thor-skills — AIエージェント开发 thor-skills, thor-skill, community, AIエージェント开发, ide skills, LLM技能, 全局规则执行, 子技能路由, 法医学工作流, 安全更改机制

v1.0.0

关于此技能

非常适合需要标准化和可重复工作流的法医分析代理,特别是与LLMs一起使用 THOR技能是一种AIエージェント技能,用于路由请求和执行全局规则

功能特性

子技能路由
全局规则执行
明确的命令和输出目录
安全的更改机制
法医学/实验室工作流支持

# 核心主题

NextronSystems NextronSystems
[0]
[0]
更新于: 3/23/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 5/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Concrete use-case guidance Explicit limitations and caution
Review Score
5/11
Quality Score
35
Canonical Locale
en
Detected Body Locale
en

非常适合需要标准化和可重复工作流的法医分析代理,特别是与LLMs一起使用 THOR技能是一种AIエージェント技能,用于路由请求和执行全局规则

核心价值

强制执行全局规则以确保安全和可重复的命令,提供明确的路径和输出目录,同时保持更改的安全性,并默认为法医和实验室工作流,同时防止THOR标志或行为的发明

适用 Agent 类型

非常适合需要标准化和可重复工作流的法医分析代理,特别是与LLMs一起使用

赋予的主要能力 · thor-skills

将请求路由到正确的子技能以实现高效的工作流管理
强制执行法医分析中的可重复命令的全局规则
防止意外的系统修改或证据删除

! 使用限制与门槛

  • 需要遵守全局规则
  • 默认焦点是法医和实验室工作流
  • 可能需要显式用户输入来执行某些操作

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The page lacks a strong recommendation layer.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作,再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”,而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核,以及是否已经进入工作流落地阶段。

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致,便于搜索引擎理解页面内容。

? FAQ

thor-skills 是什么?

非常适合需要标准化和可重复工作流的法医分析代理,特别是与LLMs一起使用 THOR技能是一种AIエージェント技能,用于路由请求和执行全局规则

如何安装 thor-skills?

运行命令:npx killer-skills add NextronSystems/thor-skill/thor-skills。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

thor-skills 适用于哪些场景?

典型场景包括:将请求路由到正确的子技能以实现高效的工作流管理、强制执行法医分析中的可重复命令的全局规则、防止意外的系统修改或证据删除。

thor-skills 支持哪些 IDE 或 Agent?

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

thor-skills 有哪些限制?

需要遵守全局规则;默认焦点是法医和实验室工作流;可能需要显式用户输入来执行某些操作。

安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行:npx killer-skills add NextronSystems/thor-skill/thor-skills。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    thor-skills 已启用,可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考,但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论,再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

thor-skills

安装 thor-skills,这是一款面向AI agent workflows and automation的 AI Agent Skill。查看评审结论、使用场景与安装路径。

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

THOR Skills

This is the root skill. It routes requests to the right sub-skill and enforces a few global rules.

Global rules

  • Don't invent THOR flags or behavior. If something is unclear, ask for the missing detail instead of guessing.
  • Prefer reproducible commands: explicit paths, explicit output directory, explicit mode.
  • Keep changes safe: don't recommend deleting evidence or modifying the target system unless the user explicitly asks.
  • Default focus is forensic / lab workflows. If it's live endpoint scanning, call that out and keep it conservative.
  • THOR versions: v10 is stable; v11 is TechPreview. Some features are v11-only. In particular, THOR Lens relies on the audit trail output, which requires THOR v11 and is not available in THOR v10.
  • THOR Lite vs full THOR: Lite is a free scanner with reduced features (~5 modules, ~4k open source signatures, no Sigma, no lab mode, no audit trail). Identify which version the user has before troubleshooting missing features.

Routing rules

  • If the user wants to run a scan or asks "what command should I run" - use thor-scan (also covers THOR Lite scanning with appropriate flag adjustments).
  • If the user pasted results or asks "what does this finding mean" - use thor-log-analysis.
  • If the user reports hangs, slowness, crashes, missing output, license/update weirdness - use thor-troubleshooting.
  • If the user asks about update/upgrade/report generation/yara-forge/offline packs - use thor-maintenance.
  • If the user asks about THOR Lens, forensic timeline viewing, importing audit trails, or MCP integration for timeline analysis - use thor-lens (note: requires full THOR v11, not compatible with THOR Lite).
  • If the user asks about thor10.db/thor11.db, scan timing, performance tuning, slow rules, or resume state - use thor-db.
  • If the user asks why a feature is missing, expects full THOR behavior from Lite, or asks about Lite limitations - use thor-lite.
  • If the user wants to write a plugin, extend THOR functionality, parse custom formats, or asks about the plugin API - use thor-plugins (requires THOR v11+).
  • If the user wants to create custom IOCs, YARA rules, Sigma rules, STIX indicators, or asks about the custom-signatures folder - use custom-signatures.

Minimum inputs to collect (only what's needed)

  • OS (Windows/Linux/macOS)
  • THOR version (v10 or v11) and install path
  • License situation if relevant (lab vs standard vs unknown)
  • Target type: live path vs mounted image vs memory dump vs log-only analysis
  • Where outputs/logs should go

Available Skills

  • thor-scan/ - Run THOR scans and produce the exact command line for the target scenario
  • thor-log-analysis/ - Triage and interpret THOR logs and findings
  • thor-troubleshooting/ - Diagnose stuck/slow/failed THOR runs and recommend next actions
  • thor-maintenance/ - Update/upgrade THOR, manage signature packs, generate reports
  • thor-lens/ - THOR Lens forensic timeline viewer; import audit trails, web UI, MCP integration (requires THOR v11)
  • thor-db/ - Analyze ThorDB (thor10.db/thor11.db) for performance tuning and diagnostics
  • thor-lite/ - THOR Lite limitations, workarounds, and guidance for the free scanner
  • thor-plugins/ - Write custom THOR plugins to extend scanner functionality (requires THOR v11+)
  • custom-signatures/ - Create custom IOCs, YARA rules, Sigma rules, and STIX indicators

相关技能

寻找 thor-skills 的替代方案 (Alternative) 或可搭配使用的同类 community Skill?探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

149.6k
0
AI

flags

Logo of vercel
vercel

React 框架

138.4k
0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

98.6k
0
开发者工具