Free agents + LAUNCH30: 30% off paid agents until 31 Dec 2026 (one-time purchases only) See free agents
Oarsman AI Sign in

E-commerce Weekly Report Skill Pack for Claude / Docs

E-commerce Weekly Report Skill Pack for Claude: setup guide

Now part of Shop Statement P&L Pro. From Shop Statement P&L Pro v1.1.0, the same four skills ship inside it (in the weekly-report/ folder) at no extra cost, alongside its main skill. If you already bought this pack, your download keeps working and stays available.

Four Agent Skills that turn raw Shopify, WooCommerce and Amazon order exports into the Monday report you'd otherwise build by hand: what sold, what changed, which products actually make money, and what looks wrong this week.

Skill What it does You get
store-export-normalizer Reads Shopify Orders CSV, WooCommerce order exports and Amazon "All Orders" reports (tab-separated, UTC). It auto-detects each, converts to your timezone, splits order-level discounts, refunds and shipping across lines, removes double-exported rows and hashes customer emails. Any other store (Etsy, Flipkart, Meesho, custom) works through a small column map. One clean order_lines.csv + a data-quality report
weekly-kpi-report Net and gross sales, orders, AOV, units, discount and refund rates, new vs returning customers. Each is compared with last week and the 4-week average, by platform, with top SKUs, movers, discount-code use and daily charts. weekly_report.md, .xlsx, 2 charts
sku-profitability Contribution margin per SKU and per SKU x platform after COGS, packaging, marketplace referral and closing fees, payment fees, FBA and shipping. You set the fee rules in an editable file. Flags loss-makers, thin margins, channel-only losers and missing costs. sku_profit.xlsx, ranked action list, chart
sales-anomaly-watch Compares this week with the previous 28 days: daily spikes or drops (robust z-score), SKUs that stopped selling, demand jumps, refund spikes, leaked discount codes, channel drops, AOV shifts, big orders. Each finding comes with a "what to check" line. anomalies.md, .csv, chart

For store owners, e-commerce managers and the freelancers and agencies who report to them.

Try it

  • "Here are my Shopify and Amazon exports. Give me this week's report."
  • "Which products are losing money once Amazon fees are in?" (attach your cost sheet)
  • "Anything weird in sales this week?"

The samples/ folder has 8 weeks of a fictional coffee store across all three platforms, with planted problems: a leaked staff discount code, a refund spike, a stockout, a loss-making gift box and a product with no cost. Run the skills on it first and see if they catch everything (they do; see TESTS.md).

AI disclosure and limits

  • It works from exports, not live store APIs, so there are no logins or API keys to hand over. Export, upload, ask.
  • Contribution margin is before ads, salaries and overheads. It isn't net profit, and the reports say so.
  • Fee defaults (Amazon referral 15%, payment 2%, shipping 70 per order) are placeholders. Put in your own before trusting margins.
  • Anomaly flags mean "go look", not "we know why". For example, the script can't see your inventory.
  • Claude writes the summary text around the numbers; that text can be wrong. Check it before you send the report on.
  • Not tested: live store APIs (it reads exports only), every custom export layout, or Claude's summary quality on your data.

What you need

  • A Claude plan with Skills and code execution turned on, or Claude Code, or the Claude API.
  • For Claude Code on your computer: Python 3.9+ with pandas and openpyxl (matplotlib optional, for charts).
  • Order exports from your store(s) and a cost sheet.

5-minute setup

  1. Unzip the pack.
  2. In claude.ai, open Settings > Capabilities. Turn on code execution.
  3. Open Customize > Skills. Click +, then Upload a skill.
  4. Upload each zip in claude-ai-uploads/. One zip is one skill.
  5. Check the skills are on. Start a chat, attach your files and ask in plain words.
  6. Not sure it works? Try a sample first: ask Claude to run sales-anomaly-watch on the files in samples/.

Using Claude Code or the API instead? See Install below.

Install

You need Python 3.9+ with pandas and openpyxl wherever the scripts run. Claude's code-execution sandbox already has them. matplotlib is optional: without it you still get every table and report, just no PNG charts.

Claude Code (CLI or desktop)

Option A: copy the skills (simplest)

unzip oarsman-ecommerce-weekly-report-pack.zip
cp -r oarsman-ecommerce-weekly-report-pack/skills/* ~/.claude/skills/        # all your projects
# or, for one project only:  cp -r oarsman-ecommerce-weekly-report-pack/skills/* .claude/skills/

Start a new session and ask for the task in plain words (see "Try it" below). Claude picks the right skill by itself.

Option B: install as a plugin (one command to update later)

unzip oarsman-ecommerce-weekly-report-pack.zip
claude plugin marketplace add ./oarsman-ecommerce-weekly-report-pack
claude plugin install oarsman-ecommerce-weekly-report-pack@oarsman-ecommerce-weekly-report

In plugin mode the skills are namespaced, e.g. /oarsman-ecommerce-weekly-report-pack:<skill-name>, and they still trigger automatically.

Claude.ai (web, desktop app)

  1. Turn on code execution: Settings > Capabilities > Code execution and file creation (in the newer layout it's called "Create and edit files").
  2. Open Customize > Skills, click +, choose Create skill, then Upload a skill.
  3. Upload each zip in claude-ai-uploads/. Each zip holds one skill, so repeat for every skill in the pack.
  4. Make sure the skills are toggled on. Then upload your files in a chat and ask in plain words.

On Team or Enterprise plans, an owner has to allow Skills and code execution under Organization settings > Plugins & skills first.

Claude API (Agent Skills)

Upload each skill folder with the Skills API (POST /v1/skills, beta header skills-2025-10-02) and attach it in the container of a Messages request that has the code-execution tool enabled. The API sandbox has no internet access and no pip install. Every script in this pack uses only the standard library plus pandas and openpyxl, which are preinstalled.

Other agents that read SKILL.md

The folders follow the open Agent Skills format (agentskills.io), so tools that support it can load them too: copy skills/* into that tool's skills folder. Only Claude has been tested.

Check it works on your machine

cd oarsman-ecommerce-weekly-report-pack
python tests/run_tests.py

This reruns every script on the bundled sample data and checks the numbers. You should see 33/33 checks passed. The full record of our own run is in TESTS.md, and the files it produced are in expected/.

What's in the folder

skills/sales-anomaly-watch/  SKILL.md, scripts/anomalies.py
skills/sku-profitability/  SKILL.md, assets/fees_default.json, scripts/sku_profit.py
skills/store-export-normalizer/  SKILL.md, assets/column_map_example.json, scripts/normalize_orders.py
skills/weekly-kpi-report/  SKILL.md, scripts/weekly_report.py
samples/            sample data used by the tests and for trying the skills
tests/              run_tests.py, validate_skills.py, fixtures/
expected/           the exact files our test run produced
TESTS.md            test record: every check, its result, and excerpts of real outputs
.claude-plugin/     plugin.json + marketplace.json for Claude Code

Licence and support

One buyer, one business (yours or the client you're working for). You can change the skills and deliver the outputs to clients, but you can't resell or share the pack. Full terms are in LICENSE.txt.

Support is self-serve: this README and TROUBLESHOOTING.md (fixes and FAQ). There is no call, chat or email support. Fixes ship as new versions at your download link; CHANGELOG.md lists every change.

Built by Oarsman AI, with AI-assisted development. Every number in the examples comes from a real test run (see TESTS.md). Not affiliated with Anthropic. Claude is a trademark of Anthropic, PBC.