Pricing Analyst
by
Weekly pricing review for ecommerce teams: find where price has room to move, size the margin at stake, and recommend the tests and basket tactics worth running.
Prices get set at launch and then revisited only when something forces it: a cost increase, a competitor move, a quarter that missed. That means most catalogs carry prices that were right two years ago, some too low on products customers would pay more for and some too high on products quietly not selling. The reason nobody fixes it is that a price change feels risky and the upside is invisible until afterwards. This skill finds where price has room to move, sizes the margin at stake, and recommends the tests and basket tactics worth running this week.
What It Does
- Estimates price sensitivity per product from your own demand history.
- Finds the products where a rise is unlikely to cost volume.
- Identifies prices that have fallen behind two years of cost increases.
- Sizes the margin at stake for each candidate before anything changes.
- Designs the test, including what to hold constant and how long to run it.
- Recommends the basket tactics that raise order value without a price change.
Use Cases
- Find the product carrying two years of cost increases at the launch price.
- Raise price on the SKU whose demand has never responded to discounting.
- Lift order value with a threshold change rather than with a price rise.
- Size the margin at stake before proposing a price change to anyone.
Example Session
Where do we have room on price this week, and what should we test?
Two products are underpriced and one threshold is worth more than either.
- Item | Current | Suggested | Sensitivity | Margin at stake | Test
- Cap, charcoal | $28 | $32 | Low | $14,600 per quarter | Raise, 3 weeks
- Core tee, black | $34 | $34 | High | $0 | No change
- Jacket, navy | $180 | $198 | Low | $31,200 per quarter | Raise, 4 weeks
- Free shipping threshold | $75 | $85 | n/a | $22,400 per quarter | Test, 2 weeks
The cap and the jacket both show demand that has not responded to past discounts, which is the signal that price is not what is deciding the purchase. The black tee is the opposite and should not move. The threshold change is the largest single item and touches no price at all: it moves the median basket from $71 to $84 on the historical distribution.
Why This Beats Prompting It Yourself
A Competitor's Price vs Your Own Demand Curve: The Hidden Risk
A generic prompt benchmarks against competitor pricing, which is the input most likely to be available and least likely to fit. Their cost base, margin target and customer are not yours. Matching a competitor on a product where your demand is insensitive gives away margin for a comparison no customer is making.
When You Still Need The Tactic That Changes No Price
The largest item in that table is a shipping threshold, not a price. Moving it from $75 to $85 is worth $22,400 a quarter, carries less risk than either price rise, and no pricing review that starts from competitor benchmarks will ever surface it. Order value and price are different levers, and the second one is not always the better place to start.
Known Limitations
Sensitivity estimates come from your own history of price and promotion changes, so a product that has never varied in price returns a wide band that the output labels rather than hides. It does not model competitor reaction, which matters most on directly comparable commodity products. It recommends the tests and the tactics, and does not change prices in your storefront.
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/pricing-analyst/
SKILL.md
references/sensitivity-model.md
weekly/
# one file per week, with the test design
# 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 competitor price comparison?
A comparison tells you where you sit against someone else's cost base and margin target. This estimates how your own demand responds to price, which is the only thing that decides whether a rise costs volume. The two recommendations disagree often, and the comparison is the one with no stake in your margin.
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?
Order history with prices paid, promotion history, product cost, and current prices. The more price variation your history contains, the narrower the sensitivity estimates, and the output states the confidence per product.
Is it safe to raise a price on this evidence?
It is safe to test one. Each recommendation comes with a test design, a duration and the margin at stake, so the change runs on a subset and is measured before it becomes permanent. The skill never recommends a catalog-wide change.
Why does it recommend threshold changes alongside price?
Because order value responds to thresholds, bundles and shipping rules without touching any price, and those moves are frequently worth more with less risk. A pricing review that only considers prices leaves the easier money on the table.
What is included with the skill?
The skill itself, the sensitivity model reference, the weekly test format, and the basket tactic library. It is free and security scanned. We re-publish the ZIP when the model changes, so download it again if your estimates start shifting.
Elasticity means nothing without a margin floor.
Polar defines contribution margin once across 45+ sources, so the pricing tests and discount changes you queue stay above it.
<script type="application/ld+json">{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"How is this different from a competitor price comparison?","acceptedAnswer":{"@type":"Answer","text":"A comparison tells you where you sit against someone else's cost base and margin target. This estimates how your own demand responds to price, which is the only thing that decides whether a rise costs volume. The two recommendations disagree often, and the comparison is the one with no stake in your margin."}},{"@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":"Order history with prices paid, promotion history, product cost, and current prices. The more price variation your history contains, the narrower the sensitivity estimates, and the output states the confidence per product."}},{"@type":"Question","name":"Is it safe to raise a price on this evidence?","acceptedAnswer":{"@type":"Answer","text":"It is safe to test one. Each recommendation comes with a test design, a duration and the margin at stake, so the change runs on a subset and is measured before it becomes permanent. The skill never recommends a catalog-wide change."}},{"@type":"Question","name":"Why does it recommend threshold changes alongside price?","acceptedAnswer":{"@type":"Answer","text":"Because order value responds to thresholds, bundles and shipping rules without touching any price, and those moves are frequently worth more with less risk. A pricing review that only considers prices leaves the easier money on the table."}},{"@type":"Question","name":"What is included with the skill?","acceptedAnswer":{"@type":"Answer","text":"The skill itself, the sensitivity model reference, the weekly test format, and the basket tactic library. It is free and security scanned. We re-publish the ZIP when the model changes, so download it again if your estimates start shifting."}}]}</script>