agentleFS
mazreanmazrean/agent-skills/skills/creating-agent-skills/SKILL.md

creating-agent-skills

Skill2 starsChanged 8 months agoMITView on GitHub

Creates well-structured Agent Skills following best practices. Use when building new skills for Claude Code, designing skill directory structures, writing SKILL.md files, or improving existing skills with progressive disclosure patterns.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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 skill directory with SKILL.md:

    line 16
  2. Distinctive:

    Use gerund form (verb + -ing) for clarity:

    line 50
  3. Very specific:

    No consecutive hyphens (--)

    line 57
  4. Very specific:

    Keep SKILL.md under 500 lines.

    line 81
  5. Distinctive:

    Avoid time-sensitive info: Use "old patterns" sections instead

    line 101
  6. Distinctive:

    Before finalizing a skill:

    line 105

≈ “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

Creating Agent Skills

Agent Skills extend Claude's capabilities with specialized knowledge and workflows. This skill helps you create effective skills that follow best practices.

Use this skill when creating new skills, improving existing ones, or designing skill architecture for projects.

Supporting files: SPECIFICATION.md for format details, BEST-PRACTICES.md for authoring guidelines, TEMPLATES.md for starter templates.

Quick Start

Create a skill directory with SKILL.md:

my-skill/
├── SKILL.md          # Required: metadata + instructions
├── scripts/          # Optional: executable code
├── references/       # Optional: detailed docs
└── assets/           # Optional: templates, resources

SKILL.md Structure

---
name: skill-name          # lowercase, hyphens only, max 64 chars
description: What it does and when to use it.  # max 1024 chars
---

# Skill Title

Brief intro and "Use this skill when..." statement.

## Quick Start
[Most common use case with example]

## Core Features
[Main capabilities organized by task]

## Support Files
[Links to reference files for detailed info]

Naming Conventions

Use gerund form (verb + -ing) for clarity:

  • processing-pdfs (preferred)
  • analyzing-data (preferred)
  • pdf-processor (acceptable)

Rules:

  • Lowercase letters, numbers, hyphens only
  • No consecutive hyphens (--)
  • Cannot start/end with hyphen
  • Max 64 characters

Writing Descriptions

Descriptions drive skill discovery. Include:

  1. What it does (actions/capabilities)
  2. When to use it (triggers/contexts)

Good:

description: Extracts text and tables from PDF files, fills forms, merges documents. Use when working with PDF files or when user mentions PDFs, forms, or document extraction.

Bad:

description: Helps with PDFs.  # Too vague

Always use third person (description is injected into system prompt).

Progressive Disclosure

Keep SKILL.md under 500 lines. Split content strategically:

  1. Metadata (~100 tokens): Loaded at startup for all skills
  2. SKILL.md body (<5000 tokens): Loaded when skill activates
  3. Reference files: Loaded only when needed
## Detailed Topics

**Form filling**: See [FORMS.md](references/FORMS.md)
**API reference**: See [REFERENCE.md](references/REFERENCE.md)
**Examples**: See [EXAMPLES.md](references/EXAMPLES.md)

Key Principles

  1. Be concise: Claude is smart; only add context it doesn't have
  2. Test with all models: What works for Opus may need detail for Haiku
  3. Use workflows: Break complex tasks into clear, sequential steps
  4. Include feedback loops: Validate → fix → repeat for quality
  5. Avoid time-sensitive info: Use "old patterns" sections instead

Checklist

Before finalizing a skill:

  • Name uses lowercase/hyphens, matches directory name
  • Description explains what AND when
  • SKILL.md under 500 lines
  • Reference files for detailed content
  • Examples are concrete, not abstract
  • Tested with real usage scenarios

Resources

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.