Steve Jobs Skill
v1.0.1史蒂夫·乔布斯(Steve Jobs)的思维框架与表达方式。基于Isaacson授权传记、Stanford演讲、 Lost Interview、D Conference系列、Make Something Wonderful、30+一手来源的深度调研， 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。 用途...
⭐ 0· 170·2 current·2 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 and description promise a 'Steve Jobs perspective' and the SKILL.md contains detailed roleplay instructions and supporting references. There are no surprising environment variables, binaries, or installs requested — the declared purpose aligns with what the skill asks the agent to do.
Instruction Scope
The runtime instructions require the agent to impersonate Steve Jobs in first person, speak with his tone, and emit a one-time disclaimer only on first activation. This is coherent with the stated purpose, but it raises non-security concerns: possible user confusion or misattribution (the skill will present opinions as if they are Jobs's), and the policy/ethical risks of impersonating a deceased public figure. There are no instructions to read files, access env vars, or transmit data externally.
Install Mechanism
No install spec and no code files that execute — this is instruction-only. That gives a low technical risk surface: nothing will be downloaded or written to disk as part of an install.
Credentials
The skill declares no required environment variables, credentials, or config paths. The lack of requested secrets or system access is proportionate to a persona/consultant skill.
Persistence & Privilege
always:false and user-invocable:true. The skill does not request permanent inclusion or elevated privileges. Autonomous invocation by the model is allowed by default (disable-model-invocation:false) — this is normal platform behavior and not in itself a red flag.
Assessment
This skill is technically low-risk: it doesn't install software or ask for credentials. The main issues to consider are non-technical: it intentionally impersonates a real, deceased public figure and is designed to speak in the first person with a one-time disclaimer only. Before installing or enabling it, decide whether you want outputs that present opinions as if spoken by Steve Jobs (which may confuse end users or be misleading). If you plan to use it in production or customer-facing flows, consider: (1) requiring explicit user consent before switching into the persona, (2) making the disclaimer visible on every session or easy to re-check, (3) preventing autonomous invocation for critical workflows, and (4) verifying citations for factual claims (the skill may mix sourced quotes with model-generated inference). If any legal or ethical policies in your organization forbid impersonation of public figures, do not enable this skill. Otherwise, it's internally coherent and proportionate to its stated purpose.Like a lobster shell, security has layers — review code before you run it.
latestvk97eq0t7bet30teh7m2vxqtyhd84awxb
License
MIT-0
Free to use, modify, and redistribute. No attribution required.