npx skills add https://github.com/jezweb/claude-skills --skill team-update向团队聊天室发布项目更新,阅读并分类反馈,并规划后续步骤。可适配任何可用的沟通和项目管理工具。
此技能使用项目根目录 .claude/team-update-playbook.md 下的一个剧本文件。
剧本是用户可以编辑的纯 Markdown 文件。它捕获了工具配置、频道偏好、消息风格、分类规则以及上次运行的元数据。
检查项目根目录下是否存在 .claude/team-update-playbook.md。
如果存在 : 读取它。所有工具配置、频道信息、消息风格和分类规则都在其中。使用已知配置跳转到阶段 1。
如果不存在 : 首先运行阶段 0b(发现)。
通过检查已连接的 MCP 工具和存在的本地工具来检测可用能力。
阅读 references/discovery-patterns.md 了解检测模式。
检查每个能力类别:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| 能力 | 如何检测 | 缺失时的备选方案 |
|---|
| 聊天 | 匹配 chat、slack、discord、teams 的 MCP 工具 | 输出格式化文本供手动发布 |
| Git | git rev-parse --is-inside-work-tree | 跳过提交摘要 |
| 问题 | 匹配 github、linear、jira 的 MCP 工具 | 跳过或输出文本列表 |
| 任务 | 匹配 tasks、todos、asana 的 MCP 工具 | 跳过或输出文本列表 |
| 知识 | Basalt Cortex (~/Documents/basalt-cortex/) | 搜索相关的知识笔记 |
发现后,请用户确认:
在发现 + 用户偏好设置后,将剧本保存到 .claude/team-update-playbook.md。
阅读 references/playbook-format.md 获取完整模板。用发现的工具和用户偏好填写所有部分。如果未找到某项能力,请在剧本中注明为“不可用”。
确保 .claude/ 在 .gitignore 中(剧本包含不应提交的空间 ID 和偏好设置)。
从所有可用来源收集信息。使用剧本的“数据源”部分来了解需要调用哪些工具。
检查剧本的“上次运行”部分以获取上次更新时间戳。如果没有之前的运行记录,询问用户需要回溯多久(默认:24 小时)。
从每个可用来源收集:
| 来源 | 收集内容 | 工具 |
|---|---|---|
| Git 提交 | git log --oneline --since=<last-update> | Bash |
| 聊天消息 | 自上次更新以来配置频道中的消息 | 剧本中的聊天 MCP 工具 |
| 开放问题/PR | 最近更新或新创建的项目 | 剧本中的问题跟踪器 |
| 活动任务 | 进行中或最近完成的任务 | 剧本中的任务跟踪器 |
按主题(而非单个哈希值)对提交进行分组。注意任何已关闭的问题、已合并的 PR 或已完成的任务。标记任何需要回复的团队消息。
阅读 references/message-composition.md 了解消息模式。
遵循剧本的“消息风格”部分。一般原则:
向用户展示草稿。包括:
需要批准 : 未经用户明确批准,切勿发布到外部频道。
使用剧本中的聊天工具发布已批准的消息。如果没有可用的聊天工具,则输出格式化消息供用户手动发布。
发布后,更新剧本的“上次运行”部分,包含:
阅读自更新发布以来配置频道中的消息。寻找:
阅读 references/feedback-triage.md 了解分类模式。
使用剧本的“分类规则”部分。默认分类:
| 类型 | 操作 |
|---|---|
| 错误报告 | 创建问题(标签:bug) |
| 功能请求 | 创建问题(标签:enhancement) |
| 问题 | 为用户批准起草回复 |
| 阻塞项 | 立即标记,建议解决方案 |
| 确认 | 记录,无需操作 |
| 无关内容 | 忽略 |
呈现反馈摘要及建议操作:
## 反馈摘要
- Daniel: "我们能添加深色模式吗?" -> 创建问题(enhancement)
- Rabin: "暂存环境认证坏了" -> 创建问题(bug,优先级)
- Karen: "看起来不错!" -> 无需操作
执行这些操作吗?
需要批准 : 未经用户明确批准,切勿创建问题、发布回复或采取外部操作。
从所有收集的上下文(提交、问题、任务、反馈)中,识别:
向用户展示优先级列表。这仅供用户规划使用——请勿将其发布到任何频道。
## 建议的优先级
1. [阻塞项] 修复暂存环境认证(来自 Rabin 的反馈)
2. [高] 完成用户资料的 API 端点(当前冲刺)
3. [下一步] 深色模式支持(来自 Daniel 的请求)
4. [待办事项] 重构数据库查询
| 操作 | 级别 |
|---|---|
| 读取/创建剧本 | 直接执行 |
| 发现工具(首次运行) | 直接执行,与用户确认偏好 |
| 收集上下文(git、聊天、问题) | 直接执行 |
| 起草更新消息 | 直接执行,显示预览 |
| 发布到外部频道 | 需要批准 |
| 创建问题/任务 | 需要批准 |
| 向团队发布回复 | 需要批准 |
| 更新剧本“上次运行” | 直接执行 |
| 呈现计划/优先级 | 直接执行 |
该技能可在任何工具可用性级别下工作:
| 可用工具 | 体验 |
|---|---|
| 仅 Git | 总结提交,输出文本供手动发布 |
| Git + 聊天 | 完整的发布/阅读周期,手动创建问题 |
| Git + 聊天 + 问题 | 完整的周期,包含自动化问题创建 |
| Git + 聊天 + 问题 + 任务 + 知识 | 完整的周期,包含持久化跟踪 |
该技能响应不同的触发短语:
| 触发词 | 行为 |
|---|---|
| "team update" / "post update" | 完整周期:收集、起草、发布、阅读反馈 |
| "check team chat" / "what did the team say" | 仅阶段 3:阅读并分类反馈 |
| "standup" / "sync with team" | 阶段 1 + 2:收集并发布,跳过反馈 |
| "project update" | 阶段 1 + 2 + 4:收集、发布、规划(跳过反馈分类) |
| "feedback loop" | 阶段 3 + 4:阅读反馈并规划 |
| 时机 | 阅读 |
|---|---|
| 首次运行 — 保存剧本 | references/playbook-format.md |
| 首次运行 — 检测工具 | references/discovery-patterns.md |
| 撰写更新消息 | references/message-composition.md |
| 分类团队反馈 | references/feedback-triage.md |
每周安装次数
197
仓库
GitHub 星标
650
首次出现
2026年3月8日
安全审计
安装于
gemini-cli187
github-copilot187
opencode187
codex186
cline186
cursor186
Post project updates to team chat, read and triage feedback, and plan next steps. Adapts to whatever communication and project tools are available.
This skill uses a playbook file at .claude/team-update-playbook.md in the project root.
The playbook is plain markdown the user can edit. It captures tool configuration, channel preferences, message style, triage rules, and last-run metadata.
Check if .claude/team-update-playbook.md exists in the project root.
If it exists : Read it. All tool configuration, channel info, message style, and triage rules are in there. Jump to Phase 1 with known config.
If it does not exist : Run Phase 0b (Discovery) first.
Detect available capabilities by checking what MCP tools are connected and what local tools exist.
Read references/discovery-patterns.md for detection patterns.
Check for each capability category:
| Capability | How to detect | Fallback if missing |
|---|---|---|
| Chat | MCP tools matching chat, slack, discord, teams | Output formatted text for manual posting |
| Git | git rev-parse --is-inside-work-tree | Skip commit summaries |
| Issues | MCP tools matching github, linear, |
After discovery, ask the user to confirm:
After discovery + user preferences, save the playbook to .claude/team-update-playbook.md.
Read references/playbook-format.md for the full template. Fill in all sections with discovered tools and user preferences. If a capability was not found, note it as "Not available" in the playbook.
Ensure .claude/ is in .gitignore (the playbook contains space IDs and preferences that shouldn't be committed).
Collect information from all available sources. Use the playbook's "Data Sources" section to know which tools to call.
Check the playbook's "Last Run" section for the last update timestamp. If no previous run, ask the user how far back to go (default: 24 hours).
Gather from each available source:
| Source | What to collect | Tool |
|---|---|---|
| Git commits | git log --oneline --since=<last-update> | Bash |
| Chat messages | Messages in the configured channel since last update | Chat MCP tool from playbook |
| Open issues/PRs | Recently updated or newly created items | Issue tracker from playbook |
| Active tasks | In-progress or recently completed tasks | Task tracker from playbook |
Group commits by theme (not individual hashes). Note any issues closed, PRs merged, or tasks completed. Flag any team messages that need response.
Read references/message-composition.md for message patterns.
Follow the playbook's "Message Style" section. General principles:
Show the draft to the user. Include:
APPROVAL REQUIRED : Never post to external channels without explicit user approval.
Post the approved message using the chat tool from the playbook. If no chat tool is available, output the formatted message for the user to post manually.
After posting, update the "Last Run" section of the playbook with:
Read messages from the configured channel since the update was posted. Look for:
Read references/feedback-triage.md for classification patterns.
Use the playbook's "Triage Rules" section. Default classification:
| Type | Action |
|---|---|
| Bug report | Create issue (label: bug) |
| Feature request | Create issue (label: enhancement) |
| Question | Draft reply for user approval |
| Blocker | Flag immediately, suggest resolution |
| Acknowledgement | Note, no action needed |
| Off-topic | Ignore |
Present a summary of feedback with proposed actions:
## Feedback Summary
- Daniel: "Can we add dark mode?" -> Create issue (enhancement)
- Rabin: "Auth is broken on staging" -> Create issue (bug, priority)
- Karen: "Looks good!" -> No action
Proceed with these actions?
APPROVAL REQUIRED : Never create issues, post replies, or take external actions without explicit user approval.
From all gathered context (commits, issues, tasks, feedback), identify:
Show the prioritised list to the user. This is for the user's planning only -- do NOT post it to any channel.
## Suggested Priorities
1. [BLOCKER] Fix auth on staging (from Rabin's feedback)
2. [HIGH] Complete API endpoint for user profiles (current sprint)
3. [NEXT] Dark mode support (from Daniel's request)
4. [BACKLOG] Refactor database queries
| Action | Level |
|---|---|
| Read/create playbook | Just do it |
| Discover tools (first run) | Just do it, confirm preferences with user |
| Gather context (git, chat, issues) | Just do it |
| Draft update message | Just do it, show preview |
| Post to external channel | Approval required |
| Create issues/tasks | Approval required |
| Post replies to team | Approval required |
| Update playbook "Last Run" | Just do it |
| Present plan/priorities | Just do it |
The skill works at any level of tool availability:
| Available tools | Experience |
|---|---|
| Git only | Summarise commits, output text for manual posting |
| Git + Chat | Full post/read cycle, manual issue creation |
| Git + Chat + Issues | Full cycle with automated issue creation |
| Git + Chat + Issues + Tasks + Knowledge | Full cycle with persistent tracking |
The skill responds to different trigger phrases:
| Trigger | Behaviour |
|---|---|
| "team update" / "post update" | Full cycle: gather, draft, post, read feedback |
| "check team chat" / "what did the team say" | Phase 3 only: read and triage feedback |
| "standup" / "sync with team" | Phase 1 + 2: gather and post, skip feedback |
| "project update" | Phase 1 + 2 + 4: gather, post, plan (skip feedback triage) |
| "feedback loop" | Phase 3 + 4: read feedback and plan |
| When | Read |
|---|---|
| First run — saving playbook | references/playbook-format.md |
| First run — detecting tools | references/discovery-patterns.md |
| Composing update messages | references/message-composition.md |
| Classifying team feedback | references/feedback-triage.md |
Weekly Installs
197
Repository
GitHub Stars
650
First Seen
Mar 8, 2026
Security Audits
Gen Agent Trust HubPassSocketWarnSnykPass
Installed on
gemini-cli187
github-copilot187
opencode187
codex186
cline186
cursor186
通过 LiteLLM 代理让 Claude Code 对接 GitHub Copilot 运行 | 高级变通方案指南
31,600 周安装
jira| Skip or output text list |
| Tasks | MCP tools matching tasks, todos, asana | Skip or output text list |
| Knowledge | Basalt Cortex (~/Documents/basalt-cortex/) | Search for related knowledge notes |