skill-create

skill-create is a command for coding agents from xu-xiang/everything-claude-code-zh. It costs 9 tokens per session (661 once invoked), scanned A, original, MIT.

A command that studies a project's Git history—the record of past code changes—to generate a reusable skill document and development habits.

In plain words
What is it for?
Use it to inspect recent commits, find frequently changed files, document common practices in SKILL.md, and create patterns for continuous learning.
Why use it?
It turns recurring patterns in commits, file changes, coding practices, and review feedback into written guidance. This can make the project's unwritten conventions easier to follow.

Command

Part of the everything-claude-code-zh plugin — 17 skills, 26 commands, 13 agents shipped together

About the project

everything-claude-code-zh is a Chinese translation of a collection of configurations for Claude Code and other AI coding agents. It provides agents, skills, hooks, commands, rules, and MCP configurations intended to support development workflows such as memory persistence, security scanning, evaluation, and research-first work. The catalogue includes commands, skills, agents, instructions, and a plugin from this configuration set.

xu-xiang/everything-claude-code-zh · 1,927 stars · on GitHub

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/xu-xiang/everything-claude-code-zh/skill-create
Clone the repo
git clone --depth 1 https://github.com/xu-xiang/everything-claude-code-zh

Or install everything-claude-code-zh, the plugin that ships this one along with the rest of its 17 skills, 26 commands, 13 agents.

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 skill-create

README.md
[![agentmods](https://agentmods.dev/badge/commands/xu-xiang/everything-claude-code-zh/skill-create.svg)](https://agentmods.dev/commands/xu-xiang/everything-claude-code-zh/skill-create)
Your own site
<a href="https://agentmods.dev/commands/xu-xiang/everything-claude-code-zh/skill-create"><img src="https://agentmods.dev/badge/commands/xu-xiang/everything-claude-code-zh/skill-create.svg" alt="Measured on agentmods" height="20"></a>
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 661 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 $0.00661
Opus 5 $0.00005 $0.00331
Sonnet 5 $0.00002 $0.00132
Haiku 4.5 $0.00001 $0.00066

Measured 4d ago against content hash 4e8758589fa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-create 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 4d 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.

.opencode/commands/skill-create.md · 118 lines

What it actually says

Skill Create 命令

分析 Git 历史(Git history)以生成 Claude Code 技能(Skill):$ARGUMENTS

你的任务

  1. 分析提交(Commits) - 从历史记录中进行模式识别(Pattern recognition)
  2. 提取模式 - 常见的实践与约定
  3. 生成 SKILL.md - 结构化的技能文档
  4. 创建直觉(Instincts) - 用于 continuous-learning-v2

分析过程

第 1 步:收集提交数据

# 最近的提交
git log --oneline -100

# 按文件类型统计提交
git log --name-only --pretty=format: | sort | uniq -c | sort -rn

# 修改最频繁的文件
git log --pretty=format: --name-only | sort | uniq -c | sort -rn | head -20

第 2 步:识别模式

提交信息模式

  • 常见前缀 (feat, fix, refactor)
  • 命名约定
  • 共同作者(Co-author)模式

代码模式

  • 文件结构约定
  • 导入(Import)组织方式
  • 错误处理方法

评审(Review)模式

  • 常见的评审反馈
  • 反复出现的修复类型
  • 质量门禁(Quality gates)

第 3 步:生成 SKILL.md

# [技能名称]

## 概述
[此技能教授的内容]

## 模式(Patterns)

### 模式 1:[名称]
- 何时使用
- 实现方式
- 示例

### 模式 2:[名称]
- 何时使用
- 实现方式
- 示例

## 最佳实践

1. [实践 1]
2. [实践 2]
3. [实践 3]

## 常见错误

1. [错误 1] - 如何避免
2. [错误 2] - 如何避免

## 示例

### 正面示例
```[language]
// 代码示例

反面模式(Anti-pattern)

// 不应该做的写法

### 第 4 步:生成直觉(Instincts)

用于 continuous-learning-v2:

```json
{
  "instincts": [
    {
      "trigger": "[场景/状况]",
      "action": "[响应动作]",
      "confidence": 0.8,
      "source": "git-history-analysis"
    }
  ]
}

输出

创建:

  • skills/[name]/SKILL.md - 技能文档
  • skills/[name]/instincts.json - 直觉集合

提示(TIP):运行 /skill-create --instincts 以同时生成用于持续学习(continuous learning)的直觉。

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. 4d ago First seen · 118 lines · 9 tokens per session scan A 4e8758589fa0

Subscribe to this mod's changes

skill-create is a command published in the GitHub repository xu-xiang/everything-claude-code-zh (1,927 stars, last pushed 6mo ago), licensed MIT. It adds 9 tokens to every session and 661 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.