eddmann/jeeves · Archived

skill-creator

Create or update skills. Use when designing, structuring, or packaging new skills with SKILL.md files.

First seen Jun 17, 2026

Installation

$ npx skills add eddmann/jeeves --skill skill-creator

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from eddmann/jeeves.

npx skills add eddmann/jeeves

Browse all from eddmann/jeeves

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 2
License LICENSE
Default branch main
Open issues 0
Status Archived

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,219 B
  • docs SUMMARY.md 123 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

Skill Creator

Create new skills by writing SKILL.md files to the workspace skills/ directory.

Skill Structure

skill-name/
├── SKILL.md (required)
└── references/ (optional)

Creating a Skill

  1. Choose a name: lowercase letters, digits, and hyphens only (max 64 chars)
  2. Create directory: workspace/skills/<skill-name>/
  3. Write SKILL.md with YAML frontmatter

SKILL.md Format

---
name: my-skill
description: What this skill does and when to use it
---

# My Skill

Instructions for using this skill...

Frontmatter Fields

  • name (required): Must match the directory name, lowercase [a-z0-9-]
  • description (required): Clear description of what the skill does AND when to trigger it

Guidelines

  • Keep SKILL.md under 500 lines
  • Be concise — the context window is shared
  • Include examples over verbose explanations
  • Only add information the agent doesn't already know
  • Split large reference material into references/*.md files
  • Don't create README.md, CHANGELOG.md, or other auxiliary files