Skill Router
v0.1.0Route the current task to the most relevant installed skill, and only suggest new skills when existing ones are not enough. Use when the user asks things lik...
⭐ 1· 377·6 current·6 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description match the runtime instructions: the skill's job is to pick the best installed skill or suggest discovery only when necessary. It does not claim capabilities (network, cloud, etc.) that would require additional credentials or binaries.
Instruction Scope
Runtime guidance confines the agent to inspecting the current installed skill set, consulting bundled reference docs, and recommending discovery flows (e.g., find-skills, skill-vetter) when appropriate. It does not instruct reading unrelated system files, environment variables, or sending data to external endpoints.
Install Mechanism
No install spec and no bundled code — instruction-only. This minimizes on-disk code execution risk and matches the described low-presence role.
Credentials
The skill requests no environment variables, credentials, or config paths. Its runtime behavior (inspect installed skills and local reference docs) is proportional to its purpose.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request elevated or permanent presence. Autonomous invocation is allowed by default on the platform but is not a unique privilege of this skill.
Scan Findings in Context
[no_code_files] expected: The package is instruction-only and the regex scanner had no code to analyze; this is consistent with the declared design.
Assessment
This skill is internally consistent and low-risk: it only inspects installed skills and uses its bundled guidance to recommend reuse vs discovery. Before installing, confirm you trust the agent environment (installed skills the router will inspect) and that companion skills it references (e.g., find-skills, skill-vetter) are present and trustworthy. If you want stronger control, restrict whether the agent can autonomously invoke routing or discovery flows, or test the router in a non-production workspace to validate its recommendations.Like a lobster shell, security has layers — review code before you run it.
latestvk977736v5tpqv8sq5msx0b2rrd82ssvw
License
MIT-0
Free to use, modify, and redistribute. No attribution required.