channel-audit

作者: microsoft

审计团队中的Teams频道——识别不活跃频道、低互动对话、近期无帖子的频道,并建议清理操作。

npx skills add https://github.com/microsoft/work-iq --skill channel-audit

Channel Audit

Audit all Microsoft Teams channels across your teams to assess activity levels and engagement health. Identifies inactive channels, stale conversations, and low‑engagement spaces — then presents a prioritized audit report with recommended cleanup actions such as archiving, merging, or reviving channels.

When to Use

  • "Audit my Teams channels"
  • "Which channels are inactive?"
  • "Find dead channels across my teams"
  • "Teams channel cleanup report"
  • "Show me channels with no posts in the last month"
  • "Which channels should we archive?"
  • "Channel health check for the Engineering team"

Instructions

Step 1: Identify the User

workiq-ask (
  question: "What is my profile information including display name, email, and time zone?"
)

Extract displayName, email, and timeZone for date calculations.

Step 2: Discover All Teams and Channels

List every team and their channels:

workiq-ask (
  question: "List all Microsoft Teams teams I belong to. For each team, list all channels including the channel name, description, type (standard, private, shared), and creation date."
)

Build an inventory of every channel:

  • Team name
  • Channel name, description
  • Channel type (standard, private, shared)
  • Created date (from channel metadata)

If the response is too large or truncated, query teams individually:

workiq-ask (
  question: "List all channels in the '<team name>' team including channel name, description, type, and creation date."
)

Step 3: Assess Channel Activity

For each channel (or batch of channels within a team), pull recent messages to measure activity:

workiq-ask (
  question: "Show me the 10 most recent messages in the '<channel name>' channel of the '<team name>' team. For each message include the sender, date, content summary, reply count, and whether it was from a bot or connector."
)

For each channel, calculate:

  • Last message date — when the most recent message was posted
  • Days since last post — time delta from today
  • Message count (in the sample) — indicator of volume
  • Unique authors — how many distinct people posted
  • Reply depth — are messages getting replies or going unanswered?
  • Content type — are posts substantive or just bot notifications?

Step 4: Get Channel Membership Data

For each channel (especially those flagged as low‑activity):

workiq-ask (
  question: "How many members are in the '<channel name>' channel of the '<team name>' team? List the member count."
)

Record:

  • Member count — total members in the channel
  • Activity ratio — unique posters vs. total members (engagement metric)

Step 5: Classify Channel Health

Categorize each channel based on activity metrics:

🟢 Active — Messages within the last 7 days, multiple authors, replies present

  • Engagement: healthy, no action needed

🟡 Slow — Last message 7–30 days ago, limited authors

  • Recommendation: monitor, consider consolidating

🟠 Stale — Last message 30–90 days ago, very few participants

  • Recommendation: notify channel owners, consider archiving

🔴 Dead — No messages in 90+ days

  • Recommendation: archive or delete

⚪ Bot‑Only — Recent messages, but only from automated bots or connectors

  • Recommendation: review if the channel serves a purpose beyond bot notifications

Step 6: Identify Potential Duplicates

Compare channel names and descriptions across teams to find potential duplicates:

  • Channels with similar names (e.g., "#design" and "#design-team")
  • Channels with overlapping membership and similar topics
  • Flag these as merge candidates

Step 7: Compile the Audit Report

Output Format

🔍 CHANNEL AUDIT REPORT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📅 Audit date: {date}
👤 Audited by: {displayName}
🏢 Teams scanned: {N}  ·  📢 Channels audited: {N}

📊 HEALTH OVERVIEW
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🟢 Active:    {N} channels  ({percentage}%)
🟡 Slow:      {N} channels  ({percentage}%)
🟠 Stale:     {N} channels  ({percentage}%)
🔴 Dead:      {N} channels  ({percentage}%)
⚪ Bot‑only:  {N} channels  ({percentage}%)

🔴 DEAD CHANNELS — Recommend Archive ({count})
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  {Team} › #{Channel}
     📅 Last post: {date} ({N} days ago)
     👥 Members: {N}  ·  💬 Last author: {name}
     💡 Action: Archive
  
  {Team} › #{Channel}
     📅 Last post: {date} ({N} days ago)
     👥 Members: {N}  ·  💬 Last author: {name}
     💡 Action: Archive

🟠 STALE CHANNELS — Monitor / Consider Archiving ({count})
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  {Team} › #{Channel}
     📅 Last post: {date} ({N} days ago)
     👥 Members: {N}  ·  📝 Active posters: {N} ({ratio}%)
     💡 Action: Notify owner, review purpose

🟡 SLOW CHANNELS — Watch List ({count})
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  {Team} › #{Channel}
     📅 Last post: {date} ({N} days ago)
     👥 Members: {N}  ·  📝 Active posters: {N}

⚪ BOT‑ONLY CHANNELS ({count})
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  {Team} › #{Channel}
     🤖 Only automated posts detected
     💡 Action: Review if bot output is still needed

🔄 POTENTIAL DUPLICATES
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  • {Team1} › #{Channel A}  ↔  {Team2} › #{Channel B}
    Reason: Similar names, overlapping members
    💡 Action: Consider merging

🟢 HEALTHY CHANNELS ({count})
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  {Team} › #{Channel} — {N} posts last 7d, {N} authors
  {Team} › #{Channel} — {N} posts last 7d, {N} authors

📋 RECOMMENDED ACTIONS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  1. 🗑️ Archive {N} dead channels
  2. 📧 Notify owners of {N} stale channels
  3. 🔄 Review {N} potential duplicate pairs
  4. 🤖 Review {N} bot‑only channels

Parameters

ParameterRequiredDefaultDescription
TeamsNoAll user's teamsSpecific teams to audit
Inactive ThresholdNo30 daysDays without posts to flag as stale
Dead ThresholdNo90 daysDays without posts to flag as dead
Include HealthyNotrueShow healthy channels in the report
Include GeneralNofalseInclude default "General" channels
Sort ByNoLast activitySort order: "last-activity", "member-count", "team"

Required MCP Tools

MCP ServerToolPurpose
workiq (Local WorkIQ CLI)askUser identity, team/channel discovery, message activity retrieval, and membership data

Tips

  • Run monthly to keep your Teams workspace clean and navigable.
  • Say "audit Engineering team only" to scope to a single team for faster results.
  • Use "show only dead channels" to skip healthy channels and focus on cleanup.
  • After identifying channels to archive, coordinate with team owners before taking action.
  • After identifying channels to clean up, coordinate with team owners to take action.
  • General channels cannot be archived or deleted — they are skipped by default.

Examples

Full workspace audit

"Audit all my Teams channels and tell me which ones I should clean up."

Scans every team the user belongs to, classifies all channels by health status, detects bot-only and duplicate channels, and produces a complete prioritized report with archive and merge recommendations.


Single-team audit with narrow threshold

"Do a channel health check for the Engineering team — flag anything with no posts in the last 2 weeks."

Scopes the audit to the Engineering team only and applies a custom inactive threshold of 14 days instead of the default 30, surfacing slow channels that would otherwise be missed.


Dead channels only, ready for archiving

"Show me only the dead channels across all teams — nothing healthy, just what we should archive."

Runs a full scan but filters the output to dead channels (90+ days without posts), listing each with member count, last author, and a direct archive recommendation — ideal for a quick cleanup session.

Error Handling

Cannot retrieve user details

  • Cause: ask returns an authentication or permission error.
  • Action: Re-authenticate and retry. Ensure the WorkIQ CLI has proper Microsoft 365 permissions.

Team list is empty or incomplete

  • Cause: ask returns no teams or only a subset of expected teams.
  • Action: Confirm the user is an active member of the expected teams in the Teams admin center. Guest accounts may have restricted visibility.

Channel message retrieval fails for one or more channels

  • Cause: ask returns an error or no data for private or shared channels where the user lacks membership.
  • Action: The audit skips inaccessible channels and notes them in the report as ⚠️ Access Restricted. Request channel membership or ask a channel owner to run the audit.

No messages returned but channel exists

  • Cause: The channel was created but never had any posts, or messages were deleted.
  • Action: The channel is treated as Dead (0 days activity) and flagged for archiving. Verify manually before archiving if the channel was recently created.

Member list unavailable

  • Cause: ask cannot retrieve membership data for a private channel due to permission restrictions.
  • Action: Member count and activity ratio are omitted for that channel; all other metrics are still reported. The channel is still classified by message activity alone.

Large workspace timeouts

  • Cause: Auditing teams with dozens of channels may require many ask calls and take significant time.
  • Action: Scope the audit to a single team (e.g., "audit the Marketing team only") to reduce call volume, or run the audit during off-peak hours.

来自 microsoft 的更多技能

oss-growth
microsoft
OSS增长黑客角色
agent-framework-azure-ai-py
microsoft
使用Microsoft Agent Framework Python SDK(agent-framework-azure-ai)构建Azure AI Foundry代理。在创建使用AzureAIAgentsProvider的持久化代理、使用托管工具(代码解释器、文件搜索、网络搜索)、集成MCP服务器、管理对话线程或实现流式响应时使用。涵盖函数工具、结构化输出和多工具代理。
development
airunway-aks-setup
microsoft
在AKS上设置AI Runway——从裸集群到运行模型。涵盖集群验证、控制器安装、GPU评估、提供商设置和首次部署。适用场景:“设置AI Runway”、“接入AKS集群”、“安装AI Runway”、“airunway设置”、“将模型部署到AKS”、“在AKS上进行GPU推理”、“在AKS上配置KAITO”、“在AKS上运行LLM”、“在AKS上使用vLLM”、“在AKS上设置模型服务”、“AI Runway控制器”。
devops
appinsights-instrumentation
microsoft
使用Azure Application Insights对Web应用进行插桩的指南。提供遥测模式、SDK设置和配置参考。适用场景:如何对应用进行插桩、App Insights SDK、遥测模式、什么是App Insights、Application Insights指南、插桩示例、APM最佳实践。
devops
applicationinsights-web-ts
microsoft
使用Application Insights JavaScript SDK(@microsoft/applicationinsights-web)为浏览器/Web应用添加检测。用于真实用户监控(RUM)——页面视图、点击、AJAX/fetch依赖项、异常、自定义事件,以及与后端OpenTelemetry追踪关联的浏览器端GenAI代理追踪。涵盖SDK加载器脚本和npm设置、框架扩展(React、React Native、Angular)、点击分析、遥测初始化器,以及从浏览器发出的代理/工具/模型跨度所遵循的OTel GenAI语义约定。
devops
azure-ai-anomalydetector-java
microsoft
使用适用于 Java 的 Azure AI 异常检测器 SDK 构建异常检测应用程序。在实现单变量/多变量异常检测、时间序列分析或 AI 驱动的监控时使用。
development
azure-ai-language-conversations-py
microsoft
使用azure-ai-language-conversations Python SDK实现对话语言理解(CLU)。当使用ConversationAnalysisClient分析对话意图和实体、构建NLP功能或将语言理解集成到应用程序中时使用。
development
azure-ai-ml-py
microsoft
Azure Machine Learning SDK v2 for Python。用于机器学习工作区、作业、模型、数据集、计算资源和管道。 触发词:“azure-ai-ml”、“MLClient”、“工作区”、“模型注册表”、“训练作业”、“数据集”。
development