ClawHub

Searching Assistant

v0.1.0

You are the leader of searching group (搜索组组长). Break down the task into independent and complementary sub-tasks. Then describe each sub-task with natural lan...

⭐ 0· 2.4k·29 current·31 all-time
by@urrrich0
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
The name and description match the SKILL.md: it instructs the agent to decompose search tasks and assign them to search agents (always using General_Search_Agent). There are no unrelated requirements (no binaries, env vars, or installs).
ℹ
Instruction Scope
The instructions are focused on task decomposition and orchestration of other agents. They reference template variables (e.g., $DATE, $SESSION_GROUP_ID) that require proper runtime substitution. The skill grants the agent authority to call other agents, which is expected for an orchestrator but means the downstream agents' behavior/permissions matter.
✓
Install Mechanism
No install spec and no code files — the skill is instruction-only, so nothing will be written to disk or downloaded during install.
✓
Credentials
The skill requires no environment variables, credentials, or config paths; nothing requests access to unrelated services or secrets.
✓
Persistence & Privilege
always:false (no forced global inclusion). disable-model-invocation:false is the platform default and acceptable here; the skill can autonomously invoke other agents, which is coherent for an orchestrator but not by itself a security problem.
Assessment
This skill is an instruction-only orchestrator for search tasks and appears coherent. Before installing, confirm that the referenced agents (especially General_Search_Agent and any other agents it may call) exist and have appropriate permissions and logging. Ensure runtime substitution for template variables like $DATE and $SESSION_GROUP_ID is provided by your environment. Because the skill can call other agents, review what data those downstream agents receive (avoid sending sensitive secrets in queries) and test with non-sensitive queries first. Also verify the intended logic around the 'DO NOT call Academic_Search when the task involves date-specific requirements' rule to ensure it matches your operational expectations.

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

latestvk9733eaf2x1p0f2sq007f2v7kn8174ca

License

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

Comments