OpenParable
Skip to content
← Back to skills

Deep Penetration Cavalry Raid

Others
deep-penetration-cavalry-raid

Deep Penetration Cavalry Raid is an Agent Skill for general use published in the baojie/shiji-kb repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Use when planning rapid cavalry raids deep into enemy territory. Based on Huo Qubing's campaigns: select elite riders, travel light (约轻赍), live off enemy resources (取食於敌), strike symbolic targets like 狼居胥山, and return before enemy concentrates.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/baojie/shiji-kb/blob/HEAD/kg/ontology/ontology-v1/skus/procedural/skill_224/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/deep-penetration-cavalry-raid, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Deep Penetration Cavalry Raid

Overview

Tactical procedure for light cavalry forces to penetrate deep into enemy territory, strike targets, and return successfully. Based on Huo Qubing's campaigns.

Key Principles

  • Travel light (约轻赍)
  • Move faster than intelligence can travel
  • Accept risk of being cut off
  • Live off the land when possible

Steps

  1. Select Elite Forces

    • Choose best cavalry and riders
    • Limit baggage and supplies
    • Include only the most capable
  2. Advance Rapidly

    • Leave main force behind
    • Travel hundreds of li ahead
    • Cross mountains, rivers, and deserts
  3. Engage Multiple Targets

    • Attack smaller kingdoms and settlements
    • Do not stop to occupy or process all captives
    • Keep moving toward primary objective
  4. Live Off Enemy Resources

    • Seize enemy food and supplies
    • Use captured horses
    • "取食於敌" - obtain food from the enemy
  5. Achieve Deep Objectives

    • Reach symbolic locations (e.g., 狼居胥山)
    • Conduct ceremonies to mark achievement
    • Demonstrate reach beyond enemy expectations
  6. Return with Captures

    • Bring captured nobles and soldiers
    • Return before enemy can concentrate forces

Success Factors

  • Speed over security
  • Quality of troops over numbers
  • Willingness to take risks
  • Good fortune (天幸)

Expected Outcome

Deep penetration into enemy heartland, capture of high-value targets, psychological impact on enemy, and enhanced reputation.

Verification

  • Confirm the raiding force consists of elite cavalry only, with minimal baggage to maintain speed
  • Validate that the force is successfully living off captured enemy resources and not relying on overstretched supply lines
  • Check that the return is executed before the enemy can concentrate forces to cut off the withdrawal route