zread-expert

zread-expert is a skill for Claude Code from tianxiao1430-jpg/zai-skills. It costs 17 tokens per session (2,797 once invoked), scanned A, original, MIT.

A repository-analysis guide for Z.AI's Zread tools. A repository is the files and history that make up a software project.

In plain words
What is it for?
Reviewing project directories, identifying modules and dependencies, reading key files, and assessing architecture or code quality.
Why use it?
It helps developers understand an unfamiliar GitHub project by mapping its structure and examining important files and code patterns.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Reviewing project directories, identifying modules and dependencies, reading key files, and assessing architecture or code quality.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tianxiao1430-jpg/zai-skills/zread-expert
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 tianxiao1430-jpg/zai-skills --skill zread-expert
Clone the repo
git clone --depth 1 https://github.com/tianxiao1430-jpg/zai-skills

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 zread-expert

README.md
[![agentmods](https://agentmods.dev/badge/skills/tianxiao1430-jpg/zai-skills/zread-expert/github.svg)](https://agentmods.dev/skills/tianxiao1430-jpg/zai-skills/zread-expert)
Your own site
<a href="https://agentmods.dev/skills/tianxiao1430-jpg/zai-skills/zread-expert"><img src="https://agentmods.dev/badge/skills/tianxiao1430-jpg/zai-skills/zread-expert/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 zread-expert

Your own site · 80×15
<a href="https://agentmods.dev/skills/tianxiao1430-jpg/zai-skills/zread-expert"><img src="https://agentmods.dev/badge/skills/tianxiao1430-jpg/zai-skills/zread-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,797 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 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 $0.00017 $0.02797
Opus 5 $0.00009 $0.01399
Sonnet 5 $0.00003 $0.00559
Haiku 4.5 $0.00002 $0.00280

Measured 12d ago against content hash 7e7a33d77245, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

zread-expert 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/zread-expert/SKILL.md · 396 lines

How it starts

The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ZAI Zread Expert / 代码库分析专家 / コードベース分析エキスパート

[English]

You are a senior software architect. Your goal is to use the zread MCP to understand, analyze, and improve GitHub repositories.

[简体中文]

你是资深软件架构师。你的目标是使用 zread MCP 来理解、分析和改进 GitHub 仓库。

[日本語]

あなたはシニアソフトウェアアーキテクトです。あなたの目標は、zread MCP を使用して GitHub リポジトリを理解、分析、改善することです。


Core Workflow / 核心工作流程 / 中核ワークフロー

1. Structural Audit / 结构审计 / 構造監査

使用场景 / Use Cases / 使用事例:

  • 快速了解新项目结构
  • 识别核心模块和依赖关系
  • 评估代码质量和架构设计

工具调用示例 / Tool Call Example / ツール呼び出し例:

# 第一步:获取项目结构
zread.structure(repo_name="owner/repo")

# 第二步:分析关键文件
zread.read(repo_name="owner/repo", file_path="src/main.ts")

示例对话 / Example Dialogue / 対話例:

用户:帮我分析一下 facebook/react 的目录结构

助手:<internal>
分析需求:React 项目结构分析
调用工具:zread.structure
预期输出:项目骨架说明 + 核心模块介绍
</internal>

我来分析 React 项目的结构...

[调用 zread.structure repo_name="facebook/react"]

📦 React 项目结构分析:

## 顶层目录

react/ ├── packages/ # 核心包 │ ├── react/ # React 核心 │ ├── react-dom/ # DOM 渲染 │ ├── react-reconciler/ # 协调器 │ └── ... ├── fixtures/ # 测试用例 ├── scripts/ # 构建脚本 └── ...


## 核心模块
1. **react** - 核心 API(createElement, useState 等)
2. **react-dom** - DOM 特定实现
3. **react-reconciler** - 虚拟 DOM 协调算法
4. **react-server** - 服务端组件支持

## 架构特点
- 单体仓库(Monorepo)管理
- 包之间严格分离
- 使用 Rollup 构建

2. Semantic Search / 语义搜索 / セマンティック検索

使用场景 / Use Cases / 使用事例:

  • 查找特定功能的实现
  • 搜索相关 Issue/PR 了解背景
  • 理解代码演进历史

工具调用示例 / Tool Call Example / ツール呼び出し例:

# 搜索代码实现
zread.search(
    repo_name="owner/repo",
    query="useEffect implementation",
    search_type="code"
)

# 搜索相关 Issue
zread.search(
    repo_name="owner/repo",
    query="useEffect memory leak bug",
    search_type="issues"
)

示例对话 / Example Dialogue / 対話例:

用户:React 的 useEffect 是怎么实现的?

助手:<internal>
分析需求:useEffect 实现原理
搜索策略:先搜索代码,再查找相关文档
预期输出:实现逻辑 + 关键代码
</internal>

我来查找 useEffect 的实现...

[调用 zread.search query="useEffect implementation hook"]
[调用 zread.read file_path="packages/react/src/ReactHooks.js"]

🔍 useEffect 实现分析:

## 核心位置
`packages/react/src/ReactHooks.js`

## 实现逻辑
```javascript
// 简化版 useEffect 实现
function useEffect(create, deps) {
  // 1. 获取当前渲染的 Hook
  const hook = mountWorkInProgressHook();

Read the full file on GitHub · 396 lines

Files

What ships with it

1 file 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 · 396 lines · 17 tokens per session scan A 7e7a33d77245

Subscribe to this mod's changes

zread-expert is a skill published in the GitHub repository tianxiao1430-jpg/zai-skills (16 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 2,797 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 2026-08-30.

Related

Other skills, from other repositories

fasterizy

Faster and direct, answer-first prose for coding-agent Q&A, planning, and technical docs. Use whenever the user asks for terser, faster, less verbose, or less filler answers—even without the word "fasterizy". Compressed Q&A; normal prose for plan artifacts and source; expands on demand. Chat: /fasterizy, /fasterizy…

felipeinf/fasterizy · 87 tokens

idea-refine

Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…

addyosmani/agent-skills · 75 tokens

officecli-word-form

Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…

iOfficeAI/OfficeCLI · 224 tokens

chinese-git-workflow

A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.

jnMetaCode/superpowers-zh · 69 tokens

chinese-documentation

A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.

jnMetaCode/superpowers-zh · 62 tokens

browser_cdp

A guide for connecting browser-control tools to an existing Chrome session through its remote debugging interface. It explains scanning ports, attaching to a browser, choosing a port, sharing a browser, and switching to a more private control mode.

agentscope-ai/skills · 97 tokens