Annual Plan
Annual planning for ecommerce teams: test the plan against what the business can actually fund and staff, then recommend the resourcing, hiring and spend changes it needs.
An annual plan is usually a revenue number with departmental budgets underneath it, built by taking last year and adding a percentage. What it rarely contains is the test of whether the business can fund the working capital that revenue requires, or hire the people fast enough to deliver it. Those two constraints are what actually break plans, and they break them in month seven when both are expensive to fix. This skill tests the plan against cash and hiring capacity, then recommends the resourcing, hiring and spend changes it needs.
What It Does
- Projects the working capital the revenue plan requires, month by month.
- Tests hiring timelines against the ramp each role actually needs.
- Finds the month where cash, not demand, becomes the binding constraint.
- Prices the spend increase implied by the growth rate in the plan.
- Identifies the department whose plan assumes headcount nobody has budgeted.
- Recommends the resourcing, hiring and spend changes, with the month each lands.
Use Cases
- Find the month the plan runs out of cash before it runs out of demand.
- Check that a hiring plan allows for the time a new hire takes to contribute.
- Price the inventory a growth number implies before agreeing to it.
- Give each department a plan its budget can actually deliver.
Example Session
Stress test next year's plan and tell me what has to change.
The revenue plan is achievable. The cash plan behind it is not, in month seven.
- Constraint | Plan assumes | Reality | Gap | Change needed
- Working capital, month 7 | $1.9M available | $1.4M available | $500k | Shift Q3 buy later
- Growth hires, paid team | 3 by month 4 | 3 by month 7 | 3 months | Start hiring now
- Ramp to full contribution | Immediate | 4 months | 4 months | Reforecast H2
- Inventory for Q4 | $2.2M | Funded to $1.8M | $400k | Narrow the Q4 range
Month seven is where it breaks: the Q3 buy lands while receivables are at their thinnest. Moving part of that buy three weeks later closes most of the gap without touching the revenue plan. The hiring assumption is the other half, because a paid hire starting in month four contributes from month eight, and the plan credits them from month five.
Why This Beats Prompting It Yourself
A Revenue Plan vs The Cash And People Behind It: The Hidden Risk
A generic prompt reviews the plan's arithmetic, its growth rates and whether the departmental splits look reasonable. All of that can be internally consistent while the plan is unfundable, because the constraint is not in the numbers on the page. It is in the month when inventory, payroll and receivables collide.
When You Still Need The Ramp Between Hiring And Contributing
Plans credit new hires from their start date, which is the single most common way a plan overstates the second half of a year. This skill puts the four month ramp in explicitly, which moves three hires' worth of contribution out of H2 and is the difference between a plan that lands and one that misses by a quarter.
Known Limitations
Working capital projection depends on payment terms and receivables timing being current, and stale terms will make the cash picture look better than it is. Ramp assumptions come from your own hiring history where available and from role-level defaults where not, which the output distinguishes. It recommends the changes and does not modify your plan or budget documents.
Install It
- Download the ZIP.
It is free and there is no account to create. - Unzip it into your agent's skills folder.
Claude Code reads ~/.claude/skills/, which is hidden by default: the command in the folder block opens it. Other agents scan their own directory, so drop the same folder there instead. - Ask your agent to use it.
Restart the agent if it was already running, then it picks the skill up with no config.
skills folder
Copy
~/.claude/skills/annual-plan/
SKILL.md
references/ramp-model.md
plans/
# one file per stress test, with the binding month
# macOS: create the folder and open it in Finder
mkdir -p ~/.claude/skills && open ~/.claude/skills
# Windows: paste in the Explorer address bar
%USERPROFILE%\.claude\skills\Frequently asked questions
How is this different from reviewing the plan in a spreadsheet?
A spreadsheet checks that the plan adds up. This checks whether it can be funded and staffed, month by month, and names the month where it stops being possible. Those are different failures, and the second one is the one that actually happens.
Which agents does the skill run in?
Any agent that supports the open SKILL.md format: Claude Code, Cursor, Codex CLI, GitHub Copilot, Gemini CLI, Manus, Grok and others load it unmodified. The format is portable, the location is not. Each agent scans its own skills directory, so you drop the same folder into whichever one yours uses. There is no config file to edit and no API key to provision.
What does it need connected to work?
The revenue and cost plan, current cash position and payment terms, inventory commitments, and the hiring plan with start dates. Historical hiring timelines improve the ramp estimates and are optional.
Why does it focus on one month rather than the year?
Because a plan does not fail across a year, it fails in the month where the constraint binds. Naming month seven gives you six months to move a purchase order, which is cheap. Discovering it in month seven means raising money or canceling inventory, which is not.
Does it tell me to lower the revenue plan?
Rarely. Most gaps close by moving timing rather than lowering ambition, which is why the recommendations are about when the buy lands and when hiring starts. Where the plan genuinely is not fundable, it says so with the number rather than implying it.
What is included with the skill?
The skill itself, the ramp model reference, the stress test format, and the working capital assumptions. It is free and security scanned. We re-publish the ZIP when the model changes, so download it again if your projections start shifting.
A plan built on platform numbers is three plans.
Polar reconciles revenue, CAC and contribution margin on one definition across 45+ sources, so hiring and spend decisions rest on a single base case.
<script type="application/ld+json">{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"How is this different from reviewing the plan in a spreadsheet?","acceptedAnswer":{"@type":"Answer","text":"A spreadsheet checks that the plan adds up. This checks whether it can be funded and staffed, month by month, and names the month where it stops being possible. Those are different failures, and the second one is the one that actually happens."}},{"@type":"Question","name":"Which agents does the skill run in?","acceptedAnswer":{"@type":"Answer","text":"Any agent that supports the open SKILL.md format: Claude Code, Cursor, Codex CLI, GitHub Copilot, Gemini CLI, Manus, Grok and others load it unmodified. The format is portable, the location is not. Each agent scans its own skills directory, so you drop the same folder into whichever one yours uses. There is no config file to edit and no API key to provision."}},{"@type":"Question","name":"What does it need connected to work?","acceptedAnswer":{"@type":"Answer","text":"The revenue and cost plan, current cash position and payment terms, inventory commitments, and the hiring plan with start dates. Historical hiring timelines improve the ramp estimates and are optional."}},{"@type":"Question","name":"Why does it focus on one month rather than the year?","acceptedAnswer":{"@type":"Answer","text":"Because a plan does not fail across a year, it fails in the month where the constraint binds. Naming month seven gives you six months to move a purchase order, which is cheap. Discovering it in month seven means raising money or canceling inventory, which is not."}},{"@type":"Question","name":"Does it tell me to lower the revenue plan?","acceptedAnswer":{"@type":"Answer","text":"Rarely. Most gaps close by moving timing rather than lowering ambition, which is why the recommendations are about when the buy lands and when hiring starts. Where the plan genuinely is not fundable, it says so with the number rather than implying it."}},{"@type":"Question","name":"What is included with the skill?","acceptedAnswer":{"@type":"Answer","text":"The skill itself, the ramp model reference, the stress test format, and the working capital assumptions. It is free and security scanned. We re-publish the ZIP when the model changes, so download it again if your projections start shifting."}}]}</script>
