xiaozhi-client: Skill for Claude Code

.agents/skills/issue-hunter/SKILL.md

issue-hunter is a skill for Claude Code, Codex from shenjingnan/xiaozhi-client. It costs 15 tokens per session (4,578 once invoked), scanned A, original, MIT.

A code-review skill that searches the xiaozhi-client project for one high-priority bug or maintainability problem at a time. It can submit the finding as a GitHub Issue.

In plain words
What is it for?
It checks areas such as documentation, MCP code, services, handlers, the command-line interface, and other project files for issues, then gives a concrete fix proposal for the selected finding.
Why use it?
It focuses attention on actionable problems instead of producing a long list of minor criticisms. Its tracking files and issue workflow help avoid reporting the same problem repeatedly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; installed under .agents/ (shared by several agents).

This is shenjingnan/xiaozhi-client's own configuration. It tells Claude Code and Codex how to work on xiaozhi-client 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 xiaozhi-client configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { MCPManager } from "../mcp-core";.

Reuse

Borrowing it

Nothing to install: this file belongs to shenjingnan/xiaozhi-client. 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/shenjingnan/xiaozhi-client/main/.agents/skills/issue-hunter/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/shenjingnan/xiaozhi-client

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 issue-hunter

README.md
[![agentmods](https://agentmods.dev/badge/skills/shenjingnan/xiaozhi-client/issue-hunter/github.svg)](https://agentmods.dev/skills/shenjingnan/xiaozhi-client/issue-hunter)
Your own site
<a href="https://agentmods.dev/skills/shenjingnan/xiaozhi-client/issue-hunter"><img src="https://agentmods.dev/badge/skills/shenjingnan/xiaozhi-client/issue-hunter/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 issue-hunter

Your own site · 80×15
<a href="https://agentmods.dev/skills/shenjingnan/xiaozhi-client/issue-hunter"><img src="https://agentmods.dev/badge/skills/shenjingnan/xiaozhi-client/issue-hunter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,578 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 $0.00015 $0.04578
Opus 5 $0.00008 $0.02289
Sonnet 5 $0.00003 $0.00916
Haiku 4.5 $0.00002 $0.00458

Measured 10d ago against content hash dbc301b3ad95, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

issue-hunter 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 10d 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.

.agents/skills/issue-hunter/SKILL.md · 639 lines

How it starts

The opening of the file, as written. The whole thing — 639 lines — stays where its author put it; the contents beside it link to each section on GitHub.

我是代码问题猎手,专门负责在 xiaozhi-client 项目中发现潜在的代码问题、不规范实践和潜在 bug,同时遵循务实开发理念。

技能使用原则

  • 问题导向:只关注真正影响代码质量或维护性的问题,避免吹毛求疵
  • 可操作性强:每个发现的问题都必须提供具体的修复方案
  • 务实判断:遵循"如无必要勿增实体"的理念,不过度批评简单直接的实现
  • 单问题专注:每次执行只发现并提交一个最高优先级问题
  • 随机轮询:通过随机选择问题类型,确保长期覆盖各类问题

项目结构感知

项目目录结构

xiaozhi-client/
├── src/                     # 统一源码目录
│   ├── server/             # 后端核心
│   │   ├── lib/mcp/        # MCP 核心库
│   │   ├── handlers/       # 处理器
│   │   ├── services/       # 业务服务
│   │   └── utils/          # 工具函数
│   ├── web/                # React 前端
│   ├── cli/                # CLI 工具
│   ├── config/             # 配置管理
│   ├── mcp-core/           # MCP 协议核心
│   ├── endpoint/           # 端点处理
│   ├── esp32/              # ESP32 硬件相关
│   ├── types/              # 共享类型定义
│   └── utils/              # 通用工具
├── todos/                  # 待解决问题(用于去重)
├── docs/                   # Nextra 文档
└── .github/workflows/
    ├── claude.yml          # @claude 触发
    └── issue-hunter.yml    # 定时执行(每10分钟)

关键文件重点关注

  • src/server/lib/mcp/manager.ts - MCP 管理器
  • src/server/services/ - 业务服务
  • src/server/handlers/ - 处理器
  • src/cli/ - CLI 入口

问题检测类型(12种)

1. 文档问题检测

检查范围: docs/, README.md, CLAUDE.md

检测内容:

  • 缺失的 API 文档(公共接口必须有 JSDoc)
  • 过时的示例代码
  • 不一致的文档格式
  • 缺失的重要说明

检测命令:

# 检查文档文件
find docs/ -name "*.mdx" -type f

2. 类型安全问题

检查命令: pnpm typecheck

检测内容:

  • any 类型使用(尤其是非测试文件)
  • 类型定义缺失
  • 类型断言滥用
  • 隐式 any

关注重点:

  • 非测试文件中的 any 类型
  • 缺少类型定义的函数参数
  • 不安全的类型转换

3. 错误处理问题

检测内容:

  • 缺失 try-catch 的异步操作
  • 错误未正确传播
  • 无意义的错误捕获
  • 缺少错误日志

代码模式:

// ❌ 危险模式
async function riskyOperation() {
  const result = await fetchSomething(); // 无错误处理
}

// ❌ 无意义捕获
try {
  // ...
} catch (e) {
  // 吞掉错误
}

// ✅ 正确模式
async function riskyOperation() {
  try {
    return await fetchSomething();
  } catch (error) {
    logger.error('操作失败', error);
    throw error; // 重新抛出
  }
}

4. 资源泄漏问题

检测内容:

  • 定时器未清理(setTimeout, setInterval)
  • 连接未关闭(WebSocket, 数据库连接)
  • 事件监听器未移除
  • 文件句柄未释放

Read the full file on GitHub · 639 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. 10d ago First seen · 639 lines · 15 tokens per session scan A dbc301b3ad95

Subscribe to this mod's changes

issue-hunter is a skill published in the GitHub repository shenjingnan/xiaozhi-client (338 stars, last pushed 6d ago), licensed MIT. It adds 15 tokens to every session and 4,578 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

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens

verify-behavior

Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…

nicknisi/dotfiles · 68 tokens

github-contributor

End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…

daymade/claude-code-skills · 133 tokens

revdiff

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…

umputun/revdiff · 248 tokens

write-pr

Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.

tldraw/tldraw · 53 tokens