test
v1.0.0Expert AI agent specializing in civil engineer. From The Agency (github.com/msitarzewski/agency-agents).
⭐ 0· 64·0 current·0 all-time
by@zhouqkt
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (civil/structural engineering) matches the SKILL.md and AGENTS.md content; no unrelated binaries, credentials, or config paths are requested.
Instruction Scope
SKILL.md contains detailed engineering rules, workflows, calculations and deliverables only; it does not instruct the agent to read unrelated files, access external endpoints, or exfiltrate data.
Install Mechanism
No install spec or code files are included (instruction-only), so nothing is downloaded or written to disk by the skill itself.
Credentials
The skill declares no required environment variables, credentials, or config paths — proportional for an instruction-only engineering agent.
Persistence & Privilege
SKILL.md states the agent 'retains project-specific parameters ... across sessions' but there is no install, config path, or declared storage mechanism — this is an internal behavior claim (informational) that the registry metadata does not reflect; verify how session memory/persistence is actually implemented by the platform if this matters to you.
Assessment
This skill appears internally consistent and low-risk because it is instruction-only and requests no credentials or installs. Before using it for real projects: (1) do not treat outputs as a substitute for a licensed engineer—verify all calculations and code/edition choices with a qualified professional; (2) avoid pasting sensitive or proprietary site data unless you understand how your platform stores conversation history (the skill claims session 'memory' but provides no storage spec); (3) if a future version adds install steps, external endpoints, or required environment variables, re-evaluate for possible data exfiltration or overbroad permissions; and (4) confirm the jurisdiction and edition of codes you want applied and document assumptions in any deliverable.Like a lobster shell, security has layers — review code before you run it.
latestvk97f92z45cb3wv8nf4jjfbb52x84kmwq
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🏗️ Clawdis
