← 返回 Skills 市场
163
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install member-complaint-agent
功能描述
Handle member/customer complaint workflows with a Linear-centered operating model. Use when the task involves 会员客诉、客户投诉、退款诉求、续费失败、自动续费争议、会员权益异常、客服草稿、风险分级、Lin...
安全使用建议
This skill is a textual playbook for handling member complaints via Linear and appears coherent. Before installing or enabling it for autonomous use, confirm: (1) how your platform supplies Linear access (connectors/credentials) so you don’t accidentally allow write permissions you didn’t intend, (2) whether you want the agent to post comments automatically or only prepare drafts for human review, and (3) that any company SOPs or sensitive customer data referenced are provided to the skill or reviewed manually. No code or external downloads are included, and no unexplained credentials are requested. If you need higher assurance, test the skill in a non-production Linear workspace and verify permission scopes for any connector used.
功能分析
Type: OpenClaw Skill
Name: member-complaint-agent
Version: 1.0.0
The member-complaint-agent skill bundle is a well-structured workflow for automating customer support tasks within the Linear platform. The instructions in SKILL.md and references/complaint-playbook.md focus on categorizing complaints, parsing metadata, and drafting responses with clear guardrails against unauthorized promises or policy invention. There is no evidence of malicious intent, data exfiltration, or suspicious execution logic.
能力评估
Purpose & Capability
The skill's name and description (Linear-centered complaint handling) match the SKILL.md content. It expects to read from and write back to Linear issues. The skill declares no required env vars or binaries — this is plausible for an instruction-only skill that assumes platform connectors will provide Linear access, but the omission is worth noting if you expect the skill to autonomously call Linear's API.
Instruction Scope
The runtime instructions stay within the stated purpose: parse Linear issue metadata, produce an analysis comment and a customer-reply draft, and generate digests. There are no instructions to read arbitrary host files, exfiltrate data, call unknown endpoints, or invent policies. The only external action implied is reading/writing Linear issues, which is consistent with the described operating model.
Install Mechanism
No install spec or code files are included; the skill is instruction-only, so nothing will be downloaded or written to disk by the skill itself.
Credentials
The skill requests no environment variables or credentials. This is proportionate for an instruction-only playbook, but it implicitly assumes the agent or platform will provide Linear integration/credentials if automated read/write is required — confirm how Linear access is granted on your platform before using it for live writes.
Persistence & Privilege
always:false and default model-invocation behavior are both set; the skill does not request forced/global inclusion or elevated persistence. It does imply potential autonomous action (normal platform default), so confirm runtime policies for automatic posting to Linear if that is a concern.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install member-complaint-agent - 安装完成后，直接呼叫该 Skill 的名称或使用
/member-complaint-agent触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release of member-complaint-agent skill.
- Manages customer complaint workflows centered on Linear, with structured analysis and reply drafting.
- Parses deterministic metadata (e.g., platform, vendor, app version) separately from AI-based judgment.
- Provides two default Linear comments per complaint: structured AI analysis and a ready-to-use customer reply draft.
- Includes detailed guidelines for SOP handling, escalation, and daily/weekly digest summaries.
- Enforces strict separation of facts, judgments, and recommended actions; prohibits unauthorized promises.
元数据
常见问题
Member Complaint Agent 是什么？
Handle member/customer complaint workflows with a Linear-centered operating model. Use when the task involves 会员客诉、客户投诉、退款诉求、续费失败、自动续费争议、会员权益异常、客服草稿、风险分级、Lin... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 163 次。
如何安装 Member Complaint Agent？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install member-complaint-agent」即可一键安装，无需额外配置。
Member Complaint Agent 是免费的吗？
是的，Member Complaint Agent 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Member Complaint Agent 支持哪些平台？
Member Complaint Agent 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Member Complaint Agent？
由 qwqcode（@qwqcode）开发并维护，当前版本 v1.0.0。
推荐 Skills