create-skill

create-skill is a command for Claude Code from j5ik2o/okite-ai. It costs 17 tokens per session (1,996 once invoked), scanned A, original, MIT.

A command for creating a project-specific coding-agent skill and reviewing it for problems before finalizing it.

In plain words
What is it for?
Use it to create skills such as PDF converters, code-review helpers, or data-analysis tools.
Why use it?
It gives skill creation a defined location and a repeatable process instead of leaving files and review steps unclear.

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/j5ik2o/okite-ai/create-skill
Clone the repo
git clone --depth 1 https://github.com/j5ik2o/okite-ai

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.

agentmods badge for create-skill

README.md
[![agentmods](https://agentmods.dev/badge/commands/j5ik2o/okite-ai/create-skill.svg)](https://agentmods.dev/commands/j5ik2o/okite-ai/create-skill)
Your own site
<a href="https://agentmods.dev/commands/j5ik2o/okite-ai/create-skill"><img src="https://agentmods.dev/badge/commands/j5ik2o/okite-ai/create-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,996 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 $0.00017 $0.01996
Opus 5 $0.00009 $0.00998
Sonnet 5 $0.00003 $0.00399
Haiku 4.5 $0.00002 $0.00200

Measured 3d ago against content hash 8246554e2280, 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/create-skill.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/create-skill - スキル作成コマンド

このコマンドは、skill-creatorスキルを使って新しいスキルを作成し、reviewing-skillsスキルでレビュー・自動修正を行います。

スコープ

重要: スキルはプロジェクトスコープ(.claude/skills/)に作成します。グローバルスコープ(~/.claude/skills/)には作成しません。 skills/が存在しても.claude/skills/に作成します。

出力先: {プロジェクトルート}/.claude/skills/{スキル名}/

使い方

引数付き起動

/create-skill pdf-converter PDFファイルを画像に変換するスキル

引数なし起動(対話的)

/create-skill

[1/3] スキル情報の取得

引数の解析

引数からスキル情報を取得します:

  • $1: スキル名
  • $2以降: スキルの説明
スキル名: $1
スキルの説明: $ARGUMENTS から $1 を除いた部分

$1が空の場合、AskUserQuestionツールを使用して以下を質問してください:

AskUserQuestion({
  questions: [
    {
      question: "作成するスキルの名前を入力してください。\n\n例:\n- pdf-converter\n- code-review\n- data-analyzer",
      header: "スキル名",
      options: [
        {
          label: "名前を入力",
          description: "スキル名を直接入力"
        }
      ],
      multiSelect: false
    }
  ]
})

スキル名取得後、説明が空の場合も質問してください:

AskUserQuestion({
  questions: [
    {
      question: "スキルの説明を入力してください。何を行うスキルですか?\n\n例:\n- PDFファイルを画像に変換し、OCR処理を行う\n- コードレビューを自動化し、改善点を提案する\n- データを分析してレポートを生成する",
      header: "スキル説明",
      options: [
        {
          label: "説明を入力",
          description: "スキルの説明を直接入力"
        }
      ],
      multiSelect: false
    }
  ]
})

[2/3] スキルの作成

TodoWriteでタスク管理

TodoWriteツールを使用してタスクを作成:

TodoWrite({
  todos: [
    {
      content: "skill-creatorでスキルを作成",
      activeForm: "スキルを作成している",
      status: "in_progress"
    },
    {
      content: "reviewing-skillsでスキルをレビュー",
      activeForm: "スキルをレビューしている",
      status: "pending"
    },
    {
      content: "レビュー結果に基づいて自動修正",
      activeForm: "スキルを自動修正している",
      status: "pending"
    }
  ]
})

skill-creatorの実行

Skillツールを使用してskill-creatorスキルを実行します:

Skill({
  skill: "example-skills:skill-creator",
  args: "[スキル名] [スキルの説明]"
})

重要:

  • skill-creatorが対話的に質問してくる場合は、ユーザーから取得した情報を元に回答してください
  • init_skill.py--pathオプションにはプロジェクトスコープを指定すること:
    # 正しい(プロジェクトスコープ)
    init_skill.py [スキル名] --path {プロジェクトルート}/.claude/skills
    
    # 間違い(グローバルスコープ)
    init_skill.py [スキル名] --path ~/.claude/skills
    

Read the full file on GitHub · 287 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. 3d ago First seen · 287 lines · 17 tokens per session scan A 8246554e2280

Subscribe to this mod's changes

create-skill is a command published in the GitHub repository j5ik2o/okite-ai (81 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 1,996 once invoked, about $0.0001 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 2026-09-01.