Skills

Research target accounts and the right people to reach.

Tools:

In 1 role:

Pre-read board materials ahead of every board meeting, and analyse or draft board documents. Learnings from doing this many times: board decks and pre-reads live in Google Drive — find the latest by company name plus "board deck" / "board pack", and verify the document actually belongs to that company before you summarise it (don't grab the most-recently-edited file globally — that's how you end up summarising the wrong company's deck). Turn the pack into decision-ready points: what changed since last meeting, what's materially at risk, and what actually needs a board decision — not a page-by-page recap. Always pair the narrative with the underlying numbers from the data lake so the board reads a claim and its evidence together.

Tools:

In 4 roles:

Read, analyse and produce monthly management reports. Learned the hard way, and the most important lesson first: a management report is a GOOGLE DRIVE DOCUMENT / PRESENTATION — the one the Managing Director writes their commentary in — NOT just data-lake numbers. So the real skill is (1) FIND the right report in Google Drive: search by company name + "management report", and verify the document actually belongs to that company and month before reading it — don't grab the most-recently-edited file globally (a classic wrong-doc mistake). (2) READ THE ACTUAL DOCUMENT (open the doc/slides, digest the text and any charts) to capture the MD's narrative — what happened, why, what's at risk, and what actions are planned — because that written analysis is the whole point and appears nowhere in the raw numbers. (3) Use the data lake only to CROSS-CHECK the figures, minding its traps: ARR-type metrics live under source "product" (not "financial"), a company-KPI-period is the SUM of component rows (never dedupe — that reads ARR as ~554K instead of ~56M), and the latest month is PROVISIONAL so trust actuals only through the last closed month. Then report BOTH the MD's narrative and the verified numbers — the story and its evidence together.

Tools:

In 7 roles:

Track budget vs actual and variances.

Tools:

In 2 roles:

Build tools/apps and publish them live via the platform.

Tools:

In 2 roles:

Read the user's calendar with the `calendar` CLI (read-only, primary calendar) to prep for what is next and answer availability questions. How to run it (the `calendar` CLI): • calendar today — the rest of today's events • calendar agenda --days 7 — upcoming events in a window • calendar find "board meeting" --days 30 — search upcoming events by text • calendar freebusy --days 5 — busy blocks, for "when am I free?" questions Use it to prep meetings and answer scheduling questions, and pair it with `drive` + `email` to pull the relevant docs and threads for each upcoming meeting.

Tools:

In 3 roles:

Track campaign performance and spend.

Tools:

In 1 role:

Watch cash, margins and KPI drift month to month.

Tools:

In 2 roles:

Monitor KPIs across the company and flag drift.

Tools:

In 2 roles:

Analyse the customer journey outside-in.

Tools:

In 1 role:

Query the financial data warehouse (the "data lake") for ARR, margins, KPIs and trends. Hard-won learnings baked in: the true grain is (unit, source, KPI, year, period, Gr1, R12, reporting-year, date-key) — always SUM the components, never pick one row. NUMERIC values come back as big.js objects, not plain numbers, so a naive value-handler silently yields null — coerce with String(). Never diagnose a shocking swing as "duplicate double-counting": double-counting inflates, while a collapse toward zero is almost always an un-summed component or the provisional latest month. Verify against pfdw before trusting anything surprising. How to run it (the `lake` CLI, plus the analysis tools built on top): • lake explore --company Acubiz — list the KPIs, sources and periods available for a company • lake series ARR --company Acubiz --source product --chart — the ARR time-series (correctly SUMmed), ready to plot • lake growth ARR --company Acubiz — period-over-period and YoY growth • lake forecast ARR --company Acubiz — projection that prefers the forecast value for the provisional month • lake validate --company Acubiz — flag genuine double-loads and mark the provisional latest month • benchmark ARR — compare one KPI across the whole portfolio • portfolio — the fleet-wide KPI snapshot; waterfall / scenario / explain for bridges, what-ifs and drill-downs • lake manual — the deep guide (grain, provisional months, big.js NUMERIC) baked into the tool itself

Tools:

In 7 roles:

Track open deals, next steps and risks.

Tools:

In 1 role:

Watch launch readiness and defects.

Tools:

In 2 roles:

Synthesise user feedback on design.

Tools:

In 1 role:

Watch engagement signals and org changes.

Tools:

In 1 role:

A concise daily/weekly briefing of what needs attention.

Tools:

In 2 roles:

Summarise user feedback into actionable themes.

Tools:

In 2 roles:

Reproduce the numbers — ARR, margins, KPIs — from the warehouse.

Tools:

In 2 roles:

Forecast the quarter/year and flag risk early.

Tools:

In 4 roles:

Track hiring pipelines and coordinate scheduling.

Tools:

In 1 role:

Read mail and documents and summarise.

Tools:

In 1 role:

Track lead statistics and how much the pipeline is worth.

Tools:

In 2 roles:

Qualify leads against the ideal-customer profile.

Tools:

In 1 role:

Prep meetings and surface what matters.

Tools:

In 1 role:

Track outreach, response rates and meetings booked.

Tools:

In 1 role:

Watch positioning and competitor moves.

Tools:

In 2 roles:

Keep the user’s priorities and follow-ups on track.

Tools:

In 1 role:

Track user needs, adoption and roadmap gaps.

Tools:

In 1 role:

Draft proposals and quotes from templates and deal context.

Tools:

In 1 role:

Watch failing tests and tech debt.

Tools:

In 2 roles:

Read and digest Drive documents — reports, decks, memos, contracts — with the `drive` CLI (read-only, as the connected account). Work agilely: pull snippets, not whole files, and confirm a hit is the right company/topic before quoting it. How to run it (the `drive` CLI): • drive search "Q3 board deck" — find files by name or content • drive find --name "management report" --type docs --since 30d — precise power-search combining filters (--name / --content / --type slides|docs|sheets|pdf / --in <folder> / --owner / --since 7d) • drive grep "ARR churn" --type docs --context 2 — return matching SNIPPETS across files (cheap; not whole files) • drive digest <fileIdOrUrl> — a triage card (structure + preview) before you commit to a full read • drive read <fileIdOrUrl> — print full content (Docs/Sheets/Slides exported as text) • drive map [folder] / drive index [folder] — folder tree / flat cached catalog for navigation • drive sheet tabs <id> ; drive sheet read <id> --tab <name> — Google Sheets as data • slides analyze <deck> — read a deck slide-by-slide (text + md5-cached vision of every image); slides text <deck> for fast text-only Typical flow: search/find the file → digest to confirm it is the right one → grep the specific point, or read / slides for the full content. Summarise into what the reader needs: the decision, the change, the number — with a link back to the source.

Tools:

In 5 roles:

Work the inbox with the `email` CLI (Gmail). IMPORTANT: this tool can read, label and DRAFT — it CANNOT send (sending is disabled by design). So you triage and prepare a ready-to-send draft, then hand it to the human, who sends. How to run it (the `email` CLI): • email search "from:acme subject:invoice newer_than:7d" — Gmail query syntax • email list --label INBOX --limit 15 — recent messages (label = INBOX / SENT / DRAFT / …) • email read <messageId> ; email thread <threadId> — read one message or a whole thread • email draft --to a@b.com --subject "…" [--cc …] [--reply-to <messageId>] — create a draft (NEVER sends; --reply-to drafts a reply in that thread) • email mark-read / mark-unread / archive <ids…> — triage • email label <ids…> --add X --remove Y ; email labels — manage labels Flow: search/list to find what needs attention → read/thread to understand it → draft the reply for the human to review and send. Never claim you sent an email — you draft, the human sends.

Tools:

In 3 roles:

Surface material risks and strategic concerns proactively.

Tools:

In 4 roles:

Model scenarios and forecast risk.

Tools:

In 1 role:

Watch team schedules and flag changes needed.

Tools:

In 2 roles:

Track strategy and governance matters.

Tools:

In 2 roles:

Check each team member’s performance daily and flag who needs support.

Tools:

In 1 role:

Research options and prototype.

Tools:

In 2 roles:

Review flows for usability and consistency.

Tools:

In 1 role: