Skip to content
cccskills
FreePublished on GitHub

agent-skill

Create and structure Claude Code agent skills. Use when the user wants to create a new skill, write an agent skill, make a claude skill, or asks about SKILL.md files.

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md4.0 KB
  • metadata.json1.4 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Agent Skill Creator

Help users create well-structured Claude Code skills through an interactive process.

Workflow

Step 1: Ask about location first

Before anything else, ask where the skill should be created:

  • Personal (~/.claude/skills/): Available across all projects for this user
  • Project (./.claude/skills/): Shared with team via version control

Use the AskUserQuestion tool for this.

Step 2: Gather requirements through questions

Ask about each of these in sequence:

  1. Skill name: What should the skill be called?

    • Must be lowercase letters, numbers, and hyphens only
    • Maximum 64 characters
    • Examples: code-review, api-docs, test-generator
  2. Purpose: What does this skill help with?

    • What specific task or capability does it provide?
    • What problem does it solve?
  3. Trigger phrases: When should this skill activate?

    • What words would users say when they need this skill?
    • Be specific about scenarios (not vague like "helps with code")
  4. Key instructions: What should Claude do when this skill is active?

    • Step-by-step process
    • Required outputs or formats
    • Constraints or rules to follow
  5. Tool restrictions: Should the skill limit available tools?

    • Full access (default): No restrictions
    • Read-only: Read, Grep, Glob
    • Write-focused: Read, Write, Edit, Glob, Grep
    • Custom: Specify exact tools
  6. Complexity: Will this skill need supporting files?

    • Simple: Single SKILL.md under 500 lines
    • Complex: Multiple files with progressive disclosure

Step 3: Generate the skill

Create the skill file at the chosen location:

  • Personal: ~/.claude/skills/{skill-name}/SKILL.md
  • Project: ./.claude/skills/{skill-name}/SKILL.md

Skill File Structure

Required YAML frontmatter

---
name: skill-name-here
description: Clear description of what it does and when to use it. Include trigger keywords users would say. Max 1024 chars.
allowed-tools: Tool1, Tool2  # Optional - omit for full access
model: claude-sonnet-4-20250514  # Optional - only if specific model needed
---

Instruction sections

After frontmatter, include:

  1. Title: # Skill Name
  2. Overview: Brief explanation of what the skill does
  3. Instructions: Clear, numbered steps for Claude to follow
  4. Examples (optional): Concrete usage examples
  5. References (if multi-file): Links to supporting files

Writing effective descriptions

The description determines when Claude activates the skill. It uses semantic matching.

Bad: "Helps with documents" Good: "Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDFs or when the user mentions document extraction."

Include:

  • Specific capabilities (verbs: extract, generate, review, format)
  • Trigger keywords users would naturally say
  • Clear "use when" guidance

Multi-file structure

For complex skills, keep SKILL.md under 500 lines and link to supporting files:

skill-name/
├── SKILL.md         # Overview and navigation
├── reference.md     # Detailed documentation
├── examples.md      # Usage examples
└── scripts/         # Utility scripts (executed, not loaded)
    └── helper.py

Key rules:

  • Keep references one level deep (no A -> B -> C chains)
  • Scripts execute without loading into context
  • Claude reads supporting files only when needed

Example skills

See examples.md for reference examples of well-structured skills.

Quality checklist

Before finalizing, verify:

  • Name is lowercase with hyphens only
  • Description includes trigger keywords
  • Description explains when to use it
  • Instructions are clear and actionable
  • Tool restrictions match the skill's purpose
  • SKILL.md stays under 500 lines
  • Supporting files are one level deep only

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

[00] TnR ABSOLUTE RIGOR — Systemic Verification Doctrine. Forced cognitive exertion for high-stakes investigations. Mandates absolute deconstruction, mathematical proof chains, and ≥95% derived certainty. Zero-tolerance for heuristics or sentiment-based reasoning. Shortcuts are defined as intentional hallucinations.

The English summary is being prepared. Showing the original description.

diegosouzapw/awesome-omni-skill64Updated Mar 2, 2026

2agent

Free

Configures 2-Agent workflow between PM and implementation roles. Use when user mentions 2-Agent, 2エージェント, PM連携設定, Cursor設定, Cursor連携, 2-agent運用. Do NOT load for: 単独運用, ワークフロー実行, ハンドオフ処理.

The English summary is being prepared. Showing the original description.

diegosouzapw/awesome-omni-skill64Updated Mar 2, 2026

Appends relevant hashtags to journal entries based on content analysis. Intended for LLM execution.

The English summary is being prepared. Showing the original description.

diegosouzapw/awesome-omni-skill64Updated Mar 2, 2026

Add a new AI coding agent to Agent Sandbox. Creates all required files (Dockerfile, templates, CI, docs) and wires the agent into the CLI, proxy, and build system.

The English summary is being prepared. Showing the original description.

diegosouzapw/awesome-omni-skill64Updated Mar 2, 2026

Add a new property to the AI agents database. Use when the user wants to add, create, or introduce a new column, property, field, or feature to track across all agents in the comparison matrix. Handles all four required steps - database updates, groups.json, table display, and GitHub issue templates.

The English summary is being prepared. Showing the original description.

diegosouzapw/awesome-omni-skill64Updated Mar 2, 2026

Add new Agent templates to the meta-agent-skills framework.

The English summary is being prepared. Showing the original description.

diegosouzapw/awesome-omni-skill64Updated Mar 2, 2026

See all skills by diegosouzapw

Report a problem with this skill