Siege Feasibility Assessment
Otherssiege-feasibility-assessmentSiege Feasibility Assessment 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 evaluating siege feasibility or deciding whether to continue besieging a fortified city. Based on Xu Jia's advice against attacking Daliang (大梁) — systematically assessing defender strength, fortification quality, historical precedent, and cost of failure before committing.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/baojie/shiji-kb/blob/HEAD/kg/ontology/ontology-v1/skus/procedural/skill_149/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/siege-feasibility-assessment, 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.
Siege Feasibility Assessment
Based on Xu Jia's advice against attacking Daliang.
Overview
Before committing to a siege, systematically evaluate the probability of success and risks of failure.
Steps
-
Assess Defender Strength
- Estimate number of defenders (e.g., 300,000)
- Evaluate quality of fortifications (e.g., 7-ren high walls)
- Consider defender morale and determination
-
Calculate Historical Precedent
- Would even legendary commanders succeed?
- If answer is no, reconsider the attack
-
Evaluate External Factors
- Are allied forces approaching?
- Will enemies attack your rear if you're committed?
-
Consider Cost of Failure
- What previous gains will be lost?
- Will your own territory become vulnerable?
-
Propose Alternative
- Accept smaller gains now while enemy is uncertain
- Let enemy allies become angry at being preempted
- Benefit from their subsequent competition to serve you
Decision Criteria
- If defenders significantly outnumber attackers: Do not besiege
- If fortifications are formidable: Do not besiege
- If failure means losing previous gains: Withdraw
- If enemy is currently uncertain: Negotiate smaller gains
Expected Outcomes
- Avoid costly failures
- Secure achievable gains
- Preserve forces for future campaigns
Validation
- Apply the historical precedent test honestly — if legendary commanders could not take the city with comparable forces, your chances are no better
- Verify that external factors (approaching allied forces, rear vulnerabilities) have been accounted for in the timeline
- Confirm the proposed alternative (accepting smaller gains) is genuinely achievable and not merely a face-saving retreat