Channel Audit logo

Channel Audit

OrganizationPopular
microsoft
channel-audit

Audit Teams channels across your teams — identify inactive channels, low‑engagement conversations, channels with no recent posts, and recommend cleanup actions.

Overview

Publishermicrosoft
Repositorywork-iq
Skill namechannel-audit
Stars
1K
Forks
140
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by microsoft on GitHub. Read the source before you install it.

Installation

Install the Channel Audit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/microsoft/work-iq/tree/main/plugins/workiq-productivity/skills/channel-audit
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/microsoft/work-iq.git /tmp/work-iq
mkdir -p .claude/skills
cp -r /tmp/work-iq/plugins/workiq-productivity/skills/channel-audit .claude/skills/channel-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Channel Audit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Channel Audit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Channel Audit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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.

Frequently asked questions

What does the Channel Audit AI skill do?

Audit Teams channels across your teams — identify inactive channels, low‑engagement conversations, channels with no recent posts, and recommend cleanup actions.

Why use Channel Audit on TypingMind?

Because you install it once and use it with any model. Channel Audit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Channel Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/microsoft/work-iq/tree/main/plugins/workiq-productivity/skills/channel-audit. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Channel Audit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Channel Audit?

As many as you like. As long as a model supports skills, you can use Channel Audit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Channel Audit AI skill free?

It is published on GitHub by microsoft. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇