Build and run a 13-week direct-method cash flow forecast: opening cash from the bank, receipts by customer and aging using the user's own collection history, disbursements (payroll calendar, rent, vendor payment runs, taxes, debt service, capex), minimum cash buffer and covenant checks, weekly roll-forward with variance to actual, and scenarios and levers such as collections pushes, payment timing, and credit line draws. Includes a Python script that rolls weekly balances from dated flows and flags weeks below a minimum. Use when asked for a 13-week cash forecast, weekly cash flow, runway in weeks, liquidity planning, or a covenant check. Do not use for an annual operating budget (build-operating-budget), month-end close (run-month-end-close), or legal or insolvency advice.
Build an annual operating plan and budget from drivers - revenue drivers, a headcount plan with fully loaded cost and start-month timing, non-headcount opex by department, COGS, monthly phasing, scenarios, and cash runway - and reconcile top-down targets with bottom-up department requests, with approval and reforecast cadence. Use when asked to build next year's budget or annual operating plan, create a headcount plan and cost model, phase a budget by month, reconcile department requests with company targets, model base, upside and downside scenarios, or check runway under the plan. Do not use for explaining actual-versus-budget variances (budget-variance-explainer), marketing channel allocation (plan-marketing-budget), a 13-week cash forecast (build-cash-forecast), or support team sizing (plan-support-staffing).
Map and improve a business process end to end. Scopes it with SIPOC (Suppliers, Inputs, Process, Outputs, Customers), draws the current-state swimlane map, measures cycle time against touch time, handoffs, rework loops, and wait states, classifies waste with the lean waste categories, finds root causes with 5 whys and a fishbone, designs the future state, assigns RACI for the redesigned steps, adds controls, and produces an implementation plan with metrics. Use when a process is slow, error-prone, full of handoffs or approvals, or nobody can say who owns a step; when asked for a process map, value stream map, swimlane, SIPOC, bottleneck analysis, or process improvement. Do not use for documenting a settled process as a procedure (sop-writer), building a metric hierarchy (kpi-tree), or post-incident analysis of a single failure (incident-postmortem).
Design a career ladder (leveling framework) for a job family. Sets individual contributor and manager tracks, the number of levels, and the dimensions that define them (scope, impact, complexity, autonomy, leadership and influence, craft), then writes observable level expectations that differ in kind between adjacent levels. Calibrates the draft against real anonymized examples, maps existing employees to levels, defines the promotion process and evidence standard, and links levels to salary bands. Use when asked to create or fix a career ladder, career framework, leveling guide, IC versus manager tracks, or promotion criteria, or when titles and levels are inconsistent across teams. Do not use for writing a single job description (job-description-writer), drafting an individual performance review (performance-review-draft), or pricing levels in pay ranges (design-comp-bands).
Build and interpret cohort retention analysis from a CSV of customers, subscriptions, or transactions, with a bundled Python script: a logo retention triangle and, when revenue is present, gross revenue retention (GRR, capped at 100%, excludes expansion) and net revenue retention (NRR, includes expansion) by cohort, plus trailing-twelve-month NRR. Handles reactivations, mid-month starts, plan changes, and small cohorts, then reads curves for flattening, cohort-over-cohort improvement, and segment differences. Use when asked for a cohort analysis, retention curve or triangle, NRR or GRR, or whether newer customers retain better. Do not use for churn risk on named accounts (churn-risk-review), a customer health score (design-customer-health-score), or unit economics (model-unit-economics).
Diagnose where and why a conversion funnel leaks, using the user's own web analytics exports, CRM stage data, or product signup and activation events. Defines stages and exact conversion formulas, chooses cohort or period measurement, cuts by segment, checks sample size before calling a difference real, ranks stages by recoverable loss rather than worst rate, gathers qualitative evidence, and ends with a scored hypothesis backlog. Use when someone asks why conversion dropped, where the funnel leaks, why signups do not activate, why leads stall between stages, for a drop-off analysis, or which funnel step to fix first. Do not use for writing landing page copy (use the landing-page-copy prompt), for designing or sizing a specific A/B test (use ab-test-setup), for building a metric hierarchy (use kpi-tree), or for retention curves after purchase (use analyze-cohort-retention).
Design a customer health score that predicts a defined outcome and drives customer success action. Defines the outcome (renewal, churn, expansion) and prediction window, selects candidate signals (usage depth and breadth, key feature adoption, support pattern, stakeholder engagement, sentiment, commercial), backtests against past renewals and churn, chooses expert weights or logistic regression, sets bands, playbooks and review cadence, and guards against gaming and lagging signals. Use when asked to build, redesign or validate a health score, pick or weight health signals, check whether a health score predicts churn, or set red, yellow and green thresholds. Do not use for reviewing a list of at-risk accounts this quarter (use churn-risk-review), for preparing a QBR (use quarterly-business-review-brief), or for cohort retention curves (use analyze-cohort-retention).
Build and allocate a marketing budget from the user's own targets and conversion data. Compares top-down methods (percent of revenue as a stated heuristic only; a pipeline back-solve from revenue target to deals, opportunities, and leads by channel) with a bottom-up build by program; allocates on marginal rather than average CAC; separates fixed from variable costs; holds a test reserve; phases by quarter; models base, cut 20%, and add 20% scenarios; and sets a tracking cadence. Use when someone asks how much to spend on marketing, how to split budget across channels, how many leads a revenue target needs, or what to cut if the budget drops. Do not use for a one-page campaign plan (use campaign-plan-one-pager), the company operating budget (use build-operating-budget), or proving channel incrementality (use measure-marketing-incrementality).
Measure what marketing actually causes rather than what it gets credit for. Explains attribution models (last-touch, first-touch, position-based, data-driven) and their biases; designs and sizes incrementality tests (randomized holdouts, ghost ads, conversion lift studies, geo-lift and matched markets, on/off switchbacks); outlines a lightweight marketing mix model; reconciles self-reported attribution; and writes a per-channel measurement plan with pre-registered decision rules. Use when someone asks whether a channel really works, why platform ROAS disagrees with revenue, how to run a holdout or geo test, or which attribution model to trust. Do not use for page or product A/B tests (use ab-test-setup), funnel drop-off diagnosis (use diagnose-conversion-funnel), or setting budget levels (use plan-marketing-budget).
Run, document, and speed up a month-end close for a small-to-mid-size company: a business-day close calendar (BD-3 to BD+10) with owners, pre-close and cutoff procedures, the core checklist (cash and bank reconciliations, AR and AP subledger ties, revenue recognition review, accruals, prepaids, fixed assets, payroll, intercompany, deferred revenue roll-forward, inventory), journal entry review standards, balance-sheet reconciliations, flux analysis against user-set thresholds, sign-off and lock, and a faster-close plan. Use when asked to build a close checklist or calendar, reconcile accounts, review journal entries, run a flux review, or shorten the close. Do not use to explain one budget variance (budget-variance-explainer), for a 13-week cash forecast (build-cash-forecast), or for accounting-standard opinions.
Plan onboarding for a new employee in a specific role, and build a reusable onboarding program for a team. Covers pre-start logistics (equipment, system access, paperwork), day one, week one, role-specific 30/60/90-day outcomes, a buddy and manager check-in cadence, a learning plan, a first meaningful contribution, stakeholder introductions, success measures such as time to productivity and new-hire feedback, and the hiring manager's checklist. Use when someone is about to start or has just started, or when asked for an onboarding plan, 30-60-90 day plan, first-week schedule, new hire checklist, buddy program, or a standard onboarding template for a team. Do not use for writing the job description (job-description-writer), designing interviews (structured-interview-kit), or designing product onboarding for app users or customers.
Design a customer referral or advocacy program that pays for itself. Tests fit first (is word of mouth already happening, per NPS and referral-source evidence), identifies who refers and why beyond cash, chooses the reward structure (single or double-sided; cash, credit, or product; tiered), models economics against alternative CAC with payback and fraud controls, flags tax and legal points for counsel, sets the moments to ask and the tracking, and launches as a test with a holdout. Use when someone asks to start or fix a referral, refer-a-friend, or customer advocacy program, what referral reward to offer, or whether referrals are worth it. Do not use for partner or reseller commissions, sales compensation (use design-sales-compensation), measuring paid channels (use measure-marketing-incrementality), or offer and pricing design (use develop-offers).
Audit and rationalize a company's software and SaaS spend. Builds the inventory from accounts payable, corporate card and expense exports plus the SSO or identity provider app list, normalizes vendor names, categorizes tools, finds overlapping and duplicate tools, measures license utilization, builds a renewal calendar with notice periods and auto-renew terms, and ranks savings levers with labelled estimates and risk checks before cancelling, ending in an owner-per-app governance model. Use when asked to audit software spend, cut SaaS costs, find unused licenses or duplicate tools, build a renewal calendar, or set up software ownership. Do not use for choosing one vendor among options (vendor-comparison), negotiating a specific renewal (negotiate-tactically), or the annual budget (build-operating-budget).
Design salary bands (pay ranges) from a job architecture and market data. Confirms job families and levels first, ages survey data to a common effective date with a user-supplied annual factor, rates match quality, sets a pay philosophy percentile, then builds midpoints, range spread ((max - min) / min), midpoint progression, and overlap by level, with geographic differentials. Places current employees with compa-ratio and range penetration, handles red- and green-circle cases, costs bringing people to minimum, and adds pay-transparency and pay-equity review steps. Use when asked to build salary bands, pay ranges, a compensation structure, compa-ratios, or to find who is under or over range. Do not use for sales commission or variable pay plans (design-sales-compensation), defining levels and expectations (design-career-ladder), or writing an individual offer letter.
Design sales compensation plans that pay for the behaviour the business needs at a cost it can afford. Defines roles, OTE and pay mix by role (SDR, hunter, farmer), up to three measures linked to quota, base commission rate math, accelerators, decelerators, thresholds, caps, SPIFFs, clawbacks, crediting and split rules, a cost-of-sales check, payout modelling at 50/80/100/120/150 percent attainment, and a plan document outline. Use when asked to build or fix a comp plan, set commission rates, choose pay mix or OTE for sales roles, add accelerators, model what reps earn at different attainment, or check whether a plan is affordable. Do not use for carving territories or setting quota totals (use plan-sales-territories), for salary bands of non-sales roles (use design-comp-bands), or for drafting an offer letter.
Run a weekly or quarterly sales forecast review that ends in a defensible number. Applies forecast categories (commit, best case, pipeline, omitted) with explicit inclusion criteria, inspects deals against evidence using MEDDPICC correctly, triangulates stage-weighted, historical-conversion and rep-judgement forecasts, checks pipeline coverage by stage against the team's own win rates, analyses slippage, pushes and aging, and writes the forecast narrative with risks and upside. Use when asked to prepare or run a forecast call, pressure-test a commit, call the quarter, review pipeline coverage, inspect deals for a forecast, or explain why the forecast moved. Do not use for building a mutual action plan with a buyer (use mutual-action-plan), for reviewing customer churn risk (use churn-risk-review), or for setting annual quotas (use plan-sales-territories).
Plan sales territories and quotas from account and whitespace data. Segments accounts (named, geographic, vertical, employee band), scores account potential, models ramped rep capacity with ramp curves and attrition, runs balance tests on potential, workload, account count and travel, reconciles a top-down bookings plan with bottom-up capacity, sanity-checks quota against OTE, and writes the transition plan with holdover rules for moved accounts. Use when asked to carve or rebalance territories, set or allocate quotas, build a sales capacity model, check whether reps have fair books, plan headcount against a bookings target, or reassign accounts for a new fiscal year. Do not use for designing commission rates, accelerators or pay mix (use design-sales-compensation), for weekly forecast calls (use review-sales-forecast), or for tiering a single rep's accounts or writing an account plan.
Answer a customer's vendor security questionnaire (SIG, CAIQ, or a custom spreadsheet) from the company's own evidence. Builds and maintains an answer library keyed to control areas, maps each question to policies, SOC 2 report sections, penetration test summaries, and architecture documents, answers Yes, No, Partial, or N/A with a short factual explanation, handles compensating controls honestly, routes answers that need security or legal sign-off, and hands back a gap list for the security owner. Use when a prospect or customer sends a security questionnaire, vendor risk assessment, third-party risk review, or due-diligence form, or needs consistent SIG or CAIQ answers. Do not use for drafting a full RFP response (rfp-response-drafter), writing security policies from scratch, running a security audit or threat model, or negotiating contract terms.
Calculate how many agents a customer support or contact center team needs from its workload. Forecasts contact volume by week, day and interval, sizes phone and chat with Erlang C against a service-level target, sizes email and ticket queues with workload hours and response-time targets, then applies occupancy caps and shrinkage to reach FTE, hires and sensitivity. Use when asked how many support agents or FTE to hire, for a support staffing model or headcount plan, to hit an 80/20 service level, to plan peak-season coverage, or to see what happens if handle time or ticket volume changes. Do not use for customer replies (support-reply-drafter), support SOPs (sop-writer), a company-wide budget (build-operating-budget), or process mapping (map-business-process).
Model the unit economics of a subscription or transactional business - contribution margin per customer or order, CAC (fully loaded vs. paid-only, blended vs. by channel), CAC payback on gross margin, LTV with its caveats, LTV:CAC, sensitivity tables, and segment and channel breakdowns. Use when asked to calculate CAC, LTV, payback period, contribution margin, or LTV to CAC ratio, to check whether customer acquisition is profitable, to compare unit economics by channel or segment, or to prepare unit economics for a board or investor review. Do not use for sizing a market (market-sizing), setting prices and packaging (develop-offers), building the annual budget (build-operating-budget), or measuring retention curves in depth (analyze-cohort-retention).