xs-skill-creator

xs-skill-creator is a skill for Claude Code, Codex from karaage0703/ai-assistant-workspace. It costs 91 tokens per session (2,205 once invoked), scanned A, original, MIT.

A guide for creating or improving skills for an assistant. It covers analysing existing skills, choosing a skill type, gathering requirements, and writing a Japanese SKILL.md file with supporting structure.

In plain words
What is it for?
Use it to create a new skill, improve an existing one, define its inputs and outputs, choose between interactive or automated behaviour, and plan checks for external tools or services.
Why use it?
It gives skill authors a repeatable way to decide what a skill should do and how it should be triggered. It also helps avoid unclear instructions and unnecessary setup steps.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit Use it to create a new skill, improve an existing one, define its inputs and outputs, choose between interactive or automated behaviour, and plan checks for external tools or services.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/karaage0703/ai-assistant-workspace/xs-skill-creator
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.

Any agent
npx skills add karaage0703/ai-assistant-workspace --skill xs-skill-creator
Clone the repo
git clone --depth 1 https://github.com/karaage0703/ai-assistant-workspace

Made for: Claude Code, Codex.

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 xs-skill-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/karaage0703/ai-assistant-workspace/xs-skill-creator/github.svg)](https://agentmods.dev/skills/karaage0703/ai-assistant-workspace/xs-skill-creator)
Your own site
<a href="https://agentmods.dev/skills/karaage0703/ai-assistant-workspace/xs-skill-creator"><img src="https://agentmods.dev/badge/skills/karaage0703/ai-assistant-workspace/xs-skill-creator/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.

agentmods 80×15 button for xs-skill-creator

Your own site · 80×15
<a href="https://agentmods.dev/skills/karaage0703/ai-assistant-workspace/xs-skill-creator"><img src="https://agentmods.dev/badge/skills/karaage0703/ai-assistant-workspace/xs-skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,205 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00091 $0.02205
Opus 5 $0.00046 $0.01103
Sonnet 5 $0.00018 $0.00441
Haiku 4.5 $0.00009 $0.00220

Measured 12d ago against content hash ae7a946267b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

xs-skill-creator 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 12d 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.

skills/xs-skill-creator/SKILL.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

スキルクリエイター

ワークスペースの既存スキル群と統一感のあるスキルを作成・改善する。

絶対遵守事項

  • 対話は日本語で行う
  • 作成するスキルのSKILL.mdも日本語で記述

プロンプト設計原則(制約少なめ・例多め)

過剰特定された制約は memorized shortcut を誤発火して品質を下げる(Akli et al., 2026, arXiv:2604.24712)。SKILL.md を書くときは:

  • 「禁止」「絶対」「必ず」を並べるより、Do の例(コマンド例・入出力例・テンプレート)で示す
  • スキル全体での禁止系制約は3つ程度を目安。それ以上は構造(章立て・例示)で表現する
  • 残す制約には「なぜそれを避けるか」を1行で添える(理由なしの禁止は誤解されやすい)

詳細とBefore/After例は [SKILL_DIR]/references/patterns.md の「9. 制約少なめ・例多めの原則」を参照。

スキル作成フロー

Step 1: ヒアリング

ユーザーに以下を確認(わかっている情報はスキップ):

  1. 何をするスキル? → 主機能の把握
  2. どんな時に使う? → トリガー条件の特定
  3. 入力と出力は? → データフローの明確化
  4. スクリプトは必要? → Python/Bash等の自動化有無

Step 2: 分類と設計

4分類のどれに該当するか判定し、適切なテンプレートを選択:

分類 特徴
対話型 ユーザーとの対話で成果物を生成 ブログ記事生成、プレゼン企画
自動実行型 指示一つで取得→加工→出力 ニュース取得、サイト巡回
ツール連携型 外部ツール/APIとの連携 API操作、DB管理
思考支援型 構造化された思考フレームワーク提供 ブレスト支援、調査整理

テンプレートの詳細は [SKILL_DIR]/references/templates.md を参照。

外部CLI、常駐サーバー、API、GPUなどに依存する場合は、あわせて次を設計する。

  1. 副作用のない可用性チェック
  2. 利用可能と判断できる成功条件
  3. 利用不可時のフォールバック、または安全なスキップ
  4. 導入・起動・ログインを自動実行してよい条件

可用性確認だけを目的に、パッケージ導入、サービス起動、ログイン、設定変更を行わない。必須機能でなければ、依存がない環境でもスキル以外の作業を継続できる構成にする。

Step 3: ディレクトリ作成

# スキル名はケバブケースで
mkdir -p [WORKSPACE]/skills/<skill-name>

# 必要に応じてサブディレクトリ作成
mkdir -p [WORKSPACE]/skills/<skill-name>/scripts
mkdir -p [WORKSPACE]/skills/<skill-name>/references
mkdir -p [WORKSPACE]/skills/<skill-name>/assets

Step 4: スクリプト作成(該当する場合)

スクリプトが必要な場合:

  1. scripts/ にPython/Bashスクリプトを配置
  2. 必ず uv run で実行するpython3 直接実行は禁止。外部依存ゼロでも uv run を使う。理由: python未インストール環境でもuvがPythonを自動解決するため)
  3. --help オプションを実装
  4. 実際に uv run でテスト実行して動作確認

Step 5: SKILL.md作成

テンプレートに従い作成。以下の要素を必ず含める:

フロントマター(必須):

---
name: xs-<skill-name>
description: [50-200文字。何をするか+いつ使うか+トリガーフレーズ]
---

本文の構成:

  1. H1タイトル - スキル名
  2. 1行概要 - 何をするスキルか
  3. 絶対遵守事項(必要な場合)
  4. 手順 - Step/STEP形式で番号付き
  5. 出力フォーマット - 期待する出力形式
  6. 使用例 - 具体的なトリガーフレーズ

パス規則:

  • [SKILL_DIR] - SKILL.mdがあるディレクトリ
  • [WORKSPACE] - ワークスペースルート
  • ハードコードパス禁止

Read the full file on GitHub · 212 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 212 lines · 91 tokens per session scan A ae7a946267b7

Subscribe to this mod's changes

xs-skill-creator is a skill published in the GitHub repository karaage0703/ai-assistant-workspace (137 stars, last pushed 25d ago), licensed MIT. It adds 91 tokens to every session and 2,205 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens