Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计通过

ln-650-persistence-performance-auditorln 650 持久性绩效审核员

Agent Skill

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

总安装

6,440

周安装

258

GitHub Stars

437

下载量

2,085
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:ln-650-persistence-performance-auditor(ln 650 持久性绩效审核员)
来源仓库:https://github.com/levnikolaevich/claude-code-skills
仓库路径:skills/ln-650-persistence-performance-auditor
安装命令:
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-650-persistence-performance-auditor
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。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-650-persistence-performance-auditor

简介

用于辅助安全审计、权限检查和常见漏洞排查。

  • 适合梳理敏感配置、检查依赖风险或分析鉴权逻辑。
  • 使用时不能直接采信工具输出,需结合最小权限和脱敏要求确认操作边界。
  • 涉及密钥或生产系统时,应先评估权限范围和影响范围。
  • 建议配合人工复核生成安全复核清单。ln-650-persistence-performance-auditor 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Paths: File paths (shared/, references/, ../ln-*) are relative to skills repo root.

Type: L2 Coordinator Category: 6XX Audit

Persistence Performance Auditor

Mandatory Read

MANDATORY READ: Load shared/references/evaluation_coordinator_runtime_contract.md, shared/references/evaluation_summary_contract.md, shared/references/evaluation_research_contract.md MANDATORY READ: Load shared/references/research_tool_fallback.md

Purpose

  • audit query efficiency, transaction correctness, runtime performance, and resource lifecycle
  • coordinate ln-651 through ln-654
  • require database and framework best-practice research before scoring

Runtime Contract

Runtime family:

  • evaluation-runtime

Identifier:

  • persistence-audit

Phase order:

  1. PHASE_0_CONFIG
  2. PHASE_1_DISCOVERY
  3. PHASE_2_RESEARCH
  4. PHASE_3_DELEGATE
  5. PHASE_4_AGGREGATE
  6. PHASE_5_REPORT
  7. PHASE_6_SELF_CHECK

Worker Set

  • ln-651-query-efficiency-auditor
  • ln-652-transaction-correctness-auditor
  • ln-653-runtime-performance-auditor
  • ln-654-resource-lifecycle-auditor

Worker Invocation (MANDATORY)

Use the Skill tool for delegated workers. Do not inline worker logic inside the coordinator.

TodoWrite format (mandatory):

  • Resolve audit scope and build manifest
  • Load data layer and runtime profile
  • Run best-practice research
  • Delegate to domain audit workers
  • Aggregate worker findings
  • Generate audit report
  • Verify cleanup and self-check

Representative invocations:

Skill(skill: "ln-651-query-efficiency-auditor", args: "{scope}")
Skill(skill: "ln-652-transaction-correctness-auditor", args: "{scope}")
Skill(skill: "ln-653-runtime-performance-auditor", args: "{scope}")
Skill(skill: "ln-654-resource-lifecycle-auditor", args: "{scope}")

Workflow

  1. Start evaluation-runtime.
  2. Discover database, ORM, transaction, and runtime context.
  3. Perform mandatory research.
  4. Delegate specialized workers.
  5. Aggregate findings into one persistence-performance audit.
  6. Write final report and evaluation-coordinator summary.

Definition of Done

  • Evaluation runtime started
  • Persistence context discovered
  • Mandatory research completed
  • All planned worker summaries recorded
  • Aggregate report written
  • evaluation-coordinator summary written
  • Runtime completed

Meta-Analysis

MANDATORY READ: Load shared/references/meta_analysis_protocol.md

After the coordinator run, analyze the session per protocol section 7 and include the protocol-formatted output with the final persistence-performance audit result.

References

  • Workers: ../ln-651-query-efficiency-auditor/SKILL.md, ../ln-652-transaction-correctness-auditor/SKILL.md, ../ln-653-runtime-performance-auditor/SKILL.md, ../ln-654-resource-lifecycle-auditor/SKILL.md

Version: 1.1.0 Last Updated: 2026-03-15

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

38.66%
按下载量换算806

Claude

31.46%
按下载量换算656

Cursor

18.29%
按下载量换算381

Gemini CLI

9.39%
按下载量换算196

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills