Pace
by
Gap-to-plan analysis for ecommerce teams: size the shortfall in dollars, then assign the corrective action across paid, pricing and lifecycle with the amount each one has to cover.
A business behind plan usually knows it is behind and does not know what closes the gap. The conversation happens in percentages, the instruction that comes out of it is to push harder, and three teams go away with the same vague brief. Paid adds budget, lifecycle adds a send, pricing discounts something, and none of them knows how much of the gap they were meant to cover. This skill sizes the shortfall in dollars, decomposes it into the drivers that produced it, and assigns a corrective action to paid, pricing and lifecycle with the amount each one has to deliver.
What It Does
- Sizes the gap to plan in dollars rather than in percentage terms.
- Decomposes it into traffic, conversion, basket and repeat rate.
- Tests which levers can realistically move at this point in the period.
- Assigns a dollar amount of the gap to paid, pricing and lifecycle.
- Prices the margin cost of each corrective action before recommending it.
- Flags the part of the gap no lever can close, so the forecast is reset instead.
Use Cases
- Turn a percentage shortfall into three briefs with numbers on them.
- Stop three teams from solving the same portion of the gap twice.
- See the part of the gap that cannot be closed and reset the forecast early.
- Price the discount a pricing action would need before approving it.
Example Session
We are behind plan this quarter. What closes the gap, and who owns what?
The gap is $340k. About $95k of it cannot be closed this quarter.
- Driver | Gap | Lever | Owner | Margin cost
- Traffic below plan | $148k | Paid, plus $52k spend | Growth | $52k
- Conversion below plan | $61k | Checkout fix plus offer | Storefront | $14k
- Repeat rate below plan | $36k | Lifecycle, winback | Retention | $6k
- Basket below plan | $95k | None available in period | Finance | Reset forecast
Basket is the honest part: it fell because the mix shifted toward entry products and nothing you can do this quarter reverses that, so reset rather than chase it. The other $245k is coverable and costs $72k of margin to cover, which is a decision worth making explicitly rather than discovering at the close.
Why This Beats Prompting It Yourself
A Percentage Behind vs A Dollar Per Owner: The Hidden Risk
A generic prompt confirms you are behind and suggests doing more of everything. Nobody leaves that conversation knowing how much of the gap they own, so the corrective actions overlap on the easy part and leave the rest uncovered. Worse, the portion of the gap that is genuinely unrecoverable keeps getting chased until the close.
When You Still Need The Part That Cannot Be Closed
The most useful number in a gap analysis is the one nobody wants. This skill states $95k that no lever reaches in the period, next to $245k that three owners can cover for $72k of margin. Saying which part is unrecoverable early is what lets a finance lead reset the forecast instead of explaining a miss after it happens.
Known Limitations
Lever sizing uses your own historical response to each action, so a business that has never run a winback or changed a threshold will get a wider estimate on that lever and the output says so. It assumes the plan itself is sound: a gap caused by an unrealistic plan looks identical to one caused by underperformance, and the skill flags that possibility rather than resolving it. It assigns the actions and does not execute any of them.
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/pace/
SKILL.md
references/lever-response.md
gaps/
# one file per period, with the assignment
# 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 a variance report?
A variance report says how far behind you are and against what. This decomposes the gap into drivers, tests which levers can move at this point in the period, and assigns a dollar amount to each owner with the margin it will cost. The output is three briefs rather than one number.
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 plan, actual revenue and its drivers, spend, and history of previous corrective actions. Without the action history it still decomposes the gap and widens its estimate of what each lever can deliver, which the output labels.
Why does it say part of the gap cannot be closed?
Because some drivers do not respond inside a quarter. A mix shift toward entry products or a lost wholesale account will not reverse in eight weeks, and chasing it burns margin on the levers that could have covered the rest. Naming it early is the point.
Does it account for the cost of closing the gap?
Yes, per lever. Covering $245k for $72k of margin is a decision someone should make deliberately, and the alternative of missing the number by that much is sometimes the better one. The skill prices both rather than assuming the gap must be closed.
What is included with the skill?
The skill itself, the lever response reference, the gap template, and the assignment format per owner. It is free and security scanned. We re-publish the ZIP when the lever model changes, so download it again if your sizing shifts.
The gap to plan is only actionable once it has a driver.
Polar computes revenue and margin to date on one definition across 45+ sources, so the corrective action names the channel and the amount.
<script type="application/ld+json">{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"How is this different from a variance report?","acceptedAnswer":{"@type":"Answer","text":"A variance report says how far behind you are and against what. This decomposes the gap into drivers, tests which levers can move at this point in the period, and assigns a dollar amount to each owner with the margin it will cost. The output is three briefs rather than one number."}},{"@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 plan, actual revenue and its drivers, spend, and history of previous corrective actions. Without the action history it still decomposes the gap and widens its estimate of what each lever can deliver, which the output labels."}},{"@type":"Question","name":"Why does it say part of the gap cannot be closed?","acceptedAnswer":{"@type":"Answer","text":"Because some drivers do not respond inside a quarter. A mix shift toward entry products or a lost wholesale account will not reverse in eight weeks, and chasing it burns margin on the levers that could have covered the rest. Naming it early is the point."}},{"@type":"Question","name":"Does it account for the cost of closing the gap?","acceptedAnswer":{"@type":"Answer","text":"Yes, per lever. Covering $245k for $72k of margin is a decision someone should make deliberately, and the alternative of missing the number by that much is sometimes the better one. The skill prices both rather than assuming the gap must be closed."}},{"@type":"Question","name":"What is included with the skill?","acceptedAnswer":{"@type":"Answer","text":"The skill itself, the lever response reference, the gap template, and the assignment format per owner. It is free and security scanned. We re-publish the ZIP when the lever model changes, so download it again if your sizing shifts."}}]}</script>