.

How to use this skill

  1. If the user asks about basic concepts or structure → read references/structure.md
  2. If the user asks about frontmatter or description → read references/frontmatter.md
  3. If the user asks about writing style or patterns → read references/writing.md
  4. If the user asks about testing, evals, or iteration → read references/testing.md
  5. If the user asks about packaging or distribution → read references/distribution.md
  6. If the user asks about repo architecture or marketplace → read references/repo-architecture.md
  7. If the user asks to scaffold a new skill → run python scripts/scaffold.py <skill-name> --category <category/subcategory>

Quick reference checklist

  • Choose a kebab-case name matching the directory (max 64 chars, lowercase + hyphens only)
  • Write frontmatter with name and description (include trigger contexts, desc ≤ 1024)
  • Optionally add compatibility (≤ 500 chars), license, metadata, allowed-tools
  • Keep SKILL.md under 100 lines — use references/ for detailed content
  • Write in imperative tone, explain the why, include examples
  • Add at least one Python script to scripts/ (no external deps)
  • Create evals/evals.json with test prompts
  • Run validation: python3 tools/validate-all.py from repo root

References

  • references/structure.md — Directory layout, progressive disclosure, size limits
  • references/frontmatter.md — Name rules, description rules, optimization
  • references/writing.md — Tone, examples, explaining reasoning, keeping lean
  • references/testing.md — Evals, assertions, grading, benchmarking, iteration
  • references/distribution.md — Marketplace.json, packaging, install
  • references/repo-architecture.md — Multi-category repo structure, validate-all.py, hierarchy
  • scripts/scaffold.py — Creates a new skill skeleton with --category support

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.