Zhang Yiming Perspective
v1.0.2基于张一鸣心智模型，提炼其长期主义、算法思维、信息透明、全球视野与第一性原理的创业与管理决策框架。
⭐ 0· 166·1 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 and description (emulate Zhang Yiming's perspective / decision frameworks) align with its contents: a SKILL.md plus research/reference files. It requests no binaries, env vars, or config paths. Minor note: README shows example install commands (npx / clawhub) but the registry metadata contains no install spec — this is an implementation/documentation inconsistency but not a security concern.
Instruction Scope
SKILL.md contains explicit runtime instructions to roleplay a public figure's mental models and expression style, enumerates triggers and limits (includes an 'honesty boundary' stating the agent is not actually Zhang Yiming). The instructions do not ask the agent to read unrelated files, access system credentials, or transmit data to external endpoints. No vague 'gather whatever context you need' authorizations are present.
Install Mechanism
There is no install spec and no code files to execute — the skill is instruction-only. This minimizes disk writes and execution risk. The README's suggested npx/clawhub commands are convenience examples but are not part of an install manifest in the registry metadata.
Credentials
The skill requires no environment variables, keys, or credentials. All referenced research is packaged with the skill. No disproportionate secret access is requested.
Persistence & Privilege
Flags show always:false and no config paths requested. Model invocation is enabled (default) which allows the agent to call the skill autonomously — this is normal for skills and not by itself a concern given this skill's limited scope and lack of credentials.
Assessment
This skill is internally coherent and low-risk: it only contains instructions and research files and asks for no credentials or installs. Before installing, consider: (1) Legal/ethics: it roleplays a public figure — avoid using it to produce false factual claims presented as that person's real statements or for impersonation-sensitive use cases. (2) Accuracy: the skill is a distilled model based on public sources and has explicit limits (information cutoff 2026-04); validate any high-stakes advice (legal, financial, regulatory) with authoritative sources. (3) Autonomy: the skill can be invoked autonomously by the agent (normal behavior); if you restrict autonomous use, adjust agent policies accordingly. (4) Documentation mismatch: README shows install examples though registry has no install spec — if you plan automated deployment, confirm the intended install method. Test the skill with non-sensitive prompts first to verify its behavior matches your expectations.Like a lobster shell, security has layers — review code before you run it.
latestvk97d1n01ak3grcjtmwwyk1cfzs84bc57
License
MIT-0
Free to use, modify, and redistribute. No attribution required.