Token导航 LogoToken导航

Agent Skill · 研究检索

linear-feedback-triage(Linear feedback triage 搜索)

用于处理 Linear 项目、Issue、团队、周期和产品开发任务流。它适合让 Agent 辅助查询任务状态、整理需求队列、创建缺陷或汇总迭代进展。使用时需要确认 workspace、team、label、assignee 和状态流转规则;涉及批量创建或修改任务时,应先核对字段和目标团队,避免把草稿需求直接写入正式项目。

linear-feedback-triage 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为调用外部服务;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 18,606。

总安装 5,998周安装 255GitHub Stars 公开资料未说明下载 2,101核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:linear-feedback-triage(Linear feedback triage 搜索)
来源仓库:https://github.com/qwqcode/linear-feedback-triage
安装命令:
openclaw skills install linear-feedback-triage
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install linear-feedback-triage

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

linear-feedback-triage 分类处理用户反馈类问题。特别针对 FB 团队工作流程优化设计。支持投诉查询与重复项识别功能。安装时按仓库提供的命令执行,建议先在测试环境验证依赖、命令权限和文件改动范围。需定期校准标签体系匹配准确性。适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install linear-feedback-triage;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

linear-feedback-triage 怎么安装?

在终端执行 openclaw skills install linear-feedback-triage。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

linear-feedback-triage 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

linear-feedback-triage 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

linear-feedback-triage 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

linear-feedback-triage 用的人多吗?

公开数据是累计安装 5,998 次,近一周安装 255 次,下载 2,101 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

linear-feedback-triage 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
linear-feedback-triage

Linear feedback triage 搜索 · 本页

5,998—调用外部服务MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
linear-feedback-triage
description
Triage user-feedback issues in Linear, especially FB team / 用户反馈 workflows. Use when asked to query Linear issues, list recent complaints, find duplicate feedback, group membership/payment complaints, decide main issue vs sub-issue, suggest status/labels/assignee, or draft user replies for the Tide feedback process.

Linear Feedback Triage

Use this skill for the Tide-style feedback workflow that lives in Linear.

Quick start

When the user asks about recent feedback, membership complaints, duplicates, or FB issues:

  1. Use exec with npx -y mcporter ... from /Users/claw/.openclaw/workspace.
  2. Query the Linear MCP server configured in config/mcporter.json.
  3. Prefer read-only queries first.
  4. Summarize findings before proposing writes.
  5. Only mutate Linear when the user clearly asks, or when the workflow explicitly calls for it.

Useful commands:

cd /Users/claw/.openclaw/workspace && npx -y mcporter call linear.list_issues team=FB limit=10
cd /Users/claw/.openclaw/workspace && npx -y mcporter call linear.get_issue id=FB-12345
cd /Users/claw/.openclaw/workspace && npx -y mcporter call linear.list_issue_statuses team=FB
cd /Users/claw/.openclaw/workspace && npx -y mcporter call linear.list_issue_labels team=FB

Core workflow

1. Query first

For broad requests, start with linear.list_issues.

Good filters:

  • team=FB for 用户反馈
  • label=会员支付 for membership/payment complaints
  • query=退款 / query=续费 / query=支付失败 for narrower searches
  • limit=10 unless the user asks for more

If descriptions are truncated, follow up with linear.get_issue on the specific IDs.

2. Normalize the feedback type

Map issues into a small set before deciding action:

  • 建议: product/content suggestion, feature request, request for a new payment method
  • BUG: broken flow, payment failure, renewal failure, login/register issue, crash, data problem
  • 内容反馈: meditation/sleep/sound/content quality issues
  • 其他: unclear but not obviously a bug or suggestion

Keep labels to at most 3, mixing platform + primary class + one secondary domain when helpful.

Label guidance

Zero-level labels

  • Android
  • iOS
  • Web
  • 重要

First-level labels

  • 建议
  • 功能故障
  • 内容反馈
  • 会员支付
  • 注册登录
  • 其他

Second-level labels

  • 专注功能
  • 睡眠功能
  • 帐号数据
  • 网络问题
  • 闪退崩溃
  • 播放功能
  • 冥想内容
  • 声音内容
  • 睡眠内容

Status guidance

Use the user's workflow vocabulary when recommending or applying statuses:

  • 待处理: raw incoming feedback
  • 待跟进: assigned and entering workflow
  • 沟通中: active user communication
  • 处理中: analysis, fixing, discussion, or investigation underway
  • 挂起: blocked or dormant short-term
  • 已解决: issue resolved or recorded elsewhere and no further user question remains
  • 已归档: duplicate/aged-out/archive state
  • 无效反馈: spam or meaningless feedback; use sparingly

Duplicate-handling rules

For suspected duplicates:

  1. Compare issue title, complaint theme, platform, account hints, and timestamps.
  2. If it is the same user and same complaint, treat it as a likely duplicate.
  3. If it matches an existing unresolved bug:

- recommend the new issue be archived - recommend linking it under the main issue as a sub-issue - reply to the user that the problem has been received and is being handled

  1. If it matches an existing resolved bug:

- recommend archive/sub-issue under the solved main issue - reply asking the user to update to the solved version or re-check

When confidence is low, say so explicitly instead of forcing a merge.

Membership/payment complaint guidance

Common membership/payment buckets:

  • refund / cancellation request
  • auto-renewal complaint
  • payment failure
  • renewal failure
  • purchase blocked by account conflict
  • payment-method suggestion

Heuristic:

  • payment method request → usually 建议 + 会员支付
  • cannot pay / renew / buy → usually BUG or transactional failure + 会员支付
  • refund / cancel auto-renewal → usually support/payment workflow item; still tag 会员支付

Reply drafting

If the user asks for a reply draft, produce text that can be used with Tide Bot:

@tidebot /reply <reply text>

Default tones:

  • unresolved known/active issue: acknowledge receipt, say it is being handled
  • resolved issue: suggest updating/retrying on latest version
  • suggestion: thank the user and say it has been recorded for evaluation

Do not claim a fix is shipped unless Linear evidence supports it.

Mutation commands

Only use these when needed:

cd /Users/claw/.openclaw/workspace && npx -y mcporter call linear.save_issue id=FB-12345 state=处理中
cd /Users/claw/.openclaw/workspace && npx -y mcporter call linear.save_issue id=FB-12345 labels='["会员支付","Android"]'
cd /Users/claw/.openclaw/workspace && npx -y mcporter call linear.save_comment issueId=FB-12345 body='处理中,已复现。'

Before writes, briefly state what you are about to change.

Output format

For analysis requests, prefer:

  • issue ID
  • short title
  • status
  • labels
  • why it matches the request
  • duplicate/main-issue recommendation if relevant

For grouping requests, prefer buckets such as:

  • 退款 / 退订
  • 自动续费争议
  • 支付失败
  • 无法购买 / 无法续费
  • 支付方式建议

Keep summaries compact and decision-oriented.

平台分布

OpenClaw

71.5%
按下载量换算1,502

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills