Team Health logo

Team Health

Organization
techwolf-ai
team-health

Periodic check on team dynamics, engagement signals, and development trajectory for all direct reports. Surfaces patterns across the team: who might need more challenge, who might need more support, who hasn't had a 1:1 recently. Uses two universal lenses: performance & growth, and wellbeing & connection. Outputs are prompts for reflection, not diagnoses.

Overview

Publishertechwolf-ai
Repositoryai-first-toolkit
Skill nameteam-health
Stars
138
Forks
7
Bundled files
2
LicenseMIT
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.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by techwolf-ai on GitHub. Read the source before you install it.

Installation

Install the Team Health 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/techwolf-ai/ai-first-toolkit/tree/main/plugins/people-management/skills/team-health
  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/techwolf-ai/ai-first-toolkit.git /tmp/ai-first-toolkit
mkdir -p .claude/skills
cp -r /tmp/ai-first-toolkit/plugins/people-management/skills/team-health .claude/skills/team-health
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Team Health 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 Team Health 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 Team Health 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.

Team Health Check

Two lenses, always. "Development" asks: is this person growing and performing? "Wellbeing" asks: is this person thriving, connected, and energised? Great managers hold both.

A periodic overview of team dynamics, engagement signals, wellbeing, and development trajectory across all direct reports.

When to Use

  • Weekly or biweekly team health review
  • Before calibration or planning meetings
  • When the manager says "how's my team doing?", "team health check", "anyone I should check in with?"
  • When preparing for skip-level conversations

Instructions

If any MCP connector is unavailable, follow the connector unavailability protocol in references/operating-principles.md.

1. Load Team Context

Read from manager-context/:

  • manager-profile.md: full list of direct reports
  • team/: individual profiles with goals, projects, last review dates
  • sources.md: channels and data locations per team member

If context is missing, note it and work with available sources.

2. Scan Per Team Member

For each direct report, gather data from the last 14 days (or since last health check):

Activity & Engagement (Slack):

  • Message volume in team/project channels (relative to their baseline if known)
  • Types of messages: asking questions, answering questions, sharing updates, celebrating, flagging issues
  • Channels they're active in
  • Any public wins or recognition received
  • Any public frustration or repeated blockers

1:1 Cadence (Calendar):

  • When was their last 1:1 with the manager?
  • Were recent 1:1s kept or cancelled?
  • Are they overdue for a 1:1?

Development Goals (Notion/Drive):

  • Last time their goals were updated
  • Any progress notes or self-assessments
  • Are there development areas with no recent activity?

Workload Signals (Calendar + Slack):

  • Meeting load (heavy/normal/light for their role)
  • Are they in channels/meetings outside their usual scope? (scope expansion, could be good or concerning)

Wellbeing & Connection Signals (Slack + Calendar):

  • Energy & wellbeing: late-night messages, weekend activity, signs of overwork
  • Connection: are they participating in non-work channels (#random, social threads, team celebrations)?
  • Celebration: have they been recognised or praised recently? Have they celebrated others?
  • Tone: are their messages upbeat, neutral, or showing signs of frustration/fatigue? (use as a soft signal only, never diagnose)
  • Fun & enjoyment: any signs of passion, enthusiasm, or joy in their work (shipping excitement, sharing wins, volunteering for things)?

3. Synthesise Per Person

For each team member, produce a brief profile covering both lenses:

### [Name]: [Role]

**🎯 Development & Performance:**
**Activity:** [Normal / Increased / Decreased], [1-line evidence]
**Recent wins:** [list any, or "None surfaced"]
**Goals:** [last updated date], [current / stale]
**Development focus:** [area from goals], [evidence of progress / no visible progress]
**Growth signals:** [scope expansion, new skills, leadership behaviours, or "None"]

**🫂 Wellbeing & Connection:**
**Energy:** [Balanced / High output / Signs of overwork], [evidence, e.g., "messages after 22:00 on 3 nights"]
**Connection:** [Active in social channels / Quiet / Only work-related activity]
**Celebrated/been celebrated:** [yes, details / not recently]
**Tone:** [Positive / Neutral / Worth checking in], [soft signal only]

**Last 1:1:** [date], [on track / overdue]
**Signals to explore:** [friction, blockers, wellbeing patterns, or "None"]

4. Surface Team-Level Patterns

Look across the team for patterns in both dimensions:

🎯 Development & Performance patterns:

  • Recognition gap: Anyone who hasn't received public recognition in >2 weeks?
  • 1:1 gap: Anyone overdue for a 1:1?
  • Goal staleness: Anyone whose development goals haven't been updated in >6 weeks?
  • Growth signals: Anyone taking on new scope or showing leadership behaviours?
  • Performance signals: Anyone showing decreased engagement across multiple indicators?

🫂 Wellbeing & Connection patterns:

  • Energy imbalance: Anyone consistently working late, weekends, or showing signs of overwork?
  • Isolation risk: Anyone who's gone quiet in social channels or stopped engaging beyond work tasks?
  • Celebration deficit: Is the team celebrating wins? Are specific people consistently uncelebrated?
  • Fun factor: Is there joy and energy in team channels, or has everything become purely transactional?
  • Workload imbalance: Anyone significantly more or less loaded than peers?

5. Produce the Health Check

Read references/output-template.md for the full output template structure.

6. Present

Here's your team health check. These are signals for your reflection. You know your people better than any tool.

Want me to prep a 1:1 for anyone specific?

7. Sub-Agent Review

Spawn a sub-agent to review the health check with fresh eyes. The reviewer should:

  • Check that both lenses (Development & Performance and Wellbeing & Connection) are meaningfully covered. Neither should be thin or skipped.
  • Check for baseline awareness: are signals calibrated against known baselines, or is normal behaviour being flagged?
  • Verify that language stays in "signal" territory, never crossing into diagnosis ("seems disengaged", "is struggling").
  • Check that celebration and recognition are given adequate weight, not just problem-flagging.
  • Flag any team member who appears to have very thin data. The manager should know where the blind spots are.

Incorporate the reviewer's feedback before presenting the final health check to the manager.

Important Notes

Read references/operating-principles.md for shared operating principles (data scope, DM flagging, signals vs diagnoses, connector unavailability).

Additional notes specific to this skill:

  • Celebrate first. Lead with wins, recognition, and positive energy. Wellbeing & Connection starts with seeing the good.
  • Both lenses, every time. Don't skip Wellbeing & Connection when the team is performing well. High performance without care leads to burnout. Don't skip Development & Performance when someone is struggling. Care without growth isn't enough.
  • Goals are the anchor for growth. The most actionable Development & Performance insight is usually about development goals: are they current? Is there visible progress?
  • Connection is the anchor for care. The most actionable Wellbeing & Connection insight is usually about belonging: does this person feel seen, celebrated, and connected?
  • Don't run too frequently. Weekly or biweekly is ideal. Daily health checks would over-index on noise.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Team Health AI skill do?

Periodic check on team dynamics, engagement signals, and development trajectory for all direct reports. Surfaces patterns across the team: who might need more challenge, who might need more support, who hasn't had a 1:1 recently. Uses two universal lenses: performance & growth, and wellbeing & connection. Outputs are prompts for reflection, not diagnoses.

Why use Team Health on TypingMind?

Because you install it once and use it with any model. Team Health 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 Team Health in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/techwolf-ai/ai-first-toolkit/tree/main/plugins/people-management/skills/team-health. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Team Health?

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 Team Health?

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

Is the Team Health AI skill free?

Yes. It is published on GitHub by techwolf-ai under the MIT license. 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 👇