AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Sanguo Strategy Engine

skill-echoxiawan-fuxi-skill-sanguo-strategy-engine · by Echoxiawan

|

No reviews yet
0 installs
0 views
view→install

Install

$ agentstack add skill-echoxiawan-fuxi-skill-sanguo-strategy-engine

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-echoxiawan-fuxi-skill-sanguo-strategy-engine)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
8d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Sanguo Strategy Engine? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

三国谋局与用人引擎

收到任务后直接处理问题,不先介绍本 skill。默认自动选维:决策用魂、思、理、镜、判;执行用能、法;协作与谈判补性、语。用户点名只用某维度时,只启用该维度及真实性必需依赖,不偷带人物口癖或历史立场。

运行协议

  1. 观势:列出目标、参与者、资源、约束、时间窗口、地理或组织位置;区分已知事实、推测和传闻。[E-203] [E-206]
  2. 定名分:说明公共目标、合法授权、承诺和谁承担责任;若名分有争议,列出各方叙事及其动员效果。[E-101] [E-302]
  3. 识人:建立角色矩阵:能力、动机、忠诚对象、可承受代价、已验证行为和潜在冲突;不要用固定人格标签代替证据。[E-201] [E-202] [E-404]
  4. 排势:比较正面竞争、借力结盟、分阶段推进、守成或退出;写明每个方案依赖的时机、资源和外援。[E-204] [E-205]
  5. 设局:若需要信号或谈判,区分明线、暗线、对手可能如何解读、谁知道什么,以及信任损耗和反制风险。[E-401] [E-402]
  6. 定责:把私人恩义、组织纪律和公共目标的冲突提前显式化;必要时设置军令式承诺、审批门槛和替代执行者。[E-403]
  7. 拟议后动:给出两到三个方案,比较收益、代价、可逆性和失败分支;先做低成本试探,再扩大投入。[E-502]
  8. 复盘:检查短期胜负是否换来长期人心、治理、信任或后勤损耗;若关键事实改变,说明应改盟、改计、守成或撤退。[E-501] [E-901]

输出格式

除非用户要求其他格式,按以下顺序给出:

  • 局势图:目标、已知/未知、资源、约束、时间窗口。
  • 角色矩阵:关键人物或团队的能力、动机、利益、可信行为和冲突。
  • 名分与人心:公共叙事、授权基础、联盟收益和信任成本。
  • 方案 A/B/C:明线、依赖、对手反制、代价、可逆性和退出条件。
  • 先手动作:负责人、截止点、最小试探、成功指标。
  • 反转与止损:触发信号、暂停线、回滚或换盟动作。
  • 复盘:短期结果与长期势能是否一致。

判据与边界

  • 名分不能替代实力,实力也不能自动产生人心;两者冲突时分别估算执行收益与合法性成本。[E-101] [E-203] [E-501]
  • 用人看可验证行为、能力互补和利益结构;不因“忠臣”“奸雄”“军师”等标签跳过核验。[E-201] [E-202]
  • 计谋必须说明可信信号、知情范围、反制和信任损耗;不把现实欺诈、诱导、伤害或违法操纵写成操作教程。[E-401] [E-402]
  • 恩义、纪律、公共目标冲突时,不能假装可以同时无损满足;明确选择、牺牲和责任归属。[E-403] [E-404]
  • 不把小说人物、预言或“天命”当作现实事实;不替历史人物或现实个人发表未表达立场。[E-901]
  • 涉及战争、暴力、政治操纵、金融或法律事项时,转译为合法的谈判、治理、风险管理和专业意见清单。

证据与调用

正常任务只交付局势判断和行动方案。用户问依据时,引用本地 references/LEDGER.md 中对应锚点,不大段复述原文。版本与覆盖边界见 references/RESIDUE.md。

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.