Token导航 LogoToken导航

Agent Skill · AI 工具

settings-management(设置管理)

settings-management 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

settings-management 是AI 工具类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证为 MIT,第三方扫描有提醒项,按安装量在AI 工具类的 2,536 个 Skill 里排第 2,262。

总安装 261周安装 11GitHub Stars 61下载 92核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:settings-management(设置管理)
来源仓库:https://github.com/melodic-software/claude-code-plugins
仓库路径:skills/settings-management
安装命令:
npx skills add https://github.com/melodic-software/claude-code-plugins --skill settings-management
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/melodic-software/claude-code-plugins --skill settings-management

这个 Skill 是做什么的

AI 工具类 Skill 用来扩展助手本身的能力,例如接模型、接检索、接外部服务。

settings-management 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态、代码变更或协作事项进行整理时使用。

它支持按来源仓库、安装命令和原始 README 核验具体用法,适用于开发协作与代码管理场景。通过 npx skills add 命令从指定 GitHub 仓库安装,需确认权限范围和维护状态后再部署。安装前建议检查是否会触发联网、命令执行或文件读写,避免误操作影响系统安全。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/settings-management

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/melodic-software/claude-code-plugins --skill s…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

settings-management 怎么安装?

在终端执行 npx skills add https://github.com/melodic-software/claude-code-plugins --skill settings-ma…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

settings-management 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

settings-management 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

settings-management 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

settings-management 用的人多吗?

公开数据是累计安装 261 次,近一周安装 11 次,下载 92 次,GitHub 61 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

settings-management 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理AI 工具类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

AI 工具类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
executing-plans

执行计划 · Codex、Claude

1,515,336173,110只读MIT通过
verification-before-completion

完成前的验证 · Codex、Claude

1,319,472173,121权限未标注MIT通过
subagent-driven-development

子 Agent 驱动开发 · Codex、Claude

1,312,416173,138只读MIT通过
copy-editing

复制编辑 · Codex、Claude

1,209,57625,632只读MIT通过
paywall-upgrade-cro

付费专区升级 cro · Codex、Claude

1,030,17625,617只读MIT通过
settings-management

设置管理 · 本页

26161接触敏感数据MIT有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Configuration Meta Skill

🚨 MANDATORY: Invoke docs-management First

STOP - Before providing ANY response about Claude Code configuration or settings: 1. INVOKE docs-management skill 2. QUERY for the user's specific topic 3. BASE all responses EXCLUSIVELY on official documentation loaded Skipping this step results in outdated or incorrect information.

Verification Checkpoint

Before responding, verify:

  • Did I invoke docs-management skill?
  • Did official documentation load?
  • Is my response based EXCLUSIVELY on official docs?

If ANY checkbox is unchecked, STOP and invoke docs-management first.


Overview

Central authority for Claude Code configuration and settings. This skill uses 100% delegation to docs-management - it contains NO duplicated official documentation.

Architecture: Pure delegation with keyword registry. All official documentation is accessed via docs-management skill queries.

When to Use This Skill

Keywords: settings, configuration, settings.json, environment variables, permissions, sandbox, enterprise settings, managed-settings.json, user settings, project settings, local settings, tools, hooks configuration, model configuration, plugin settings, precedence

Use this skill when:

  • Configuring settings.json files
  • Understanding settings hierarchy and precedence
  • Setting up permission rules (allow, deny, ask)
  • Configuring sandbox settings
  • Managing enterprise policies
  • Setting environment variables
  • Understanding available tools
  • Configuring plugin settings
  • Troubleshooting configuration issues

Keyword Registry for docs-management Queries

Use these keywords when querying docs-management skill for official documentation:

Settings Files

TopicKeywords
Overview"settings", "settings.json", "configuration files"
User Settings"user settings", "~/.claude/settings.json"
Project Settings".claude/settings.json", "project settings"
Local Settings"settings.local.json", "local settings"
Enterprise"managed-settings.json", "enterprise managed policy"

Available Settings

TopicKeywords
Settings Table"available settings", "settings options"
Model Setting"model setting", "model override"
Hooks Setting"hooks setting", "disableAllHooks"
Output Style"outputStyle setting", "output style config"
Status Line"statusLine setting", "status line config"
API Key Helper"apiKeyHelper", "custom script auth"
Keybindings"keybindings.json", "keyboard shortcuts config", "custom keybindings"
Plans Directory"plansDirectory", "plans directory setting", "plan file storage"
Turn Duration"showTurnDuration", "turn duration display", "timing display"

Permissions

TopicKeywords
Permission Settings"permission settings", "allow deny ask rules"
Allow Rules"permissions allow", "allow tool rules"
Deny Rules"permissions deny", "deny tool rules", "excluding sensitive files"
Ask Rules"permissions ask", "confirmation rules"
Default Mode"defaultMode", "permission modes"

Sandbox

TopicKeywords
Sandbox Settings"sandbox settings", "bash sandboxing"
Sandbox Network"sandbox network", "allowUnixSockets", "allowLocalBinding"
Excluded Commands"excludedCommands", "sandbox exclusions"
Auto Allow"autoAllowBashIfSandboxed", "auto-approve sandboxed"

Precedence

TopicKeywords
Settings Precedence"settings precedence", "configuration hierarchy"
Override Order"enterprise project user precedence", "settings override"

Environment Variables

TopicKeywords
Environment Variables"environment variables", "ANTHROPIC_API_KEY"
Model Variables"ANTHROPIC_MODEL", "model environment"
Proxy Variables"HTTP_PROXY", "HTTPS_PROXY", "proxy configuration"
Telemetry Variables"DISABLE_TELEMETRY", "telemetry settings"
Bedrock Variables"CLAUDE_CODE_USE_BEDROCK", "bedrock environment"
Vertex Variables"CLAUDE_CODE_USE_VERTEX", "vertex environment"
Temp Directory"CLAUDE_CODE_TMPDIR", "temporary directory", "temp file location"
Background Tasks"CLAUDE_CODE_DISABLE_BACKGROUND_TASKS", "disable background tasks", "background process control"

Plugins

TopicKeywords
Plugin Configuration"plugin configuration", "enabledPlugins"
Marketplaces"extraKnownMarketplaces", "plugin marketplaces config"

JSON Schema

TopicKeywords
Custom Schema"settings schema", "JSON schema", "claude-code-settings.schema.json"
Schema Location"custom schema", "extended schema", "SchemaStore"
Schema Updates"update schema", "schema refresh", "/update-settings-schema"
Schema Validation"validate schema", "schema compliance", "draft-07"

Tools

TopicKeywords
Available Tools"tools available to Claude", "tool table"
Tool Permissions"tool permissions", "permission required tools"

Quick Decision Tree

What do you want to do?

  1. Configure settings file -> Query docs-management: "settings.json", "available settings"
  2. Set up permissions -> Query docs-management: "permission settings", "allow deny rules"
  3. Configure sandbox -> Query docs-management: "sandbox settings", "bash sandboxing"
  4. Understand precedence -> Query docs-management: "settings precedence", "configuration hierarchy"
  5. Set environment variables -> Query docs-management: "environment variables", specific variable name
  6. Configure enterprise policy -> Query docs-management: "managed-settings.json", "enterprise managed policy"
  7. Set up plugin settings -> Query docs-management: "plugin configuration", "enabledPlugins"
  8. Understand available tools -> Query docs-management: "tools available to Claude"
  9. Exclude sensitive files -> Query docs-management: "excluding sensitive files", "deny rules"
  10. Configure model -> Query docs-management: "model setting", "ANTHROPIC_MODEL"
  11. Troubleshoot config issues -> Query docs-management: "configuration troubleshooting" + specific issue

Topic Coverage

⚠️ STALENESS WARNING: The lists below are for navigation reference only. ALWAYS query docs-management for the authoritative, current list of settings fields, environment variables, and configuration options. These change with Claude Code releases.

Settings File Types

Query Pattern: docs-management: "settings.md file types locations"

  • User settings, project settings, local settings
  • Enterprise policies (managed settings)
  • Platform-specific paths

Key Settings Options

Query Pattern: docs-management: "settings.md available settings table"

Categories include: authentication helpers, cleanup, announcements, environment, permissions, hooks, model, output styling, status line. Query docs-management for the complete list of current settings fields.

Permission Settings

Query Pattern: docs-management: "settings.md permission settings allow deny ask"

Covers: allow/deny/ask rules, additional directories, default mode, bypass mode controls.

Sandbox Settings

Query Pattern: docs-management: "settings.md sandbox settings network"

Covers: enabled flag, auto-allow behavior, excluded commands, network settings (sockets, binding, proxies).

Settings Precedence

Query Pattern: docs-management: "settings.md precedence hierarchy"

Order (query docs-management for current precedence rules).

Environment Variable Categories

Query Pattern: docs-management: "settings.md environment variables"

Categories: authentication, model config, provider settings, proxy, telemetry, tool behavior.

Plugin Configuration

Query Pattern: docs-management: "settings.md plugin configuration enabledPlugins"

Covers: enabled plugins map, marketplace sources.

Tools Available to Claude

Query Pattern: docs-management: "interactive-mode.md tools available to Claude"

Categories: file operations, execution, user interaction, specialized tools, notebook editing.

Delegation Patterns

Standard Query Pattern

User asks: "How do I configure permissions?"

1. Invoke docs-management skill
2. Use keywords: "permission settings", "allow deny rules"
3. Load official documentation
4. Provide guidance based EXCLUSIVELY on official docs

Multi-Topic Query Pattern

User asks: "I want enterprise settings with sandbox and restricted permissions"

1. Invoke docs-management skill with multiple queries:
   - "managed-settings.json", "enterprise managed policy"
   - "sandbox settings", "bash sandboxing"
   - "permission settings", "deny rules"
2. Synthesize guidance from official documentation

Troubleshooting Pattern

User reports: "My settings aren't taking effect"

1. Invoke docs-management skill
2. Use keywords: "settings precedence", "configuration hierarchy"
3. Guide user through precedence rules from official docs

Troubleshooting Quick Reference

IssueKeywords for docs-management
Settings not applied"settings precedence", "configuration hierarchy"
Permission denied"permission settings", "deny rules"
Sandbox blocking commands"sandbox settings", "excludedCommands"
Environment variable not working"environment variables", specific variable name
Enterprise policy override"managed-settings.json", "enterprise policy"
Plugin not loading"plugin configuration", "enabledPlugins"
Tool not available"tools available", "tool permissions"

Repository-Specific Notes

This repository has project-level settings in .claude/settings.json including:

  • Custom hooks configuration
  • Permission rules
  • Model settings

When modifying this repository's settings, ensure changes align with the hook-management skill guidance for hook configurations.

Auditing Settings

This skill provides the validation criteria used by the settings-auditor agent for formal audits.

Audit Resources

ResourceLocationPurpose
Audit Frameworkreferences/audit-framework.mdQuery guides and scoring criteria

Scoring Categories

CategoryPointsKey Criteria
JSON Validity20Valid syntax, well-formed
Schema Compliance25Only valid settings options
Permission Rules25Valid patterns, appropriate restrictions
Environment Config15Valid env vars, no secrets
Precedence Awareness15Correct scope usage

Thresholds: 85+ = PASS, 70-84 = PASS WITH WARNINGS, <70 = FAIL

Related Agent

The settings-auditor agent (Haiku model) performs formal audits using this skill:

  • Auto-loads this skill via skills: settings-management
  • Uses audit framework and docs-management for rules
  • Generates structured audit reports
  • Invoked by /audit-settings command

External Technology Validation

When auditing settings that reference external technologies (scripts, packages, runtimes), the auditor MUST validate claims using MCP servers before flagging findings.

Technologies Requiring MCP Validation:

  • .NET/C# scripts: Validate with microsoft-learn + perplexity
  • Node.js/npm packages: Validate with context7 + perplexity
  • Python scripts/packages: Validate with context7 + perplexity
  • Shell scripts: Validate with perplexity
  • Any version-specific claims: ALWAYS validate with perplexity

Validation Rule:

Never flag a technology usage as incorrect without first:

  1. Querying appropriate MCP server(s) for current documentation
  2. Verifying with perplexity for recent changes (especially.NET 10+)
  3. Documenting MCP sources in the finding

Stale Data Warning:

  • microsoft-learn can return cached/outdated documentation
  • ALWAYS pair microsoft-learn with perplexity for version verification
  • Trust perplexity for version numbers and recently-released features

VS Code Integration

This plugin provides an extended JSON Schema for Claude Code settings that enables IntelliSense in VS Code.

Schema Association Options

Option 1: Workspace Settings (Recommended)

Add to .vscode/settings.json:

{
  "json.schemas": [
    {
      "fileMatch": ["**/.claude/settings.json", "**/.claude/settings.local.json"],
      "url": "./plugins/claude-ecosystem/skills/settings-management/references/claude-code-settings.schema.json"
    }
  ]
}
Option 2: In-File Schema Reference

Add at the top of your settings.json:

{
  "$schema": "https://raw.githubusercontent.com/melodic/claude-code-plugins/main/plugins/claude-ecosystem/skills/settings-management/references/claude-code-settings.schema.json"
}

Note: In-file $schema references override workspace settings. Use workspace settings for flexibility.

Environment Variable IntelliSense

The schema includes 68+ environment variables with:

  • Full autocomplete for all official env var names
  • Descriptions and categories for each variable
  • enum: ["0", "1"] for boolean flags (type safety)
  • Deprecation markers for obsolete variables

Try it: In your settings.json, type "env": {"A and VS Code will autocomplete ANTHROPIC_API_KEY, ANTHROPIC_MODEL, etc.

Schema Version

The schema tracks Claude Code versions and includes version history:

FieldPurpose
x-schema-versionPlugin schema version (e.g., 1.1.0)
x-claude-code-versionClaude Code version tracked
x-env-var-countNumber of env vars defined (68+)
x-last-updatedLast schema update date

Keeping Schema Updated

Run /update-settings-schema to sync the schema with latest canonical documentation. This extracts new env vars and settings from the official docs.

References

Official Documentation (via docs-management skill):

  • Primary: "settings" documentation
  • Related: "iam", "hooks", "sandboxing", "model-config", "network-config"

Repository-Specific:

  • Project settings: .claude/settings.json
  • Hooks configuration: .claude/hooks/

Version History

  • v1.1.0 (2026-01-16): Added v2.1.4-v2.1.9 keyword registry entries

- Added keybindings.json setting keywords (v2.1.7) - Added plansDirectory setting keywords (v2.1.9) - Added showTurnDuration setting keywords (v2.1.7) - Added CLAUDE_CODE_TMPDIR env var keywords (v2.1.5) - Added CLAUDE_CODE_DISABLE_BACKGROUND_TASKS env var keywords (v2.1.4)

  • v1.0.0 (2025-11-26): Initial release

- Pure delegation architecture - Comprehensive keyword registry - Quick decision tree - Topic coverage for all configuration features - Troubleshooting quick reference


Last Updated

Date: 2026-01-16 Model: claude-opus-4-5-20251101

平台分布

Antigravity

31.73%
按下载量换算29

trae

21.22%
按下载量换算20

windsurf

18.02%
按下载量换算17

Claude Code

12.66%
按下载量换算12

Codex

7.64%
按下载量换算7

Gemini CLI

3.76%
按下载量换算3

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。

继续浏览同类 Skills