技能 skill-permissions

📦

skill-permissions

Name: skill-permissions
Author: guo-yu

内容修订 r1 高风险 ⚙️ 外部命令📁 文件系统访问

审计技能权限

Claude Code 技能可能需要 shell 权限，而这些权限很难手动审查。此技能会分析声明的命令用法，并帮助创建匹配的允许列表条目，同时对范围较大的更改发出警告。

支持: Claude Codex Code(CC)

⚠️ 38 差

安装前请停下并请求确认。

请审查安装计划，并在更改文件前获得用户明确同意。

使用我的智能体安装

将此请求复制给你的智能体，其中包含权威 Skill 页面和清单。

智能体请求

Review the Skillstore skill "skill-permissions" from https://skillstore.io/skills/guo-yu-skill-permissions.md and its manifest at https://skillstore.io/api/skills/guo-yu-skill-permissions/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

你的智能体仍应展示其计划，并按安全策略请求必要确认。

Agent 可读资源

当 AI Agent、爬虫或脚本需要干净上下文，而不是读取完整页面时，请使用这些链接。

Markdown 详情 GET /skills/guo-yu-skill-permissions.md 已签名 manifest GET /api/skills/guo-yu-skill-permissions/manifest 已签名 lockfile GET /api/skills/guo-yu-skill-permissions/lockfile

测试它

正在使用“skill-permissions”。分析 port-allocator 技能。

预期结果:

列出检测到的命令，例如 find、ls、cat 和 lsof。
显示建议的 Claude Code allow 规则。
为该技能推荐一条特定的 allow 命令。

正在使用“skill-permissions”。显示所有技能的权限。

预期结果:

显示已安装技能及主要权限组的表格。
标记需要授权的技能。
建议在批量授权前审查结果。

正在使用“skill-permissions”。授权一个已审查的技能。

预期结果:

报告权限规则已合并。
显示受影响的设置文件。
提醒用户权限会在新会话中或清除后生效。

安全审计

高风险

v6 • 2026/7/9 打开版本化报告

The skill is a security-sensitive permission management helper, not malware. Most dangerous command hits are documented blocklist examples, but the skill can broaden Claude Code Bash allow rules and batch-modify settings or skill files, so publication should require strong warnings and safer defaults.

已扫描文件

894

分析行数

115

复核项

已忽略误报

已确认安全问题 (4)

高

SKILL.md:16-18 SKILL.zh-CN.md:156-188

Batch Permission Expansion and Skill File Modification

The skill documents allow-all and inject modes that can modify settings.json or add allow commands across installed skills. This creates broad local permission expansion risk even though the documentation warns users.

The behavior is explicitly described in multiple language files and affects configuration plus many skill files. The warnings reduce surprise but do not remove the risk.

高

SKILL.md:201-210 SKILL.zh-CN.md:429-438

Overbroad Claude Directory Allow Rules

The generated allow rules include broad access to ~/.claude paths, including Bash(cat ~/.claude/*). These rules can expose sensitive local Claude configuration if granted too broadly.

The allow rules are shown directly in the documented authorization flow. The risk depends on user approval, but the scope is broad and security-sensitive.

中

SKILL.md:23

System reconnaissance

- Avoid `inject` or `allow-all` unless you understand the impact

The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.

中

SKILL.md:217

System reconnaissance

1. **Conservative analysis** - Only identify explicitly appearing commands, avoid over-authorization

The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.

能力复核项 (115)

这些是真实的本地能力，对此技能可能是预期行为，因此需要复核，但不会按已确认恶意行为计分。

高

SKILL.ja.md:47

Hidden file in home directory

cat ~/.claude/* → Bash(cat ~/.claude/*)

The finding references reading or writing Claude Code settings or skill directories. This is intended permission-management behavior, but it is security-sensitive because it can broaden local tool permissions.

高

SKILL.ja.md:67

Hidden file in home directory

"Bash(cat ~/.claude/*)",

高

SKILL.ja.md:82

Hidden file in home directory

find ~/.claude/skills -name "SKILL.md" -type f 2>/dev/null

高

SKILL.ja.md:126

Hidden file in home directory

場所: ~/.claude/skills/port-allocator

高

SKILL.ja.md:136

Hidden file in home directory

- Bash(cat ~/.claude/*)

高

SKILL.ja.md:150

Hidden file in home directory

- Bash(cat ~/.claude/*)

高

SKILL.ja.md:152

Hidden file in home directory

設定ファイル: ~/.claude/settings.json

高

SKILL.ja.md:159

Hidden file in home directory

- **権限設定**: `~/.claude/settings.json`

高

SKILL.ja.md:160

Hidden file in home directory

- **スキルディレクトリ**: `~/.claude/skills/`

高

SKILL.ja.md:173

Hidden file in home directory

1. `~/.claude/settings.json` を読み取り

高

SKILL.ja.md:180

Hidden file in home directory

"Bash(find ~/.claude/skills *)",

高

SKILL.ja.md:181

Hidden file in home directory

"Bash(cat ~/.claude/*)"

高

SKILL.md:47

Hidden file in home directory

cat ~/.claude/* → Bash(cat ~/.claude/*)

高

SKILL.md:68

Hidden file in home directory

"Bash(cat ~/.claude/*)",

高

SKILL.md:83

Hidden file in home directory

find ~/.claude/skills -name "SKILL.md" -type f 2>/dev/null

高

SKILL.md:100

Hidden file in home directory

SKILL_PATH=$(find ~/.claude/skills -type d -name "<skill-name>" 2>/dev/null | head -1)

高

SKILL.md:148

Hidden file in home directory

Location: ~/.claude/skills/port-allocator

高

SKILL.md:159

Hidden file in home directory

- Bash(cat ~/.claude/*)

高

SKILL.md:174

Hidden file in home directory

- Bash(cat ~/.claude/*)

高

SKILL.md:177

Hidden file in home directory

Config file: ~/.claude/settings.json

高

SKILL.md:184

Hidden file in home directory

- **Permission config**: `~/.claude/settings.json`

高

SKILL.md:185

Hidden file in home directory

- **Skill directory**: `~/.claude/skills/`

高

SKILL.md:198

Hidden file in home directory

1. Read `~/.claude/settings.json`

高

SKILL.md:205

Hidden file in home directory

"Bash(find ~/.claude/skills *)",

高

SKILL.md:206

Hidden file in home directory

"Bash(cat ~/.claude/*)"

高

SKILL.zh-CN.md:47

Hidden file in home directory

cat ~/.claude/* → Bash(cat ~/.claude/*)

高

SKILL.zh-CN.md:68

Hidden file in home directory

"Bash(cat ~/.claude/*)",

高

SKILL.zh-CN.md:93

Hidden file in home directory

find ~/.claude/skills -name "SKILL.md" -type f 2>/dev/null

高

SKILL.zh-CN.md:123

Hidden file in home directory

SKILL_PATH=$(find ~/.claude/skills -type d -name "<skill-name>" 2>/dev/null | head -1)

高

SKILL.zh-CN.md:138

Hidden file in home directory

cat ~/.claude/settings.json 2>/dev/null || echo '{"permissions":{"allow":[]}}'

高

SKILL.zh-CN.md:171

Hidden file in home directory

1. 读取 `~/.claude/settings.json`

高

SKILL.zh-CN.md:198

Hidden file in home directory

| `cat ~/.claude/*` | `Bash(cat ~/.claude/*)` |

高

SKILL.zh-CN.md:273

Hidden file in home directory

📁 位置: ~/.claude/skills/dangerous-skill

高

SKILL.zh-CN.md:284

Hidden file in home directory

- Bash(cat ~/.claude/*)

高

SKILL.zh-CN.md:316

Hidden file in home directory

📁 位置: ~/.claude/skills/port-allocator

高

SKILL.zh-CN.md:328

Hidden file in home directory

- Bash(cat ~/.claude/*)

高

SKILL.zh-CN.md:359

Hidden file in home directory

- Bash(cat ~/.claude/*)

高

SKILL.zh-CN.md:363

Hidden file in home directory

配置文件: ~/.claude/settings.json

高

SKILL.zh-CN.md:382

Hidden file in home directory

- **权限配置**: `~/.claude/settings.json`

高

SKILL.zh-CN.md:383

Hidden file in home directory

- **skill 目录**: `~/.claude/skills/`

高

SKILL.zh-CN.md:426

Hidden file in home directory

1. 读取 `~/.claude/settings.json`

高

SKILL.zh-CN.md:433

Hidden file in home directory

"Bash(find ~/.claude/skills *)",

高

SKILL.zh-CN.md:434

Hidden file in home directory

"Bash(cat ~/.claude/*)"

高

SKILL.zh-CN.md:459

Hidden file in home directory

- Bash(find ~/.claude/skills *)

高

SKILL.zh-CN.md:460

Hidden file in home directory

- Bash(cat ~/.claude/*)

高

SKILL.zh-CN.md:462

Hidden file in home directory

配置文件: ~/.claude/settings.json

中

SKILL.ja.md:47

Hidden file access

cat ~/.claude/* → Bash(cat ~/.claude/*)

中

SKILL.ja.md:67

Hidden file access

"Bash(cat ~/.claude/*)",

中

SKILL.ja.md:82

Hidden file access

find ~/.claude/skills -name "SKILL.md" -type f 2>/dev/null

中

SKILL.ja.md:126

Hidden file access

場所: ~/.claude/skills/port-allocator

中

SKILL.ja.md:136

Hidden file access

- Bash(cat ~/.claude/*)

中

SKILL.ja.md:150

Hidden file access

- Bash(cat ~/.claude/*)

中

SKILL.ja.md:152

Hidden file access

設定ファイル: ~/.claude/settings.json

中

SKILL.ja.md:159

Hidden file access

- **権限設定**: `~/.claude/settings.json`

中

SKILL.ja.md:160

Hidden file access

- **スキルディレクトリ**: `~/.claude/skills/`

中

SKILL.ja.md:173

Hidden file access

1. `~/.claude/settings.json` を読み取り

中

SKILL.ja.md:180

Hidden file access

"Bash(find ~/.claude/skills *)",

中

SKILL.ja.md:181

Hidden file access

"Bash(cat ~/.claude/*)"

中

SKILL.md:16

Ruby/shell backtick execution

| `/skill-permissions inject` | High | Batch modify all skill SKILL.md files |

The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.

中

SKILL.md:17

Ruby/shell backtick execution

| `/skill-permissions allow-all` | Medium | Batch modify settings.json |

The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.

中

SKILL.md:23

Ruby/shell backtick execution

- Avoid `inject` or `allow-all` unless you understand the impact

The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.

中

SKILL.md:30

Ruby/shell backtick execution

| `/skill-permissions` | Analyze all skills and show permission summary |

The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.

中

SKILL.md:33

Ruby/shell backtick execution

| `/skill-permissions allow-all` | Execute one-time authorization for all skills |

The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.

中

SKILL.md:34

Ruby/shell backtick execution

| `/skill-permissions inject` | Inject allow command into all skills |

The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.

中

SKILL.md:60-62

Ruby/shell backtick execution

Convert identified commands to `permissions.allow` rules:

中

SKILL.md:184-185

Ruby/shell backtick execution

- **Permission config**: `~/.claude/settings.json`

中

SKILL.md:185-190

Ruby/shell backtick execution

- **Skill directory**: `~/.claude/skills/`

中

SKILL.md:198-199

Ruby/shell backtick execution

1. Read `~/.claude/settings.json`

中

SKILL.md:199-201

Ruby/shell backtick execution

2. Merge the following permissions to `permissions.allow`:

中

SKILL.md:100

Shell command substitution

SKILL_PATH=$(find ~/.claude/skills -type d -name "<skill-name>" 2>/dev/null | head -1)

中

SKILL.md:47

Hidden file access

cat ~/.claude/* → Bash(cat ~/.claude/*)

中

SKILL.md:68

Hidden file access

"Bash(cat ~/.claude/*)",

中

SKILL.md:83

Hidden file access

find ~/.claude/skills -name "SKILL.md" -type f 2>/dev/null

中

SKILL.md:100

Hidden file access

SKILL_PATH=$(find ~/.claude/skills -type d -name "<skill-name>" 2>/dev/null | head -1)

中

SKILL.md:148

Hidden file access

Location: ~/.claude/skills/port-allocator

中

SKILL.md:159

Hidden file access

- Bash(cat ~/.claude/*)

中

SKILL.md:174

Hidden file access

- Bash(cat ~/.claude/*)

中

SKILL.md:177

Hidden file access

Config file: ~/.claude/settings.json

中

SKILL.md:184

Hidden file access

- **Permission config**: `~/.claude/settings.json`

中

SKILL.md:185

Hidden file access

- **Skill directory**: `~/.claude/skills/`

中

SKILL.md:198

Hidden file access

1. Read `~/.claude/settings.json`

中

SKILL.md:205

Hidden file access

"Bash(find ~/.claude/skills *)",

中

SKILL.md:206

Hidden file access

"Bash(cat ~/.claude/*)"

中

SKILL.zh-CN.md:147-156

Ruby/shell backtick execution

### 命令: `/skill-permissions allow-all`

The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.

中

SKILL.zh-CN.md:156-158

Ruby/shell backtick execution

### 命令: `/skill-permissions inject`

The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.

中

SKILL.zh-CN.md:158-163

Ruby/shell backtick execution

为所有 skill 注入 `allow` 子命令:

The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.

中

SKILL.zh-CN.md:198

Ruby/shell backtick execution

| `cat ~/.claude/*` | `Bash(cat ~/.claude/*)` |

中

SKILL.zh-CN.md:309-314

Ruby/shell backtick execution

- `allow_override`: 从默认黑名单中移除的命令(谨慎使用)

The documentation allows users to remove patterns from the default blocklist. That is intentional configuration, but it can weaken safeguards around dangerous commands.

中

SKILL.zh-CN.md:382-383

Ruby/shell backtick execution

- **权限配置**: `~/.claude/settings.json`

中

SKILL.zh-CN.md:383-389

Ruby/shell backtick execution

- **skill 目录**: `~/.claude/skills/`

中

SKILL.zh-CN.md:416-417

Ruby/shell backtick execution

1. **文件修改风险** - `inject` 命令会修改所有 skill 的 SKILL.md 文件

The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.

中

SKILL.zh-CN.md:417-420

Ruby/shell backtick execution

2. **权限扩大风险** - `allow-all` 会为所有 skill 添加权限,可能授予过多权限

The documented command can modify many skill files or settings entries. This is intentional functionality, but it creates real permission-expansion and file-modification risk if used without review.

中

SKILL.zh-CN.md:426-427

Ruby/shell backtick execution

1. 读取 `~/.claude/settings.json`

中

SKILL.zh-CN.md:427-429

Ruby/shell backtick execution

2. 合并以下权限到 `permissions.allow`:

中

SKILL.zh-CN.md:47

Hidden file access

cat ~/.claude/* → Bash(cat ~/.claude/*)

中

SKILL.zh-CN.md:68

Hidden file access

"Bash(cat ~/.claude/*)",

中

SKILL.zh-CN.md:93

Hidden file access

find ~/.claude/skills -name "SKILL.md" -type f 2>/dev/null

中

SKILL.zh-CN.md:123

Hidden file access

SKILL_PATH=$(find ~/.claude/skills -type d -name "<skill-name>" 2>/dev/null | head -1)

中

SKILL.zh-CN.md:138

Hidden file access

cat ~/.claude/settings.json 2>/dev/null || echo '{"permissions":{"allow":[]}}'

中

SKILL.zh-CN.md:171

Hidden file access

1. 读取 `~/.claude/settings.json`

中

SKILL.zh-CN.md:198

Hidden file access

| `cat ~/.claude/*` | `Bash(cat ~/.claude/*)` |

中

SKILL.zh-CN.md:273

Hidden file access

📁 位置: ~/.claude/skills/dangerous-skill

中

SKILL.zh-CN.md:284

Hidden file access

- Bash(cat ~/.claude/*)

中

SKILL.zh-CN.md:316

Hidden file access

📁 位置: ~/.claude/skills/port-allocator

中

SKILL.zh-CN.md:328

Hidden file access

- Bash(cat ~/.claude/*)

中

SKILL.zh-CN.md:359

Hidden file access

- Bash(cat ~/.claude/*)

中

SKILL.zh-CN.md:363

Hidden file access

配置文件: ~/.claude/settings.json

中

SKILL.zh-CN.md:382

Hidden file access

- **权限配置**: `~/.claude/settings.json`

中

SKILL.zh-CN.md:383

Hidden file access

- **skill 目录**: `~/.claude/skills/`

中

SKILL.zh-CN.md:426

Hidden file access

1. 读取 `~/.claude/settings.json`

中

SKILL.zh-CN.md:433

Hidden file access

"Bash(find ~/.claude/skills *)",

中

SKILL.zh-CN.md:434

Hidden file access

"Bash(cat ~/.claude/*)"

中

SKILL.zh-CN.md:459

Hidden file access

- Bash(find ~/.claude/skills *)

中

SKILL.zh-CN.md:460

Hidden file access

- Bash(cat ~/.claude/*)

中

SKILL.zh-CN.md:462

Hidden file access

配置文件: ~/.claude/settings.json

风险因素

⚙️ 外部命令 (50)

📁 文件系统访问 (50)

检测到的模式

System reconnaissance×2

审计者: claude 查看审计历史 →

分享与引用此报告

分享版本化评估报告、中性徽章、嵌入卡片和引用。Skillstore 只报告证据，不判断该 Skill 是否安全。

打开版本化报告

复制报告链接

https://skillstore.io/skills/guo-yu-skill-permissions/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

[![Skillstore security assessment](https://skillstore.io/badges/skills/guo-yu-skill-permissions/security.svg)](https://skillstore.io/skills/guo-yu-skill-permissions?utm_source=security_passport_badge)

HTML 徽章

<a href="https://skillstore.io/skills/guo-yu-skill-permissions?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/guo-yu-skill-permissions/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

嵌入卡片

<iframe src="https://skillstore.io/embed/skills/guo-yu-skill-permissions.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

学术引用 (APA · BibTeX · CFF)

APA 引用

guo-yu. (2026). skill-permissions security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/guo-yu-skill-permissions/audits/6

BibTeX 引用

@techreport{guo-yu-guo-yu-skill-permissions-2026,
  author = {guo-yu},
  title = {skill-permissions security audit report (audit version 6)},
  institution = {Skillstore},
  year = {2026},
  number = {6},
  url = {https://skillstore.io/skills/guo-yu-skill-permissions/audits/6},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "skill-permissions security audit report (audit version 6)"
version: "unspecified"
type: report
authors:
  - name: "guo-yu"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/guo-yu-skill-permissions/audits/6"
identifiers:
  - type: other
    value: "skillstore:guo-yu-skill-permissions:audit:6"
    description: "Skillstore immutable audit report identifier"

Skillstore 评分

评分依据证据置信度: 中

架构

可维护性

内容

社区

规范符合性

你能构建什么

审查新的社区技能

在授予 Claude Code Bash 权限之前，分析单个已下载的技能。

准备本地技能集

在团队设置会话之前，汇总已安装技能的权限。

记录权限需求

生成 allow 命令指南，用于说明某个技能所需的权限。

试试这些提示

分析一个技能

使用 skill-permissions 分析 <skill-name> 所需的权限，并解释每项请求的权限。

授权前审查

对 <skill-name> 运行只读技能权限分析。在我批准建议的 allow 规则之前，不要修改设置。

审计所有已安装技能

分析所有已安装的 Claude Code 技能，并按低、中、高权限风险对结果分组。

规划受控授权

分析所有技能，识别不应自动批准的权限，并仅为已审查的技能准备明确的 allow 命令。

最佳实践

在使用任何授权命令之前，先运行只读分析。
优先使用明确的按技能授权，而不是 allow-all 或 inject 模式。
在将生成的通配符权限添加到 settings.json 之前先进行审查。

避免

不要对未经审查的社区技能运行批量授权。
不要将生成的 allow 规则视为技能安全的证明。
不要在没有版本控制或备份的情况下，将 allow 命令注入大量技能文件。

常见问题

此技能会执行检测到的命令吗？

文档中记录的分析流程会扫描技能文件并生成权限规则。授权命令会修改 Claude Code 设置。

为什么此技能对安全性敏感？

它可以添加 Bash allow 规则，并且在批处理模式下可以修改设置或技能文档。

我应该使用 allow-all 吗？

只有在审查每一项生成的权限后，才使用 allow-all。按技能授权更安全。

它能检测恶意技能吗？

它可以突出显示危险的命令模式，但不能替代完整的安全审查。

它会触及哪些文件？

文档引用了 ~/.claude/settings.json 以及 ~/.claude/skills 下的已安装技能文件。

新权限何时生效？

该技能说明，权限更新会在新会话中或运行 /clear 后生效。

开发者详情

作者

guo-yu

许可证

MIT

Skillstore 修订

版本提示

作者未声明版本。

仓库

https://github.com/guo-yu/skills/tree/master/skill-permissions

引用

1ffa7643651792ccb4bd3b15d924d2c97edff755

维护新鲜度

2026/7/24

使用量

5 次下载 · 275 次浏览

文件结构

📄 SKILL.ja.md

📄 SKILL.md

📄 SKILL.zh-CN.md

guo-yu 的更多技能

查看全部

📦

skill-i18n

全局翻译技能文档

技能文档通常需要为国际用户提供本地化版本。此技能可帮助 Claude、Codex 和 Claude Code 翻译 SKILL.md 和 README.md，同时保留技术文本。

文档查看

📦

share-skill

使用 Git 分享 Claude Skills

本地 Claude skills 难以进行版本管理、发布，并在多台机器之间复用。此 skill 会指导你将其迁移到仓库中，配置远程仓库，并生成用于分享的文档。

DevOps 与基础设施查看

📦

port-allocator

分配本地开发端口

当多个 AI 编码会话启动开发服务器时，本地项目可能会发生冲突。此技能会分配可预测的端口范围，并记录下来以便重复使用。

DevOps 与基础设施查看

查看全部

📦

building-agents

构建 Claude Code 智能体

由 C0ntr0lledCha0s

创建可靠的 AI 智能体需要清晰的 schema、安全的工具和可重复的审查步骤。此技能为 Claude Code 工作流中的智能体设计、验证、迁移和维护提供指导。

编码与开发查看

📦

agent-development

构建 Claude Code 智能体

由 Dami-Randle

如果缺少结构，设计可靠的 Claude Code 智能体会很困难。此技能为智能体提示词、触发器、工具和元数据提供模板、验证规则和示例。

编码与开发查看

📦

building-commands

构建 Claude Code 斜杠命令

由 C0ntr0lledCha0s

团队需要易于调用和审查的可重复 AI 工作流。此技能可帮助创建、更新、验证和记录 Claude Code 斜杠命令。

编码与开发查看

📦

building-plugins

构建 Claude Code 插件

由 C0ntr0lledCha0s

创建 Claude Code 插件需要正确的结构、验证、文档和安全打包。此技能将指导用户完成插件架构、模板、验证和发布工作流。

DevOps 与基础设施查看

📦

building-hooks

构建 Claude Code 自动化钩子

由 C0ntr0lledCha0s

Claude Code hooks 可以自动执行检查、格式化和策略强制执行，但不安全的 hook 脚本可能会影响本地文件或命令。此技能会引导用户进行结构化的 hook 设计、验证和维护。

DevOps 与基础设施查看

📦

writing-hookify-rules

为 Claude Code 编写 Hookify 规则

由 anthropics

在 bash、file、stop 和 prompt 事件中正确编写 hook 规则可能并不容易。此技能为 Claude、Codex 和 Claude Code 提供创建和测试 Hookify 规则的实用指导。

DevOps 与基础设施查看

skill-permissions

使用我的智能体安装

Agent 可读资源

测试它

安全审计

已确认安全问题 (4)

风险因素

检测到的模式

复制报告链接

Markdown 徽章

HTML 徽章

嵌入卡片

APA 引用

BibTeX 引用

CITATION.cff

Skillstore 评分

你能构建什么

审查新的社区技能

准备本地技能集

记录权限需求

试试这些提示

最佳实践

避免

常见问题

开发者详情

guo-yu 的更多技能

skill-i18n

share-skill

port-allocator

相关技能

building-agents

agent-development

building-commands

building-plugins

building-hooks

writing-hookify-rules