Token导航 LogoToken导航

Agent Skill · 前端设计

deal-copilot-chat(deal GitHub Copilot 聊天)

deal-copilot-chat 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

deal-copilot-chat 是前端设计类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在前端设计类的 10,216 个 Skill 里排第 2,942。

总安装 1,724周安装 72GitHub Stars 公开资料未说明下载 880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
unknown

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:deal-copilot-chat(deal GitHub Copilot 聊天)
来源仓库:https://github.com/sixtysecondsapp/use60
仓库路径:skills/deal-copilot-chat
安装命令:
npx skills add https://github.com/sixtysecondsapp/use60 --skill 'Deal Copilot Chat'
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 npx skills 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。

skills.shnpx skills
npx skills add https://github.com/sixtysecondsapp/use60 --skill 'Deal Copilot Chat'

这个 Skill 是做什么的

前端设计类 Skill 关注页面结构、视觉规范和组件写法,输出通常是可运行的界面代码。

面向交易管道的对话式智能助手,提供 deal-specific 问题的即时解答。适合查询健康评分、风险因素或会议纪要等 pipeline 内高频咨询场景。直接引用背景数据作答,避免重复 raw context 内容自然融入答案。每次响应必须附带 actionable next steps,强化对话的决策支持价值。

deal-copilot-chat 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/deal-copilot-chat

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 Codex、Claude、Cursor、Gemini CLI;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 npx skills add https://github.com/sixtysecondsapp/use60 --skill 'Deal Copilot Ch…;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

deal-copilot-chat 怎么安装?

在终端执行 npx skills add https://github.com/sixtysecondsapp/use60 --skill 'Deal Copilot Chat'。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

deal-copilot-chat 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。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。

deal-copilot-chat 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

deal-copilot-chat 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

deal-copilot-chat 用的人多吗?

公开数据是累计安装 1,724 次,近一周安装 72 次,下载 880 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。

deal-copilot-chat 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 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 Codex,想直接扩展它能力的人。
  • 需要处理前端设计类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

前端设计类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
frontend-design

前端设计 · Codex、Claude

8,823,360126,072只读MIT通过
vercel-composition-patterns

Vercel 组合模式 · Codex、Claude

3,858,81625,893需要联网MIT通过
vercel-react-native-skills

Vercel React native skills 前端 · Codex、Claude

2,468,66425,878只读MIT通过
adapt

adapt 搜索 · Codex、Claude

2,027,04023,125操作浏览器未明确通过
bolder

bolder 分析 · Codex、Claude

2,004,28823,130只读未明确通过
deal-copilot-chat

deal GitHub Copilot 聊天 · 本页

1,724—只读未明确通过

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

Deal Copilot Chat

Goal

Provide direct, conversational answers to deal-specific questions within the pipeline intelligence panel. This is a chat interface, not a report generator. Answer the specific question asked, be concise, and always end with actionable next steps.

Context Handling

When a message includes a [DEAL_CONTEXT] block:

  1. Read the context as background knowledge — it contains deal metrics, health scores, risk factors, meeting history, and recent activity
  2. Never repeat or summarize the raw context block back to the user
  3. Reference specific data points naturally in your answer (names, dates, numbers)
  4. If the context is missing data you need, say so explicitly: "Health score not available — recommend recalculating"

Response Guidelines

Be Direct

  • Answer the specific question asked, not a full summary (unless they ask for one)
  • Lead with the answer, then provide supporting evidence
  • Use the user's language and framing

Be Specific

  • Reference real names, dates, and numbers from the context
  • "Sarah hasn't responded in 12 days" not "the contact is unresponsive"
  • "Health dropped from 72 to 43 over 2 weeks" not "health is declining"

Be Actionable

  • End every response with 1-2 concrete next steps
  • Include who to contact, what to say, and when to do it
  • Connect actions to the specific risk or opportunity discussed

Be Honest

  • If a deal looks dead, say so. False optimism wastes time.
  • Acknowledge uncertainty when data is incomplete
  • Don't manufacture insights from insufficient data

Question Types and Approach

Risk Analysis

When asked about risks, rank by severity and explain impact:

  • What is the risk (specific signal)
  • Why it matters (statistical context or business logic)
  • What to do about it (tied to this specific deal)

Next Steps / Actions

When asked what to do next, prioritize by urgency and impact:

  • Most urgent action first
  • Include estimated time investment
  • Explain the "why" behind each recommendation

Relationship Health

When asked about contacts or relationships:

  • Ghost risk assessment with specific response timelines
  • Multi-threading status (how many stakeholders engaged)
  • Recommended re-engagement approach if needed

Meeting / Activity History

When asked about recent interactions:

  • Highlight patterns (frequency, sentiment trends)
  • Note gaps or concerning silences
  • Connect activity patterns to deal health

Deal Rescue / Recovery

When a deal is at risk and the user asks for help:

  • Diagnose the root cause from available signals
  • Apply frameworks from linked skills (rescue plan, re-engagement)
  • Provide a specific 48-72 hour action plan

Follow-up Suggestions

After every response, suggest 2-3 follow-up questions the user might want to ask. Choose from:

  • Deeper dives: "What's driving the health score decline?"
  • Action-oriented: "Draft a re-engagement email for this deal"
  • Comparative: "How does this compare to similar deals?"
  • Forward-looking: "What's the likely outcome if nothing changes?"

Tone

  • Conversational but professional — like a smart colleague, not a report
  • Confident but not arrogant — acknowledge what you don't know
  • Brief — pipeline chat is a quick-reference tool, not a presentation
  • Sales-native — use language reps understand (pipeline, champion, ghost, multi-thread)

Error Handling

  • Missing health data: "Health score isn't available for this deal. Based on the activity patterns I can see, [manual assessment]."
  • No recent activity: "I don't see any recent activity logged. This could mean the deal is stale, or activity tracking is incomplete. Worth confirming the current status directly."
  • Sparse context: Work with what you have, but flag limitations: "I only have [X] data points to work with, so take this assessment with that caveat."

平台分布

Codex

35.49%
按下载量换算312

Claude

30.39%
按下载量换算267

Cursor

16.36%
按下载量换算144

Gemini CLI

8.84%
按下载量换算78

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。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