LeoYeAI/agent-master-skills / skills/art-of-war-agents
art-of-war-agents
VerifiedApply Sun Tzu's Art of War to AI agent orchestration. Use for: task assessment (五事七计), deployment decisions, multi-agent strategy, token cost optimization, risk management, and agent collaboration patterns. Maps all 13 chapters to practical agent workflows with decision trees and troubleshooting.
| File | Kind | Size |
|---|---|---|
| CARD.md | markdown | 10.5 KB |
| CHANGELOG.md | markdown | 943 B |
| README.md | markdown | 4.1 KB |
| SKILL.md | skill md | 22.5 KB |
| _meta.json | config | 287 B |
| references/thirteen-chapters.md | markdown | 11.8 KB |
| scripts/assess-task.py | script | 4.3 KB |
| scripts/quick-decision.py | script | 3.4 KB |
scripts/quick-decision.py
View on GitHub#!/usr/bin/env python3
"""
Art of War Quick Decision Card
Interactive prompt-based decision helper for agent deployment
Usage: python quick-decision.py
"""
import sys
QUESTIONS = [
# 始计篇 — Task Assessment
("始计篇", [
("任务目标清晰吗?", "Task goal is clearly defined"),
("现在是合适的时机吗?", "Timing is right (dependencies ready)"),
("有足够的上下文/数据吗?", "Sufficient context/data available"),
("有合适的 agent 吗?", "Right agent(s) available"),
("流程清晰吗?", "Workflow and success criteria defined"),
]),
# 谋攻篇 — Planning
("谋攻篇", [
("这个任务能消除/自动化吗?", "Can task be eliminated/automated"),
("单 agent 能解决吗?", "Can single agent handle it"),
("还是必须多 agent 协作?", "Or is multi-agent truly necessary"),
]),
# 作战篇 — Cost
("作战篇", [
("Token 预算是多少?", "What's the token budget"),
("有设迭代限制吗?", "Iteration limit set"),
("有重用现有输出吗?", "Reusing existing outputs"),
]),
# 军形篇 — Risk
("军形篇", [
("最坏情况是什么?", "Worst case identified"),
("有回滚方案吗?", "Rollback plan exists"),
("有验证机制吗?", "Validation mechanism in place"),
]),
]
DECISIONS = {
(17, 20): "✅ DEPLOY — 条件有利,速战速决",
(13, 16): "⚠ CONDITIONAL — 先补弱点再部署",
(0, 12): "❌ NO DEPLOY — 重新规划,上兵伐谋",
}
def get_score():
total = 0
max_score = 0
print("=" * 60)
print("ART OF WAR AGENT DECISION CARD")
print("=" * 60)
print()
for section, questions in QUESTIONS:
print(f"\n📍 {section}")
print("-" * 40)
for q_cn, q_en in questions:
print(f"\n {q_cn}")
print(f" ({q_en})")
while True:
ans = input(" [0=no, 1=yes, s=skip]: ").strip().lower()
if ans == 's':
break
elif ans == '1':
total += 1
max_score += 1
break
elif ans == '0':
max_score += 1
break
else:
print(" 输入 0, 1, 或 s")
return total, max_score
def get_decision(score, max_score):
for (min_s, max_s), decision in DECISIONS.items():
if min_s <= score <= max_s:
return decision
return "❓ UNKNOWN"
def main():
score, max_score = get_score()
pct = (score / max_score * 100) if max_score > 0 else 0
print("\n" + "=" * 60)
print("RESULTS")
print("=" * 60)
print(f"\nScore: {score}/{max_score} ({pct:.0f}%)")
print()
print(get_decision(score, max_score))
print()
# Specific recommendations
print("=" * 60)
print("KEY REMINDERS")
print("=" * 60)
print()
print("• 知彼知己 — Understand task + know agent limits")
print("• 上兵伐谋 — Plan first, execute second")
print("• 速战速决 — Set iteration limits, force conclusions")
print("• 先胜后战 — Ensure conditions favor success")
print("• 三反原则 — Cross-verify with 3+ sources")
print()
print("=" * 60)
if __name__ == "__main__":
main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |