annual-operating-plan
Skill15 starsChanged 3 months agoMITView on GitHub
Reconciles leadership's top-down target against the driver-based bottom-up build line by line via a bundled calculator, flagging every gap over 10% instead of quietly averaging the two into a number nobody actually believes. Use whenever the user is building the annual operating plan, needs to reconcile a leadership target with a bottoms-up model, or has a plan where the top-down ask and the bottom-up build were never actually compared line by line.
In this repository23 other files it gives its agents.
- ar-ap-aging-analyzerSkill
- balance-sheet-health-checkSkill
- board-reporting-pack-builderSkill
- capex-roi-evaluatorSkill
- cash-runway-burn-analyzerSkill
- covenant-headroom-monitorSkill
- credit-risk-scoringSkill
- debt-schedule-modelSkill
- driver-based-budget-builderSkill
- fx-exposure-advisorSkill
- kpi-tree-dashboardSkill
- liquidity-stress-testSkill
- margin-decompositionSkill
- month-end-close-acceleratorSkill
- peer-benchmarkingSkill
- recurring-report-builderSkill
- rolling-forecast-builderSkill
- scenario-planning-engineSkill
- thirteen-week-cash-forecastSkill
- three-statement-modelSkill
- variance-bridge-analyzerSkill
- working-capital-optimizerSkill
- zero-based-budget-plannerSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Build the bottom-up plan first, independently: Use driver-based-budget-builder's discipline: real volume, price, and cost drivers by …
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Annual Operating Plan
When to use
Use whenever the annual plan needs to reconcile what leadership wants (a top-down growth or margin target, often set for investor or board reasons) against what a driver-based bottom-up model actually produces. Especially use when the current "plan" is really just the top-down number with a supporting narrative built backward to justify it, rather than a genuine reconciliation.
What it does
Compares top-down target and bottom-up build line by line via a bundled calculator, computes the gap and gap percentage for every line item, and flags any line with more than a 10% gap — forcing an explicit resolution (revise the target, find real drivers to close the gap, or accept it with a named owner) instead of letting the two numbers get quietly blended into a plan nobody actually built.
Method
- Build the bottom-up plan first, independently. Use driver-based-budget-builder's discipline: real volume, price, and cost drivers by department, not a top-down number divided by twelve.
- State the top-down target explicitly — the number leadership or the board has in mind, and why (a growth rate expected by investors, a margin target tied to a prior commitment).
- Run the bundled calculator (
scripts/aop_reconciliation.py) to compare every line item, revenue, margin, opex, and any other planned metric, top-down versus bottom-up, with the gap and gap percentage shown. - Treat every flagged gap (over 10%) as requiring one of three resolutions, not a rounding error to smooth over: revise the top-down target to something the bottom-up model can actually support, find specific additional drivers (a new channel, a price change, a cost action) that would close the gap for real, or explicitly accept the gap with a named owner and a plan to close it during the year.
- Never let the published plan silently split the difference between top-down and bottom-up without documenting which resolution was chosen and why — a plan that's an unexplained average of two numbers is not a real plan, it's a compromise nobody can defend later.
- Revisit the reconciliation at each planning checkpoint (quarterly re-forecast), not just once at the start of the year — the gap-closing actions from step 4 need to actually show up in the numbers, or the same gap reappears next cycle.
Inputs
- Top-down targets by line item with the rationale behind each
- Bottom-up, driver-based build for the same line items
- Config saved as JSON matching the format documented at the top of
scripts/aop_reconciliation.py
Output format
Line-by-line table of top-down target, bottom-up build, gap, and gap percentage; explicit flag for every line item over a 10% gap; required resolution stated for each flagged item (revised target, closing drivers, or accepted gap with owner).
Example
Leadership's top-down revenue target is $24M; the bottom-up build, based on realistic sales capacity and conversion rates, comes to $21.5M, a 10.4% gap the calculator flags immediately. Rather than publishing $24M with a hopeful narrative, the resolution names two specific closing drivers (a new outbound motion and a price increase on renewals) sized to close roughly half the gap, with the remaining gap explicitly accepted and owned by the sales VP with a Q2 checkpoint.
Common pitfalls
- Publishing the top-down number as the plan without ever showing the bottom-up build that was supposed to support it.
- Averaging top-down and bottom-up into a compromise number with no stated rationale for the blend.
- Reconciling once at the start of the year and never revisiting whether the gap-closing actions actually materialized.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

