Token导航 LogoToken导航

Agent Skill · 研究检索

system(系统)

system 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

system 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证为 MIT,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 36,592。

总安装 1,901周安装 80GitHub Stars 11,771下载 666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:system(系统)
来源仓库:https://github.com/danielmiessler/personal_ai_infrastructure
仓库路径:skills/system
安装命令:
npx skills add https://github.com/danielmiessler/personal_ai_infrastructure --skill System
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/danielmiessler/personal_ai_infrastructure --skill System

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

system 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。适用于系统相关的研究与检索场景,可结合来源仓库进一步核验具体用法。

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。安装前建议确认是否会触发联网、命令执行或文件读写等操作。system 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/system

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/danielmiessler/personal_ai_infrastructure --sk…;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

    它需要需要联网,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

system 怎么安装?

在终端执行 npx skills add https://github.com/danielmiessler/personal_ai_infrastructure --skill System。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

system 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。

system 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

system 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。

system 用的人多吗?

公开数据是累计安装 1,901 次,近一周安装 80 次,下载 666 次,GitHub 11,771 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。

system 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

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。
  • 来源仓库有 11,771 星,维护活跃度相对可查。

先想清楚的地方

  • 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。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
system

系统 · 本页

1,90111,771需要联网MIT未通过

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

Customization

Before executing, check for user customizations at: ~/.claude/skills/CORE/USER/SKILLCUSTOMIZATIONS/System/

If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.

System Skill

System validation, integrity audits, documentation tracking, and security scanning for the PAI system.

Visibility

This skill runs in the foreground so you can see all output, progress, and hear voice notifications as work happens. Documentation updates, integrity checks, and other system operations should be visible to maintain transparency.


Voice Notification

When executing a workflow, do BOTH:

  1. Send voice notification: curl -s -X POST http://localhost:8888/notify \ -H "Content-Type: application/json" \ -d '{"message": "Running WORKFLOWNAME workflow from System skill"}' \ > /dev/null 2>&1 &
  2. Output text notification: Running the **WorkflowName** workflow from the **System** skill...

Workflow Routing

Core Operations (The Three)

WorkflowTriggerPurposeFile
IntegrityCheck"integrity check", "audit system", "check references", "system health"Find and fix broken references across the systemWorkflows/IntegrityCheck.md
DocumentSession"document session", "document today", "document this session", "log session"Document current session's work from transcriptWorkflows/DocumentSession.md
DocumentRecent"document recent", "catch up docs", "what's undocumented", "document since last update"Catch-up documentation for changes since last documented updateWorkflows/DocumentRecent.md

Composition Rules:

  • Integrity Check → may produce fixes → Document Session
  • After any session → Document Session
  • Periodic catch-up → Document Recent

Security Workflows

WorkflowTriggerFile
SecretScanning"check for secrets", "scan for credentials", "security scan"Workflows/SecretScanning.md
PrivacyCheck"privacy check", "check for sensitive data", "data isolation"Workflows/PrivacyCheck.md

Utility Workflows

WorkflowTriggerFile
WorkContextRecall"we just worked on", "what did we do with", "remember when we", "didn't we already"Workflows/WorkContextRecall.md

Note: For public PAI integrity ("check PAI integrity", "audit PAI packs"), use the PAI skill → PAIIntegrityCheck.md


Examples

Core Operations

Example 1: Integrity Check

User: "Run an integrity check"
→ Invokes IntegrityCheck workflow
→ Spawns parallel agents to audit ~/.claude
→ Finds broken references, missing files
→ Returns list of issues found/fixed

Example 2: Document Current Session

User: "Document this session"
→ Invokes DocumentSession workflow
→ Reads current session transcript
→ Uses AI to extract what changed and why
→ Creates entry in MEMORY/PAISYSTEMUPDATES/

Example 3: Catch-up Documentation

User: "What's undocumented? Catch up the docs."
→ Invokes DocumentRecent workflow
→ Finds last documented update timestamp
→ Compares git history since then
→ Generates documentation for missed changes

Security Workflows

Example 4: Secret Scanning

User: "Check for secrets before I push"
→ Invokes SecretScanning workflow
→ Runs TruffleHog on specified directory
→ Reports any API keys, credentials found

Utility

Example 5: Recall Past Work

User: "We just worked on the status line - why broken again?"
→ Invokes WorkContextRecall workflow
→ Searches MEMORY/, git history for "status line"
→ Presents timeline of changes and possible regression

Quick Reference

The Three Core Operations

OperationInputOutputDuration
IntegrityCheckCodebase scanList of broken refs found/fixed~2-5 min
DocumentSessionSession transcriptPAISYSTEMUPDATES entry~30s
DocumentRecentGit history since last updateMultiple PAISYSTEMUPDATES entries~1-2 min

Composition Patterns

End of Session:     DocumentSession
After Refactoring:  IntegrityCheck → DocumentSession
Catch-up:           DocumentRecent

Security Audits

Audit TypeToolScopeDuration
Secret ScanTruffleHogAny directory~30s-2min
Privacy Checkgrep/patternsskills/ (excl USER/WORK)~30s

Documentation Format

Verbose Narrative Structure:

  • The Story (1-3 paragraphs): Background, Problem, Resolution
  • How It Used To Work: Previous state with bullet points
  • How It Works Now: New state with improvements
  • Going Forward: Future implications
  • Verification: How we know it works

When to Use

Integrity Checks

  • After major refactoring
  • Before releasing updates
  • Periodic system health checks
  • When something "feels broken"
  • Before pushing to public PAI repo

Documentation

  • End of significant work sessions
  • After creating new skills/workflows/tools
  • When architectural decisions are made
  • To maintain system history

Security Scanning

  • Before any git commit to public repos
  • When auditing for credential leaks
  • Periodic security hygiene checks
  • After receiving external code/content

Privacy Validation

  • After working with USER/ or WORK/ content
  • Before any public commits
  • When creating new skills that might reference personal data
  • Periodic audit to ensure data isolation

Work Context Recall

  • When user asks about past work ("we just fixed that")
  • Questions about why decisions were made
  • Finding artifacts from previous sessions
  • Debugging something that was "already fixed"
  • Resuming multi-session projects

Tools

ToolPurposeLocation
SecretScan.tsTruffleHog wrapper for credential detectionCORE/Tools/SecretScan.ts
CreateUpdate.tsCreate new system update entriesTools/CreateUpdate.ts
UpdateIndex.tsRegenerate index.json and CHANGELOG.mdTools/UpdateIndex.ts
UpdateSearch.tsSearch and query system updatesTools/UpdateSearch.ts
ExtractArchitectureUpdates.tsHistorical migration tool (one-time use)Tools/ExtractArchitectureUpdates.ts

Templates

TemplatePurposeLocation
Update.mdTemplate for system update entriesTemplates/Update.md

Output Locations

OutputLocation
Integrity ReportsMEMORY/STATE/integrity/YYYY-MM-DD.md
System UpdatesMEMORY/PAISYSTEMUPDATES/YYYY/MM/*.md
Update IndexMEMORY/PAISYSTEMUPDATES/index.json
ChangelogMEMORY/PAISYSTEMUPDATES/CHANGELOG.md

Related Skills

  • PAI - Public PAI repository management (includes PAIIntegrityCheck)
  • CORE - System architecture and memory documentation
  • Evals - Regression testing and capability verification

平台分布

Claude Code

27.67%
按下载量换算184

Gemini CLI

22.62%
按下载量换算151

OpenCode

17.55%
按下载量换算117

clawdbot

15.16%
按下载量换算101

Cursor

8.13%
按下载量换算54

Codex

3.91%
按下载量换算26

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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