Agent skill

Em Grid Scorer

by manager-dot-dev in manager-dot-dev/manager-skills

Score an Engineering Manager's coverage across all 12 cells of the EM Grid based on their calendar and Slack.

MITAuto-check passedKnowledge Management

Install Em Grid Scorer

skills CLI
$ npx skills add manager-dot-dev/manager-skills --skill em-grid-scorer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install manager-dot-dev/manager-skills em-grid-scorer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/manager-dot-dev/manager-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/em-grid-scorer .claude/skills/em-grid-scorer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
em-grid-scorer
GitHub stars
114
Token cost
~5.8k tokens
SKILL.md length
3,034 words
Files
4 (incl. scripts, references)
Skills in repo
27
Repo updated
First seen
Licence
MIT

At a glance

Score an Engineering Manager's coverage across all 12 cells of the EM Grid based on their calendar and Slack.

  • Works in 7 steps: Prerequisites → Load Role Context → Gather and Process Calendar Data… → …
  • Someone wants to understand where theyre spending their management energy
  • SKILL.md covers Step 0: Prerequisites, Step 1: Load Role Context, Step 2: Gather and Process… and Step 3: Gather Slack Data (if…, plus 4 more sections
  • Runs Python scripts from its folder; calls python

What it does

Em Grid Scorer is an agent skill from manager-dot-dev/manager-skills. Score an Engineering Manager's coverage across all 12 cells of the EM Grid based on their calendar and Slack. Use this skill whenever someone wants to understand where they're spending their management energy, find blind spots, get a monthly self-reflection on their EM focus, or hear phrases like "score my EM grid", "where am I spending time as a manager", "what are my blind spots", "analyze my calendar as EM", "which EM areas am I neglecting", "how balanced is my management focus", or "check my EM grid…

Its SKILL.md is about 5.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `references/driver-explanations.md`, `references/suggested-actions.md` and `scripts/process_calendar.py`).

It sits in Knowledge Management, covering Journaling and reflection. It works with Slack and Model Context Protocol. The repository describes itself as: Skills for engineering managers. The licence is MIT.

When your agent uses it

  • Someone wants to understand where theyre spending their management energy
  • Find blind spots
  • Get a monthly self-reflection on their EM focus
  • Hear phrases like score my EM grid

Example prompts

  • “score my EM grid”
  • “where am I spending time as a manager”
  • “what are my blind spots”
  • “/em-grid-scorer”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Prerequisites
  2. Load Role Context
  3. Gather and Process Calendar Data Efficiently
  4. Gather Slack Data (if available)
  5. Classify Each Event Group
  6. Score Each Cell
  7. Output

What it can do on your machine

Read from SKILL.md and the folder at commit c47ebc7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Em Grid Scorer loads about 5.8k tokens when it runs, and up to ~8.9k if it reads all its reference files. Until then it costs about 155 tokens; SKILL.md has 3,034 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~155
When it runs · the whole SKILL.md, loaded when a task matches
~5.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from manager-dot-dev/manager-skills at commit c47ebc7, republished under its MIT licence (© manager-dot-dev). 3,034 words, ~5,833 tokens.

Download SKILL.mdSave it as .claude/skills/em-grid-scorer/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
em-grid-scorer
description
Score an Engineering Manager's coverage across all 12 cells of the EM Grid based on their calendar and Slack. Use this skill whenever someone wants to understand where they're spending their management energy, find blind spots, get a monthly self-reflection on their EM focus, or hear phrases like "score my EM grid", "where am I spending time as a manager", "what are my blind spots", "analyze my calendar as EM", "which EM areas am I neglecting", "how balanced is my management focus", or "check my EM grid coverage". Always pull live calendar data — never ask the user to describe their week manually.

EM Grid Scorer

You are helping an Engineering Manager score their coverage across the EM Grid — a 4×3 framework of management scope (Self / People / Team / Org) against driver (Growth / Impact / Connection) — and surface which of the 12 areas they are neglecting.

The goal is a rigorous, honest, data-driven assessment. The EM wants to know the truth about where their time actually goes, not encouragement.


Step 0: Prerequisites

Calendar MCP — required

Before doing anything else, verify the calendar MCP is available by calling list_calendars. If it fails or returns nothing, stop immediately and say:

"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."

Do not proceed without calendar access.

Check if a Slack MCP is available. If it is not connected, say:

"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."

Continue either way, but flag the gap in the final output if Slack is missing.

Time window

Default to the last 30 days. Do not ask. State it upfront and proceed. Only deviate if the user explicitly requests a different period.

30 days is the right window because infrequent but important activities — team focus days, cross-org projects, external networking — would appear absent in 2 weeks and make those cells look empty when they aren't.


Step 1: Load Role Context

Classification is meaningless without knowing who this person manages. Before scoring anything:

Check em-context first. Read .agents/em-context.md if it exists. Extract:

  • 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

If em-context doesn't exist or is missing this, ask exactly one question:

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

Do not ask anything else manually.

How role context changes classification:

  • 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.

Step 2: Gather and Process Calendar Data Efficiently

Fetch events

Call list_calendars to identify work-relevant calendars. Call list_events for the last 30 days. Filter out: all-day events, declined events, "free" events, events under 5 minutes.

Process with the bundled script

A month of calendar data can be 150–250 raw events. Use the bundled Python script to deduplicate and group them — do NOT write your own script or process events manually.

Step 1: Save the raw MCP output

When you call list_events, save the full JSON response to /tmp/cal_events.json using the Write tool (or Bash redirect).

Step 2: Find and run the script

Use Glob to find the script: search for **/em-grid-scorer/scripts/process_calendar.py. Then run it:

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

Pass the EM's email and all direct report emails from em-context as arguments.

The script outputs:

  • A human-readable summary table to stdout (print it to your context)
  • Full grouped JSON to /tmp/em_grid_calendar_groups.json

Step 3: Load the grouped data

Read /tmp/em_grid_calendar_groups.json. Each entry in groups is a unique event pattern with:

  • 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

Classify each group (not each raw event) in Step 4.

Cross-reference attendees for accurate scope

The script's attendee_category already handles most scope decisions. Use it as the primary signal. Cross-check against em-context for edge cases: direct report names not in the email list, MoM patterns, or unusually large meetings that the category might miscategorize.


Step 3: Gather Slack Data (if available)

Goal: classification signal, not a comprehensive audit. Do not read all messages. Use this three-phase protocol.

Phase 1 — Channel landscape (~5 calls)
  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?
Phase 2 — Activity distribution (~10 calls)
  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
Phase 3 — Targeted content sampling (~10–15 calls)
  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
What Slack maps to
Slack signalGrid cell
DMs with direct reports containing personal check-ins, warmth, life questionsPeople×Connection
DMs with direct reports sharing resources, career questions, developmental feedbackPeople×Growth
Social/celebratory messages in team channel, reactions to team members' postsTeam×Connection
Messages in leadership/exec channels with business languageOrg×Impact
Messages or DMs with cross-dept people (non-task)Org×Connection
User sharing articles, asking technical questions, referencing learningSelf×Growth
Timely informal feedback to engineers close to an eventPeople×Connection

Classify the pattern across each channel type, not individual messages.


Step 4: Classify Each Event Group

For each unique event pattern from Step 2:

  • Scope (Self / People / Team / Org) — from attendees
  • Driver (Growth / Impact / Connection) — from purpose
  • Total minutes = duration × occurrence count
Scope rules
AttendeesScope
No attendees / blocked solo timeSelf
1:1 with your own manager or skip-levelSelf
1:1 with a direct reportPeople
Whole team or majority of your teamTeam
Your team + people from other teamsOrg
Entirely outside your team (other depts, execs, customers)Org
Hiring interviewsPeople
Driver rules
PurposeDriver
Building capabilities, learning, developing for the futureGrowth
Producing results, shipping, moving metrics, unblocking deliveryImpact
Building relationships, belonging, being seen and appreciatedConnection
The 12 cells — detailed definitions

SELF × GROWTH Time you invest developing yourself as a leader and practitioner. You are the student.

Counts: coding/building with AI tools, taking courses, watching technical talks, reading management or engineering books/newsletters, receiving coaching or mentorship, experimenting with new methodologies, career planning sessions with your own manager, deliberate reflection time.

Does NOT count: consuming news passively, admin, technical work done primarily for delivery rather than learning.


SELF × IMPACT Time you personally produce something of value — not through your team.

Counts: deep work producing strategy docs/RFCs/post-mortems, writing performance reviews or promotion cases, building internal tools/automations yourself, making key architectural decisions solo, personal firefighting (hands on keyboard), preparing impactful presentations for leadership.

Does NOT count: facilitating meetings where others produce the output. Admin. Reading or learning (Self×Growth).


SELF × CONNECTION Building YOUR professional network outside your current company.

Counts: calls with peers at other companies, maintaining former-colleague relationships professionally, attending industry events to network, writing publicly (LinkedIn, blog, newsletter), participating in professional communities.

Does NOT count: internal company networking (Org×Connection). LinkedIn scrolling without engagement.


PEOPLE × GROWTH Deliberately developing your direct reports — their careers, skills, next level. Intentional and forward-looking.

Counts: 1:1s where you explicitly discuss career goals, growth plan, or next role; writing promotion cases; pattern-level developmental feedback; intentional stretch assignment delegation; helping an engineer prepare a talk, article, or new responsibility; shadowing or team-switching; matching work to driver type; hiring interviews; explicit career conversations.

Does NOT count: 1:1s that are purely task status. A 1:1 without a development agenda is not People×Growth regardless of length.

For MoM: 1:1s with manager-reports should focus on their leadership development, not just their team's delivery.


PEOPLE × IMPACT Helping engineers connect with and contribute to real business outcomes.

Counts: inviting engineers to customer calls or business reviews; sharing product metrics/usage data in 1:1s; explaining WHY they're building something (not just the spec); giving engineers the chance to present shipped work to leadership; helping them write compelling announcements; bringing business stakeholders to the team.

Does NOT count: pure delivery management (Team×Impact). Engineers passively CC'd on a meeting.


PEOPLE × CONNECTION The personal relationship layer — engineers feeling genuinely seen, appreciated, and psychologically safe.

Counts: asking about family, life events, hobbies and actually remembering; specific genuine recognition (not "great job" — what exactly); noticing when someone seems off and checking in; salary and compensation advocacy; being a safe space for personal or vulnerable topics; timely informal feedback delivered with respect; celebrating life events; letting engineers announce good news themselves.

Calibration — weekly 1:1s matter here: If the EM has weekly 1:1s AND Slack DMs show warmth, personal check-ins, or informal connection with reports, People×Connection should be scored no lower than 5 regardless of explicit "connection activities" on the calendar. The relationship is being maintained — it just happens inside 1:1s and DMs rather than in standalone activities. Only score lower if DMs are purely operational or 1:1s are infrequent.

Does NOT count: team social events (Team×Connection). Purely performative appreciation.


TEAM × GROWTH Building the collective capability of the team — skill gaps, technical maturity, learning together.

Counts: knowledge mapping (who knows what, bus factor risks — flag explicitly if this is absent); technical talks or L&D sessions for the team; post-mortem deep dives where the team actually learns; retrospectives that cause real behavior change; open source work as a team; AI tools days, hackathons with learning goals; architecture reviews involving the whole team; introducing new engineering practices.

Does NOT count: sprint planning/delivery standups (Team×Impact). Team social events (Team×Connection).


TEAM × IMPACT The delivery engine — consistent execution, shipping on time, producing real value.

Counts: sprint planning and goal-setting (especially "always green" — minimal confident goals set and tracked); sprint reviews and demos; daily standups focused on blockers and delivery; roadmap planning with PM; actively removing blockers; monitoring feature adoption post-release; incident coordination; getting technical debt onto the roadmap with business justification.

Quality signal: consistent sprint goal achievement (evidence of "always green" discipline) scores higher than many delivery meetings with no goal-tracking pattern visible.

Does NOT count: 1:1s. Social activities.


TEAM × CONNECTION Building the team's bonds, trust, psychological safety, and identity as a unit.

Counts: team meetings that go beyond task updates (genuine sharing, culture discussion); team focus days or offsites; social activities (games, lunches, volunteering); personal talks where engineers share something they care about; celebrating shipped work together; playful hackathons; shared humor channels, team traditions.

Does NOT count: task-update standups. Work-sprint-only focus days.


ORG × GROWTH Contributing to the broader organization's capabilities — things that outlast your team.

Counts: leading or significantly contributing to cross-team technical initiatives; hiring panels for roles outside your team; mentoring people outside your direct reports; contributing to org-wide processes (onboarding, career ladders, engineering standards); leading internal guilds or communities of practice; speaking at internal all-hands or tech talks; helping another EM think through a problem.

Does NOT count: attending (but not contributing to) org-wide meetings.


ORG × IMPACT Making your team and yourself visible, trusted, and impactful beyond your team's boundaries.

Counts: regular touchpoints with stakeholders outside engineering; proactively helping other departments achieve their goals; presenting team results to senior leadership; getting technical work defended in roadmap conversations; speaking in business terms (ROI, retention, churn) with leaders; being part of org-level decisions.

Positioning level — note which level the EM is operating at:

  • 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.

Does NOT count: internal team delivery. Attending stakeholder meetings passively.


ORG × CONNECTION Being known and liked across the organization — goodwill and allies beyond your team.

Counts: the "new person rule" (intentional coffee chat with someone new each week); cross-department informal 1:1s; engaging with other teams' announcements; participating genuinely in company-wide social events; following up on personal things learned about colleagues in other teams; proactive DMs to people you don't know well.

Does NOT count: external professional networking (Self×Connection). Stakeholder management with a business agenda (Org×Impact).


Show full SKILL.md (880 more words)Show less

Step 5: Score Each Cell

Raw minutes: total duration of classified events per cell (split proportionally when an event covers two cells)

Add Slack signal: for cells where Slack data reveals meaningful uncalendared activity, add an estimated 60–240 minutes per month per cell depending on how active the pattern appeared. Be conservative — err toward underestimating rather than inflating.

Normalize to whole numbers (0–10):

  • 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

Quality adjustment (±1 point, applied before rounding):

  • 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

Action suggestion check — before writing recommendations: Cross-check each suggested action against what calendar and Slack already show. Do NOT suggest something the EM is already doing. If the calendar shows weekly 1:1s and Slack shows personal check-ins, do not suggest "ask personal questions in 1:1s." Find what's genuinely missing.


Step 6: Output

Driver intro (before the grid)

Open with a brief, plain-English explanation of the three columns:

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.

The grid

Use a colored square to give each cell an instant visual read, then the whole-number score. No warnings, no footnotes in the table.

Color scale:

  • 🔴 0–2 (critical gap)
  • 🟠 3–4 (weak)
  • 🟡 5–6 (moderate)
  • 🟢 7–8 (good)
  • 💚 9–10 (strong)
## Your EM Grid — Last 30 Days

|          | Growth    | Impact    | Connection |
|----------|-----------|-----------|------------|
| **Self** | 🟠 4      | 💚 9      | 🔴 1       |
| **People**| 💚 9     | 🟠 3      | 🟡 5       |
| **Team** | 🔴 1      | 💚 10     | 🔴 2       |
| **Org**  | 🟠 3      | 🟠 3      | 🟢 7       |

Below the table, one line only: the data sources — e.g. "Based on 43 unique meeting patterns across 178 calendar events + Slack activity across 9 channels and 7 active DM threads."

Pattern diagnosis

2–3 direct sentences naming what kind of EM this pattern reveals. Read the overall shape:

  • 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.

Examples of the right register:

  • "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."

Be direct and specific to their actual numbers.

Top 3 blind spots

For the 3 lowest-scoring cells that aren't already explained away by role/context (e.g. a 2-person team won't have strong Team×Connection — flag that differently):

  • 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.
Optional: one flag worth naming

If there's something in the scores that's notable but isn't a blind spot — unusually high Self×Impact (possible delegation risk), strong Org×Connection with weak People×Connection (managing up more than managing people), etc. — call it out in one sentence as a thing to watch.

Overall score and final assessment

Calculate a single combined score: the average of all 12 cells, rounded to one decimal.

Present it as:

Overall EM Score: X.X / 10

Then write 2–3 sentences of final assessment — what this score means in context, not just the number. A 6.5 with strong fundamentals but neglected self-development is very different from a 6.5 that's evenly mediocre. Call out the specific shape:

  • 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?

Example register:

"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."

Data note (if Slack was missing)

If Slack was not connected:

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.

If both sources were used, no caveat needed.


Tone

Direct, specific, brief. No preamble beyond the driver intro. No filler encouragement. The grid, a short diagnosis, three blind spots, and one optional flag. Everything on one screen.

© manager-dot-dev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in skills/em-grid-scorer of manager-dot-dev/manager-skills.

  • SKILL.md
  • references/driver-explanations.md
  • references/suggested-actions.md
  • scripts/process_calendar.py

Open the folder on GitHubat commit c47ebc7

Compare with similar skills

Em Grid Scorer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Em Grid Scorer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Em Grid Scorer this skillmanager-dot-dev/manager-skills114—~5.8kAutomated safety check: PassMIT
Solomdzhitongblog/solomd1.2k—~2kAutomated safety check: PassMIT
Oce Field Opsdatadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction344—~532Automated safety check: PassMIT
Weekly Review PlanningNousResearch/hermes-agent252k—~994Automated safety check: PassMIT
Openloomimelandlabs/openloomi1k—~835Automated safety check: PassApache-2.0
Journaldavekilleen/Dex493—~1.8kAutomated safety check: PassCustom licence

Similar skills

  • Solomd

    zhitongblog/solomd

    Read, search, edit, and version-control any folder of Markdown notes via the SoloMD MCP server.

    1.2k GitHub stars~2k tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Oce Field Ops

    datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction

    Field operations in OpenConstructionERP: punch list, daily diary, HSE observations and task tracking on site.

    344 GitHub stars~532 tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed
  • Weekly Review Planning

    NousResearch/hermes-agent

    Weekly reset: commitments, stalled work, next-week plan. An agent skill from NousResearch/hermes-agent.

    252k GitHub stars~994 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Openloomi

    melandlabs/openloomi

    OpenLoomi entrypoint for skill-only agent runtimes without a plugin mechanism.

    1k GitHub stars~835 tokensUpdated 14 days ago
    Knowledge ManagementAuto-check passed
  • Journal

    davekilleen/Dex

    Toggle journaling or start a morning/evening/weekly journal entry.

    493 GitHub stars~1.8k tokensUpdated 5 days ago
    Knowledge ManagementAuto-check passed
  • Composio

    ComposioHQ/composio

    Route and complete Composio work across Composio For You and Composio Platform.

    30k GitHub starsUsed in 1 repo~1.7k tokens
    Productivity & AutomationAuto-check passed

More from manager-dot-dev/manager-skills

All 27 skills in this repo
  • Em Context

    manager-dot-dev/manager-skills

    Foundation skill for engineering managers. An agent skill from manager-dot-dev/manager-skills.

    114 GitHub stars~1.6k tokensUpdated 5 mo ago
    Auto-check passed
  • 1on1s

    manager-dot-dev/manager-skills

    Prepares agendas, diagnoses struggling 1:1 relationships, and gives frameworks for running effective 1:1 meetings with direct reports.

    114 GitHub stars~3k tokensUpdated 5 mo ago
    Auto-check passed
  • Business Literacy

    manager-dot-dev/manager-skills

    Explains business financial terms and frameworks for engineering managers — produces term definitions (ARR, COGS, CAC, LTV, gross margin, burn rate, EBITDA, AARRR), translation formulas for making…

    114 GitHub stars~2.4k tokensUpdated 5 mo ago
    Auto-check passed
  • Career Development

    manager-dot-dev/manager-skills

    Helps engineering managers support direct report growth — produces a stage-by-stage model of engineering impact (Circles of Influence), a framework for non-linear career planning (Tarzan Method)…

    114 GitHub stars~2.3k tokensUpdated 5 mo ago
    Auto-check passed
  • Delegation

    manager-dot-dev/manager-skills

    Guides managers out of the bottleneck role — provides the Team Rep pattern, Epic Ownership model, Task-Relevant Maturity framework, kingdom ownership, and three-layer assignment strategy.

    114 GitHub stars~3.3k tokensUpdated 5 mo ago
    Auto-check passed
  • Developer Productivity

    manager-dot-dev/manager-skills

    Helps engineering managers measure and improve team delivery — produces a history of why common metrics fail, the DORA four-key-metrics framework (deployment frequency, lead time, change failure…

    114 GitHub stars~2.5k tokensUpdated 5 mo ago
    Auto-check passed

Questions about Em Grid Scorer

What does Em Grid Scorer do?

Score an Engineering Manager's coverage across all 12 cells of the EM Grid based on their calendar and Slack. Em Grid Scorer is an agent skill from manager-dot-dev/manager-skills. Score an Engineering Manager's coverage across all 12 cells of the EM Grid based on their calendar and Slack.

When should I use Em Grid Scorer?

Em Grid Scorer fits situations like: someone wants to understand where theyre spending their management energy; find blind spots; get a monthly self-reflection on their EM focus; hear phrases like score my EM grid.

How do I install Em Grid Scorer in Claude Code?

Run `npx skills add manager-dot-dev/manager-skills --skill em-grid-scorer -a claude-code`. Or copy the skill folder (skills/em-grid-scorer in manager-dot-dev/manager-skills) into .claude/skills/em-grid-scorer in your project. Claude Code loads it when a task matches its description.

How do I install Em Grid Scorer in Codex?

Run `npx skills add manager-dot-dev/manager-skills --skill em-grid-scorer -a codex`. Or copy the skill folder (skills/em-grid-scorer in manager-dot-dev/manager-skills) into .agents/skills/em-grid-scorer in your project. Codex loads it when a task matches its description.

Can I use Em Grid Scorer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add manager-dot-dev/manager-skills --skill em-grid-scorer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/em-grid-scorer, .gemini/skills/em-grid-scorer, .github/skills/em-grid-scorer and .opencode/skills/em-grid-scorer in your project.

What does Em Grid Scorer need to run?

Going by SKILL.md and its folder, Em Grid Scorer needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Em Grid Scorer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Em Grid Scorer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Em Grid Scorer use?

Em Grid Scorer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Em Grid Scorer use?

About 5.8k tokens (SKILL.md is roughly 23k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3k tokens, read only when the agent opens those files.

What are the alternatives to Em Grid Scorer?

Skills that share tags, products or a category with Em Grid Scorer: Solomd (zhitongblog/solomd, 1.2k stars), Oce Field Ops (datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction, 344 stars), Weekly Review Planning (NousResearch/hermes-agent, 252k stars) and Openloomi (melandlabs/openloomi, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Em Grid Scorer?

manager-dot-dev (a GitHub organization) maintains it in manager-dot-dev/manager-skills, which has 114 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on May 9, 2026.

Source: manager-dot-dev/manager-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.