- Home
- Skills
- Finance & Accounting
- Weekly KPI Digest from a Sales CSV
More screenshots
Works with the AI Agents you already use
Weekly KPI Digest from a Sales CSV
Works out this week vs last week from a simple sales and expenses CSV and writes a plain-English digest. No forecasts or financial advice.
$5
Weekly KPI Digest from a Sales CSV
Example session with this skill installed
How did the shop do last week? Here's my sales and expenses export, sample_ledger.csv (date, type, category, amount, order_id). Use the latest full Monday–Sunday week.
- Read your context and instructions
- Compiled the weekly kpi digest
- Generated the data export
Weekly digest: 2026-10-12 to 2026-10-18
Example output written by an agent from examples/sample_kpi_facts.md. Every figure is copied from that file.
Headline: Revenue was $1,098.00, up $572.25 (+108.84%) on last week, and the week finished with a net of $123.00 after a net loss of -$234.25 the week before.
What happened
- Revenue: $1,098.00 (+$572.25 / +108.84% vs last week). Gross sales were $1,122.00, less $24.00 in refunds, the same refund amount as last week.
- Expenses: $975.00 (+$215.00 / +28.29%).
- Net: $123.00 (last week -$234.25). The % change is shown as n/a because last week's net was negative.
- Orders: 41 (+14); the average order was $27.37, up from $20.36.
Drivers
- Coffee beans brought in $738.00 this week, up $450.00 on last week, the biggest single change. Merch was up $96.00 and drinks up $39.00.
- Expenses rose mainly because of a new $185.00 equipment repair line. Supplies were up $30.00. Payroll was $640.00.
Watch list
- Refunds were $24.00 for the second week running (Merch).
- 7 rows from this week (Oct 19 onward) aren't included yet because the week isn't finished.
- Only 2 earlier full weeks were available for the trailing average (revenue $634.88, expenses $1,360.00; the expenses average includes the $1,200.00 rent payment on Oct 1).
Questions for you
- Was the $185.00 equipment repair a one-off?
- Do you know what drove the jump in coffee bean sales (a promotion, a wholesale order)? The data doesn't say.
Numbers calculated from sample_ledger.csv, data through 2026-10-20. Draft for your review.
KPI facts: week 2026-10-12 to 2026-10-18
Compared with last week (2026-10-05 to 2026-10-11).
| Metric | This week | Last week | Change | Change % |
|---|---|---|---|---|
| Revenue (sales - refunds) | $1,098.00 | $525.75 | +$572.25 | +108.84% |
| Gross sales | $1,122.00 | $549.75 | +$572.25 | +104.09% |
| Refunds | $24.00 | $24.00 | $0.00 | 0.00% |
| Expenses | $975.00 | $760.00 | +$215.00 | +28.29% |
| Net (revenue - expenses) | $123.00 | -$234.25 | +$357.25 | n/a |
| Orders | 41 | 27 | +14 | +51.85% |
| Average order value | $27.37 | $20.36 | +$7.01 | +34.43% |
| Net margin | 11.20% | -44.56% |
Trailing average of the previous 2 week(s): revenue $634.88, expenses $1,360.00, net -$725.13, orders 27.00.
This week by category
| Revenue category | Amount |
|---|---|
| Coffee beans | $738.00 |
| Merch | $240.00 |
| Pastries | $68.00 |
| Drinks | $52.00 |
| Expense category | Amount |
|---|---|
| Payroll | $640.00 |
| Equipment repair | $185.00 |
| Supplies | $150.00 |
Biggest revenue moves vs last week: Coffee beans +$450.00; Merch +$96.00; Drinks +$39.00
Biggest expense moves vs last week: Equipment repair +$185.00; Supplies +$30.00
Data notes
- 7 row(s) dated after 2026-10-18 were not included (current, unfinished week).
Expected KPI facts for examples/sample_ledger.csv, data dated 2026-09-22 to 2026-10-20.
sample_ledger.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Give your agent a CSV with date, type (sale, refund or expense) and amount (optionally category and order ID). It works out gross sales, refunds, revenue, expenses, net, margin, orders and average order value for the week, week-over-week change, a trailing average of up to 4 earlier weeks, and the biggest category moves, then writes a short digest that uses only those numbers and asks you about causes instead of guessing.
Drafts, not autopilot. This skill prepares drafts and reports for you to review. It never sends email, posts replies, or contacts anyone.
Your data. The skill makes no network calls. Your agent sees the content you give it under your agent/model provider's terms.
Uses the open Agent Skills format supported by Claude Code, Cursor, Codex and others.
AI-assisted. This skill was built with AI assistance. Your own AI agent writes the drafts and does any arithmetic by following the skill's steps, so read every draft and check every total.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Finance & Accounting.
- Other exports (Shopify, Square, bank) must first be mapped to the three columns (your agent can help).
- Fixed KPIs.
- No forecasts or financial advice.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 25 days ago
- Software
- Code execution
Python, for example. Without it the agent only attempts a small ledger and rechecks each sum.
Permissions
File Scopes
Services: None. No network access; it doesn't connect to email, accounting or review sites, and never sends or posts anything. File scopes: Read: the CSV you name. Write: only files you ask for (e.g. digest-YYYY-MM-DD.md).