sunzibingfa
v1.0.0《孙子兵法》实战应用技能。当用户询问为人处世、言谈交流、思考方法、做事技巧、领导力、团队管理、竞争策略、人际博弈、决策思维等问题时，或需要指导如何处理人际关像、职场困境、商业竞争、家庭矛盾等情况时，激活此技能。适用场景包括：(1) 用户问"如何..."类问题，(2) 用户描述困境需要建议，(3) 用户请求分析决策...
⭐ 0· 83·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description: advisory skill based on Sunzi. Declared and actual requirements: no binaries, no env vars, no install, no external endpoints. The content (handbook + SKILL.md) matches the stated goal of giving interpersonal/strategy advice—there is nothing requesting unrelated resources.
Instruction Scope
SKILL.md instructs the agent to read the bundled manual (references/孙子兵法实战应用手册.md) and to apply frameworks (五事七计、诡道十二法, etc.) when answering. That scope is coherent with the purpose. Note: the manual contains explicit tactical advice (including manipulative/competitive tactics like '怒而挠之', '亲而离之') — this is expected for the subject matter but may be ethically sensitive depending on use.
Install Mechanism
No install spec, no downloads, and no code files. Instruction-only skills are lowest-risk from an installation perspective.
Credentials
The skill requires no environment variables, credentials, or config paths. There is no disproportionate access requested relative to the described advisory function.
Persistence & Privilege
always:false and user-invocable:true. The skill does not request permanent presence or elevated privileges and does not modify other skills or system settings.
Assessment
This skill is internally coherent and does not request credentials or install code. Before enabling: (1) Review the included handbook yourself — it contains explicit competitive/manipulative tactics that can be ethically sensitive; (2) avoid feeding the skill private or identifying details about third parties (to prevent misuse); (3) if you will allow autonomous agent invocation, monitor outputs to ensure advice is appropriate for your context; (4) if you later see the skill ask for environment variables, network endpoints, or to run external code, treat that as a new risk and re-evaluate. Overall low technical risk, but consider policy/ethical use of the tactics it recommends.Like a lobster shell, security has layers — review code before you run it.
latestvk97532zs8h59sa57mk7t9mf97n84hq6x
License
MIT-0
Free to use, modify, and redistribute. No attribution required.