create-skill

A guided command for creating a Claude Code skill, which is a reusable set of instructions that teaches Claude how to handle a specific task. It follows Anthropic's documented skill structure.

In plain words
What is it for?
Collecting a skill's name, purpose, and installation scope, then preparing YAML metadata, instructions, resources, and scripts for a personal or project skill.
Why use it?
It helps create the required metadata, instructions, and optional supporting files without having to remember the format.

Command

Part of the claude-tools plugin — 12 commands, 46 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/rafaelkamimura/claude-tools/create-skill
Clone the repo
git clone --depth 1 https://github.com/rafaelkamimura/claude-tools

Or install claude-tools, the plugin that ships this one along with the rest of its 12 commands, 46 agents.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,396 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.03396
Opus 5 $0.00000 $0.01698
Sonnet 5 $0.00000 $0.00679
Haiku 4.5 $0.00000 $0.00340

Measured 2d ago against content hash d6052875d3a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/create-skill.md · 550 lines

How it starts

The opening of the file, as written. The whole thing — 550 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create New Claude Code Skill

Guides you through creating a new Claude Code skill following Anthropic's official skill structure and best practices.

Purpose

  • Create well-structured skills for Claude Code
  • Follow Anthropic's progressive disclosure pattern
  • Support both personal and project-specific skills
  • Generate proper YAML frontmatter and instructions
  • Include optional resources and scripts

Execution Steps

Step 1: Gather Skill Information

Output: "Let's create a new Claude Code skill!

What is the skill name? (max 64 characters, use kebab-case like 'api-builder' or 'data-analyzer'):"

WAIT for user's skill name input.

Store skill name as SKILL_NAME.

Output: "What does this skill do? Provide a complete description including what the skill does AND when Claude should use it (max 1024 characters):"

WAIT for user's description input.

Store description as SKILL_DESCRIPTION.

Step 2: Determine Skill Scope

Use AskUserQuestion tool:

  • question: "Where should this skill be installed? Personal skills are available globally across all projects. Project skills are specific to the current repository."
  • header: "Skill Scope"
  • multiSelect: false
  • options:
    1. label: "Personal (~/.claude/skills/)", description: "Available globally in all projects"
    2. label: "Project (.claude/skills/)", description: "Only available in current project"

If user chooses Personal:

  • Set SKILL_DIR to /Users/nagawa/.claude/skills/${SKILL_NAME}

If user chooses Project:

  • Use Bash tool to get current directory:
    • Command: pwd
    • Description: "Get current working directory"
  • Set SKILL_DIR to ${PWD}/.claude/skills/${SKILL_NAME}

Step 3: Check for Existing Skill

Use Bash tool to check if skill directory exists:

  • Command: test -d "${SKILL_DIR}" && echo "exists" || echo "new"
  • Description: "Check if skill directory already exists"

If result is "exists": Output: "Warning: Skill '${SKILL_NAME}' already exists at ${SKILL_DIR}. Overwrite? (yes/no):"

Read the full file on GitHub · 550 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 550 lines · 0 tokens per session scan A d6052875d3a5

Subscribe to this mod's changes

create-skill is a command published in the GitHub repository rafaelkamimura/claude-tools (10 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,396 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.