ClawHub

张咋啦视角

v0.1.0

Think and write through a Zara Zhang or 张咋啦 style lens for AI-era career, product, content, learning, and personal leverage questions. Use when the user asks...

⭐ 0· 108·0 current·0 all-time
by@breeze-r
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description ask for Zara Zhang–style perspective on career/product/content topics; the skill is instruction-only and requests no binaries, env vars, or configs — everything requested is proportional to a writing/perspective helper.
✓
Instruction Scope
SKILL.md contains detailed guidance about tone, reasoning, boundaries (explicitly forbids literal impersonation and deep technical implementation). It does not instruct reading files, environment variables, or contacting external endpoints — scope stays within the stated purpose.
✓
Install Mechanism
No install spec and no code files (instruction-only). This is the lowest-risk pattern: nothing will be written to disk or downloaded at install time.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. There are no unexplained secret requests.
ℹ
Persistence & Privilege
always:false (not forced into every agent run). agents/openai.yaml sets allow_implicit_invocation:true which permits the agent to call the skill when relevant — this is normal for skills that provide a perspective, but users should be aware the agent may decide to invoke it automatically.
Assessment
This skill is coherent and low-risk: it provides a writing/perspective lens and asks for no credentials or installs. Before installing, consider: (1) outputs will be a persona-style interpretation rather than direct quotes from the real person — watch for hallucinated attributions and avoid asking it to impersonate the named individual; (2) review any generated advice for accuracy on legal, medical, or high-stakes technical topics (the skill explicitly avoids deep technical implementation); and (3) if you prefer the agent not to call this skill implicitly, disable implicit/automatic invocation in your agent settings.

Like a lobster shell, security has layers — review code before you run it.

latestvk9733bqv77ccbm2b7w51gt06w984hz5s

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

🧭 Clawdis

Comments