create-skill

A command for creating a new Claude Code skill from a name, purpose, and optional documentation links. A skill is a reusable set of instructions for an AI coding agent.

In plain words
What is it for?
Use it to define a skill name and purpose, optionally research its documentation sources, and generate the new skill.
Why use it?
It turns a short description into a structured skill while using supplied documentation to guide its design.

Command for Claude Code

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/nodnarbnitram/claude-code-extensions/create-skill
Clone the repo
git clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensions

Made for: Claude Code.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,525 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 $0.00009 $0.01525
Opus 5 $0.00005 $0.00763
Sonnet 5 $0.00002 $0.00305
Haiku 4.5 $0.00001 $0.00153

Measured 2d ago against content hash 03a3c9cd8fbe, 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.

.claude/commands/create-skill.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create New Skill

You will create a new skill for Claude Code based on the provided name, description, and optional documentation URLs.

Arguments: $ARGUMENTS

Important:

  • First argument: skill name (kebab-case)
  • Second argument: description/purpose (in quotes)
  • Remaining arguments (optional): documentation URLs to analyze

Your Task

Follow these steps to create the skill:

Step 1: Parse Arguments

Extract from $ARGUMENTS:

  • Skill Name: The first argument (kebab-case identifier, e.g., pdf-processor)
  • Description/Purpose: The second argument (in quotes) describing what the skill does
  • Documentation URLs: Any remaining arguments (optional)

Examples:

  • /create-skill pdf-processor "Extract text and tables from PDF files"
  • /create-skill temporal-workflow "Build durable workflows" https://docs.temporal.io https://typescript.temporal.io

Step 2: Gather Context

If documentation URLs were provided: Launch technical-researcher agents in parallel (one per URL) to analyze the documentation. Each researcher should investigate:

  • Key concepts, APIs, and patterns relevant to the skill's purpose
  • Best practices and conventions
  • Common workflows and use cases
  • Important implementation details
  • Configuration examples and templates that should be bundled

IMPORTANT: Do NOT use WebFetch directly. Always use the technical-researcher agent to ensure comprehensive analysis and proper extraction of reusable content.

If NO documentation URLs were provided: Use the AskUserQuestion tool to gather more information. Ask about:

  • What specific problem does this skill solve?
  • Are there documentation URLs or references to analyze?
  • What tools will the skill need access to? (Read-only? Bash access?)
  • What are the key workflows and steps?
  • What trigger keywords should activate this skill?

Adapt questions based on the description provided - skip questions that are already answered.

Step 3: Copy Skeleton Template

Read the full file on GitHub · 181 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 · 181 lines · 9 tokens per session scan A 03a3c9cd8fbe

Subscribe to this mod's changes

create-skill is a command published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 1,525 once invoked, about $0.0000 per session on Opus 5. 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 2026-08-30.