ClawHub

Q Wms

v1.0.62

千易 WMS 智能查询技能。默认开放一期 stable 场景：今日仓内总览、今日待办与异常、出库积压归因、昨日问题恢复情况，以及库存、订单、任务、绩效和仓库/货主上下文查询。所有查询必须通过 q-claw。

⭐ 0· 181·0 current·0 all-time
bylee@ljqdh
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/description (WMS intelligent queries) match the SKILL.md routing and scenes. All functionality is explicitly about inventory, orders, tasks, performance, and manager views and is implemented as calls to the q-claw tool. There are no unrelated environment variables, binaries, or install steps requested.
✓
Instruction Scope
Runtime instructions are narrowly scoped to routing user intents to specific scenes via q-claw and to handle tool-returned payloads according to strict rules. The skill does not instruct reading local files, broad environment state, or arbitrary endpoints. It does read context.locale (reasonable for locale behavior) and expects runtime injection of tenantKey/openId (consistent with a service-backed tool).
✓
Install Mechanism
There is no install spec and no code files; this is instruction-only, which minimizes disk-write/installation risk.
✓
Credentials
The skill declares no required env vars, no primary credential, and no config paths. The expected runtime inputs (tenantKey/openId) are described as injected by the runtime/tool, which is proportionate for a backend-backed WMS query skill.
✓
Persistence & Privilege
always is false and autonomous model invocation is allowed (platform default). The skill does not request permanent presence or system-wide configuration changes.
Assessment
This skill appears coherent and limited to routing WMS queries through the q-claw tool. Before installing, confirm: (1) what implementation of the q-claw tool your agent will call and which backend endpoints it uses; (2) how authentication/authorization (tenantKey/openId) is provided and whether the tool will request user credentials or present authorization links; and (3) that you trust the backend providing WMS data. Because the skill is instruction-only, any risky behavior would come from the q-claw tool/backend — verify those separately.

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

latestvk9793cr4b5te58f0spa6qpj65984w52r

License

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

Comments