What is create-skill?

A command for creating a coding-agent skill, which is a reusable set of instructions and supporting files. It guides the work from requirements through validation and cleanup.

Use it to start a new skill, decide whether it needs scripts, reference documents, or assets, and check the result before using it.

It gives skill creation a repeatable structure and helps avoid incomplete instructions, poorly organized files, and formatting errors.

create-skill — Command for Claude Code by georgekhananaev

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/georgekhananaev/claude-skills-vault

agentmods

npx agentmods add commands/georgekhananaev/claude-skills-vault/create-skill

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/georgekhananaev/claude-skills-vault/create-skill/github.svg)](https://agentmods.dev/commands/georgekhananaev/claude-skills-vault/create-skill)

Your own site

<a href="https://agentmods.dev/commands/georgekhananaev/claude-skills-vault/create-skill"><img src="https://agentmods.dev/badge/commands/georgekhananaev/claude-skills-vault/create-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/georgekhananaev/claude-skills-vault/create-skill"><img src="https://agentmods.dev/badge/commands/georgekhananaev/claude-skills-vault/create-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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 1,537 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01537
Opus 5	$0.00000	$0.00768
Sonnet 5	$0.00000	$0.00307
Haiku 4.5	$0.00000	$0.00154

Measured 11d ago against content hash 9c4567a42dcf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

create-skill scanned grade A with 1 finding 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 11d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

result = subprocess.run(

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

create-skill — 100% identical, 0 lines differ

.claude/commands/create-skill.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Skill Command

Goal: Create production-ready skills w/ validation, testing & optimization.

1. Required Skills

Use these skills during creation:

Skill	Path	Purpose
`skill-creator`	`.claude/skills/skill-creator/`	Core creation workflow
`token-formatter`	`.claude/skills/token-formatter/`	Compress SKILL.md content
`md`	`.claude/skills/document-skills/md/`	Clean markdown w/o errors

2. Creation Flow

Step 1: Understand Requirements

Ask user:

"What should this skill do?"
"Example usage scenarios?"
"Any scripts/assets needed?"

Step 2: Init Skill

python scripts/init_skill.py <skill-name> --path .claude/skills/<skill-name>

Creates:

skill-name/
├── SKILL.md
├── scripts/
├── references/
└── assets/

Step 3: Plan Resources

Analyze examples → identify:

Resource	When
`scripts/`	Repeated code, deterministic tasks
`references/`	Docs, schemas, API specs
`assets/`	Templates, images, fonts

Step 4: Write Content

SKILL.md rules:

YAML frontmatter: name & description (req)
Imperative form ("To do X" not "You should")
Keep lean → move details to references/
Apply token-formatter compression

Writing style:

# Skill Name

Brief purpose (1-2 sentences).

## When to Use

Invoke when:
- Condition 1
- Condition 2

## Process

1. Step one
2. Step two

Step 5: Optimize

Apply token-formatter:

Abbreviations: fn, str, num, config, auth, db, etc.
Remove filler words
Compress tables & lists
Use symbols: →, |, &, w/, w/o

Apply md skill:

Proper fence nesting (use ```` for outer)
Match opening/closing fences
Escape | in tables
Consistent list indentation
Blank lines around code blocks

3. Testing (REQUIRED)

Test Location

tests/<skill-name>/
├── test_*.py          # Python tests
├── test_*.sh          # Bash tests
├── fixtures/          # Test data
└── expected/          # Expected outputs

Read the full file on GitHub · 252 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.

11d ago First seen · 252 lines · 0 tokens per session scan A 9c4567a42dcf

Subscribe to this mod's changes

create-skill is a command published in the GitHub repository georgekhananaev/claude-skills-vault (28 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,537 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Claude Code claude claude-commands claude-mcp claude-skills claude-skills-hub

create-skill