list_calendars

"This skill needs access to your calendar to work — without it, we're just guessing. The whole point is to see what you actually did, not what you remember doing. Self-reported data is heavily biased.

Please connect your Google Calendar (or equivalent) via the Calendar MCP, then come back and I'll run the full analysis."

"I don't see a Slack integration. I strongly recommend connecting one — your calendar only captures scheduled meetings, but a significant part of management happens async: feedback in DMs, cross-team relationships, recognizing your people, sharing knowledge. Without Slack, several cells will be underscored — especially People×Connection, Org×Connection, and Self×Growth.

You can proceed with calendar-only, but the picture will be incomplete. Connect Slack when you can."

.agents/em-context.md

• Number of direct reports
• Whether any direct reports are themselves managers (manager of managers = MoM)
• Team size (total engineers, including indirect reports)
• The EM's seniority level/title if mentioned

"Quick context before I analyze: how many people do you directly manage, and are any of them managers themselves?"

• MoM: Their 1:1s are with other managers → scope shifts from People×Growth toward Org×Growth. Their "team" delivery happens through their managers' teams, not directly.
• Large team (6+): 2 1:1s per week is thin. 8 is appropriate. Scale expectations accordingly.
• Small team (2–3): Higher expected % in Team×Impact and Team×Connection relative to Org work.
• Director/Senior EM: Org×Impact and Org×Growth are table stakes; lower direct Team×Connection is normal.

list_events

/tmp/cal_events.json

**/em-grid-scorer/scripts/process_calendar.py

python "<script_path>" /tmp/cal_events.json <em_email> [report_email_1] [report_email_2] ...

• A human-readable summary table to stdout (print it to your context)
• Full grouped JSON to

  /tmp/em_grid_calendar_groups.json

/tmp/em_grid_calendar_groups.json

groups

• count

  — how many times it occurred

• total_minutes

  — total duration

• attendee_category

  — one of:

  solo

  ,

  1:1-report

  ,

  1:1-manager

  ,

  1:1-external

  ,

  team

  ,

  cross-team

  ,

  external-group

• sample_names

  — names of non-EM attendees

1. conversations.list

   (type: member) — get all channels the user belongs to
2. Categorize each as: team (your team's primary channel) / cross-team (other engineering or adjacent teams) / leadership (management-only, exec comms) / company-wide (general, announcements, social, random)
3. Note: does the user post here, or just read?

1. For each channel category, count the user's messages in the last 30 days — do NOT load full content yet
2. List DM conversations active in last 30 days — get partner names/IDs
3. Cross-reference DM partners against direct reports list: split into "DMs with direct reports" vs "DMs with others (peers, cross-dept, leadership)"
4. Count emoji reactions the user gave in the last 30 days, especially ❤️ 🎉 👏 — this is a People×Connection signal

1. Team channel: fetch the user's 20 most recent messages — classify as social/connective vs task/delivery
2. Cross-team channels where user is active: fetch user's 15 most recent messages — look for relationship-building vs technical collaboration vs business/impact language
3. DMs with direct reports: fetch last 10 user-authored messages per report — look for developmental content ("what do you want to work on", sharing resources, feedback patterns, personal check-ins) vs pure operational content (blockers, task status)
4. DMs with non-reports: note who they are and check for relationship-building signals

• Scope (Self / People / Team / Org) — from attendees
• Driver (Growth / Impact / Connection) — from purpose
• Total minutes = duration × occurrence count

• Level 1 (visible): attending cross-functional meetings, being present in shared channels
• Level 2 (appreciated): people seek you out, you're known for being helpful and curious
• Level 3 (trusted): you proactively help other depts achieve their goals before they ask — CS, QA, finance, HR. This is where real organizational trust is built.

• Find the cell with the most total minutes → that becomes 10
• All others:

  round((cell_minutes / max_minutes) × 10)

  — round to nearest whole number
• Cell with 0 minutes and no Slack signal: score = 0
• People×Connection floor: if the EM has weekly 1:1s with direct reports AND Slack DMs show warmth or personal check-ins, minimum score is 5

• 1:1s that Slack DMs confirm are purely operational (no warmth, no development signal): People×Growth down 1, People×Connection stays at floor
• Clear "always green" discipline visible in calendar (consistent sprint planning + review cadence): Team×Impact up 1
• Slack shows consistent developmental DMs with reports (resources shared, career discussed): People×Growth up 1
• Org×Impact shows Level 3 activity (proactively helping other depts): Org×Impact up 1

Growth — activities that build capability for the future: your own learning, developing your engineers, building team skills, growing the org's knowledge. Impact — activities that produce results now: shipping reliably, moving business metrics, creating visibility, making decisions that stick. Connection — activities that build relationships: with your engineers as individuals, your team as a unit, and the broader organization.

Want a deeper breakdown of any column? Ask "explain [Growth / Impact / Connection]" after reviewing your grid.

• 🔴 0–2 (critical gap)
• 🟠 3–4 (weak)
• 🟡 5–6 (moderate)
• 🟢 7–8 (good)
• 💚 9–10 (strong)

undefined

• Which row dominates? Which driver dominates?
• What's the implication for the team, the EM's career, and the org?
• If there's a tension or a flag worth naming (e.g. Self×Impact unusually high = possible delegation risk), name it here.

• "You're in execution mode — Team×Impact dominates and almost everything else is thin. Your team ships, but you're not investing in their development, your own growth, or your organizational presence."
• "People×Growth is strong, which is real investment. But Team×Impact is weak — delivery probably lives or dies by the team's own discipline, not your active involvement."

• Cell name and score
• What's missing in practice: one sentence about what's not happening and why it matters
• One action this week: small, specific, immediately doable — read

  references/suggested-actions.md

  and pick the most contextually relevant option. Do not suggest anything already visible in calendar or Slack.

Overall EM Score: X.X / 10

• What's genuinely working (don't just list high scores — name why they matter)
• The one thing that, if improved, would have the highest compounding effect on everything else
• A forward-looking sentence: what does this grid look like in 3 months if nothing changes?

"Overall: 5.8 / 10. Your delivery and people-development engine is solid — that's the foundation. The compounding gap is Team×Growth: a team navigating an AI pivot without collective learning will drift in quality before anyone names it. In 3 months at this pace, you'll still be shipping, but the skill debt will start showing in code review quality and in engineer confidence on the harder technical decisions."

Calendar-only analysis — People×Connection, Org×Connection, and Self×Growth are likely underscored if you're active in DMs and channels. Connect Slack for a more complete picture.