claude-code-best-practice-zh: Command for Claude Code

.claude/commands/workflows/best-practice/workflow-claude-skills.md

workflow-claude-skills is a command for Claude Code from rongxinzy/claude-code-best-practice-zh. It costs 16 tokens per session (1,851 once invoked), scanned A, a copy of workflow-claude-skills, MIT.

A command workflow that checks recent changes to Claude Code's documented skills and compares them with a local report. Claude Code is a programming assistant, and skills are reusable instruction bundles for it.

In plain words
What is it for?
Use it to research a selected number of Claude Code versions, review the existing change log, and produce a report of documentation differences and priority actions.
Why use it?
It helps maintainers spot newly added or removed frontmatter fields and built-in skills before updating their documentation.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Claude Code.

This is rongxinzy/claude-code-best-practice-zh's own configuration. It tells Claude Code how to work on claude-code-best-practice-zh itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-best-practice-zh configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rongxinzy/claude-code-best-practice-zh. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rongxinzy/claude-code-best-practice-zh/main/.claude/commands/workflows/best-practice/workflow-claude-skills.md
Clone the repo
git clone --depth 1 https://github.com/rongxinzy/claude-code-best-practice-zh

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 workflow-claude-skills

README.md
[![agentmods](https://agentmods.dev/badge/commands/rongxinzy/claude-code-best-practice-zh/workflow-claude-skills/github.svg)](https://agentmods.dev/commands/rongxinzy/claude-code-best-practice-zh/workflow-claude-skills)
Your own site
<a href="https://agentmods.dev/commands/rongxinzy/claude-code-best-practice-zh/workflow-claude-skills"><img src="https://agentmods.dev/badge/commands/rongxinzy/claude-code-best-practice-zh/workflow-claude-skills/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 workflow-claude-skills

Your own site · 80×15
<a href="https://agentmods.dev/commands/rongxinzy/claude-code-best-practice-zh/workflow-claude-skills"><img src="https://agentmods.dev/badge/commands/rongxinzy/claude-code-best-practice-zh/workflow-claude-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,851 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.
Origin 88% copy Near-identical to another mod 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 $0.00016 $0.01851
Opus 5 $0.00008 $0.00925
Sonnet 5 $0.00003 $0.00370
Haiku 4.5 $0.00002 $0.00185

Measured 12d ago against content hash c95b00987498, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

workflow-claude-skills 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.

Origin

This is a copy

88% identical to workflow-claude-skills — 149 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/workflows/best-practice/workflow-claude-skills.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

工作流变更日志 —— 技能报告

你是 claude-code-best-practice 项目的协调员。你的工作是启动研究代理,等待其结果,并呈现关于技能参考报告(best-practice/claude-skills.md)差异的报告。

此工作流精确检查两种类型的差异

  1. Frontmatter 字段 —— 官方文档中添加或删除的任何字段
  2. 官方捆绑技能 —— 添加或删除的任何捆绑技能

检查版本数: $ARGUMENTS(默认:如果为空或非数字则为 10)

这是一个先读取后报告的工作流。启动代理,合并发现,生成报告。仅在用户批准时采取行动。


阶段 1: 启动研究代理

使用此提示生成 workflow-claude-skills-agent

研究 claude-code-best-practice 项目的技能报告差异。检查最后 $ARGUMENTS 个版本(默认:10)。

获取这 2 个外部来源:

  1. 技能参考:https://code.claude.com/docs/zh-CN/skills
  2. 变更日志:https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md

然后读取本地报告(best-practice/claude-skills.md)。

精确检查两件事:

  1. Frontmatter 字段:将官方文档支持的技能 frontmatter 字段与报告的 Frontmatter 字段表格对比。标记任何添加或删除的字段。
  2. 官方捆绑技能:将官方文档的捆绑技能列表(以及变更日志中提到的任何新捆绑技能)与报告的官方技能表格对比。标记任何添加或删除的技能。

阶段 2: 读取之前的变更日志条目

在代理运行时,读取 changelog/best-practice/claude-skills/changelog.md 获取最近 25 个条目。解析优先行动项以识别:

  • 重复项目 —— 之前出现过且仍未解决的问题
  • 新增项目 —— 首次出现的问题
  • 已解决项目 —— 之前标记的问题现已修复

阶段 3: 生成报告

**等待代理完成。**生成包含以下部分的报告:

  1. Frontmatter 字段变更 —— 官方文档与我们的报告中添加或删除的字段
  2. 官方捆绑技能变更 —— 与我们的表格相比添加或删除的捆绑技能

以优先的行动项摘要表格结尾。每个项目必须包含显示 新增重复(首次出现:<日期>)已解决状态 列:

优先行动项:
#  | 类型              | 行动                                | 状态
1  | 新字段            | 添加 <字段> 到 frontmatter 表格      | 新增
2  | 删除字段          | 从表格删除 <字段>                    | 重复(首次出现:<日期>)
3  | 新技能            | 添加 <技能> 到官方技能表格           | 新增
4  | 删除技能          | 从表格删除 <技能>                    | 新增

还要包含一个自上次运行以来已解决部分,列出之前运行中不再是问题的项目。


阶段 3.5: 追加摘要到变更日志

此阶段是强制的 —— 在向用户呈现报告之前始终执行。

读取现有的 changelog/best-practice/claude-skills/changelog.md 文件,然后在末尾追加(不要覆盖)新条目。条目格式必须完全为:

---

## [<YYYY-MM-DD HH:MM AM/PM PKT>] Claude Code v<版本>

| # | 优先级 | 类型 | 行动 | 状态 |
|---|----------|------|--------|--------|
| 1 | 高/中/低 | <类型> | <行动描述> | <状态> |
| ... | ... | ... | ... | ... |

状态格式 —— 必须使用以下三种格式之一:

  • 已完成 (原因) —— 已采取行动并成功解决
  • 无效 (原因) —— 发现不正确、不适用或有意的
  • 暂停 (原因) —— 行动推迟,等待外部依赖或用户决定

Read the full file on GitHub · 139 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. 12d ago First seen · 139 lines · 16 tokens per session scan A c95b00987498

Subscribe to this mod's changes

workflow-claude-skills is a command published in the GitHub repository rongxinzy/claude-code-best-practice-zh (6 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 1,851 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to workflow-claude-skills, differing in 149 lines, and is treated as a copy.