Xiong Xiaoge Perspective V2
v1.0.0熊晓鸽(IDG 资本创始人)的思维操作系统 v2.0。基于公开演讲、访谈、投资案例和媒体报道的深度调研, 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,用熊晓鸽的视角分析投资问题、审视商业决策、判断媒体与科技趋势。 当用户提到「用熊晓鸽的视角」「熊晓鸽会怎么看」「熊晓鸽模...
⭐ 0· 91·1 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 skill's name/description (presenting a thinking-framework from publicly available materials) matches the SKILL.md instructions. It does not request unrelated credentials, binaries, or config paths. Everything requested (nothing) is proportionate to providing a persona-based advisory view.
Instruction Scope
The instructions direct the agent to respond in first person as 熊晓鸽 and to stay in character (use 'I', adopt tone, avoid meta-commentary), which is consistent with the stated purpose. The skill does include a top-line disclaimer ('this is not the person') but instructs the agent to present as the person and to only disclose that disclaimer on first activation — this could lead to user confusion or unintentional impersonation if not handled carefully.
Install Mechanism
No install spec, no code files, no downloads. Instruction-only skills have minimal technical footprint and this one writes nothing to disk and requires no binaries — low technical installation risk.
Credentials
The skill requires no environment variables, credentials, or config paths. There is no disproportionate access requested.
Persistence & Privilege
always:false and default invocation settings are used. The skill does not request permanent presence or elevated privileges, nor does it modify other skills or system settings.
Assessment
This skill is technically low-risk and internally consistent with its stated goal (roleplay as a public-figure perspective using public sources). Before installing, consider non-technical risks: the skill explicitly instructs the agent to answer in first person as a living public figure — that can be misleading to end users. To reduce harm, require a visible, repeated disclaimer (not just on first activation) that responses are a simulated perspective based on public sources and not the real person. Also: avoid allowing it to produce actionable, specific investment recommendations (the SKILL.md already forbids stock picks/short-term advice — keep that enforced). Ask the author to add provenance/citations for claims, a persistent disclaimer on each response, and guardrails to refuse impersonation requests beyond high-level perspective (e.g., never claim private/internal facts). Technically, no credentials or installs are needed, so the main decision is whether you are comfortable exposing users to a persona-simulation of a living individual.Like a lobster shell, security has layers — review code before you run it.
latestvk97068nkcxatxfa89njjp8a1ad84gpac
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
