Su Hua Perspective V2
v1.0.0宿华的思维操作系统 v2.0。基于快手创业历程、公开演讲、访谈和决策记录的深度调研， 提炼 10 个核心心智模型、8 条决策启发式和完整的表达 DNA。 用途：作为思维顾问，用宿华的视角分析产品、社区、商业化、下沉市场等问题。 当用户提到「用宿华的视角」「宿华会怎么看」「宿华模式」「su hua perspect...
⭐ 0· 46·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (a Su Hua thinking-framework roleplay) matches the SKILL.md instructions: the skill is purely a persona and guidance library. It does not request unrelated binaries, env vars, or config paths.
Instruction Scope
The SKILL.md strictly instructs the agent to adopt Su Hua's identity and voice (first-person), provides triggers and example dialogs, and says the disclaimer should be shown only on first activation. There is no instruction to read files, call external endpoints, or access credentials. Two items worth noting: (1) the trigger list is broad and could cause the skill to activate in contexts where impersonation is inappropriate; (2) restricting the disclaimer to 'only once' increases the chance users will be misled later. These are ethical/usability concerns rather than incoherent functionality.
Install Mechanism
No install spec and no code files — lowest-risk model. Nothing is written to disk or downloaded.
Credentials
The skill requests no environment variables, credentials, or config paths; there is no excessive access requested compared to its stated purpose.
Persistence & Privilege
always is false and there is no special persistence or system-wide config changes. Autonomous invocation (model can call skill) is enabled by default — normal — but combined with persona/trigger breadth this could increase the chance of inadvertent invocation in multi-skill agents.
Assessment
This skill is internally coherent and low-risk from a technical/resource perspective: it only contains instructions for role‑playing and asks for no secrets or installs. Before installing, consider the following: 1) impersonation risk — the skill instructs the agent to speak in first person as a named public figure; ensure you’re comfortable with potential legal/ethical implications and user confusion (consider requiring an explicit, repeated disclaimer). 2) activation scope — the trigger list is broad and may cause the skill to run unexpectedly; tighten triggers or require explicit user invocation. 3) autonomous use — if you don’t want the agent to call this persona without an explicit user prompt, disable autonomous invocation for this skill. 4) accuracy — the skill is based on public sources and may be incomplete or out of date; treat outputs as advisory, not statements of fact. If you want stronger safeguards, ask the maintainer to: always show a clear disclaimer in every response, make triggers opt-in, and document sources for the distilled claims.Like a lobster shell, security has layers — review code before you run it.
latestvk9720b0kjyh4ckbswxx6jcdmc184ecqr
License
MIT-0
Free to use, modify, and redistribute. No attribution required.