invoices-billing – Other skill for AI agents
Invoice and billing register: invoice number, client, project, issue and due dates, subtotal, discount, tax and withholding, total, payments, balance and aging. Use for billing follow-up.
Install the invoices-billing skill with one command
Pick the tool you use, copy the command and paste it in your terminal. The skill lands in that tool's skills folder and is ready in your next session.
Claude Code
mkdir -p ~/.claude/skills && curl -fsSL https://skill.dn1nguoi.com/z/invoices-billing-1d450.tgz | tar xz -C ~/.claude/skills
Call it in Claude Code: /invoices-billing – then describe the task you want done.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/invoices-billing-1d450.tgz | tar xz -C ~/.codex/skills
Call it in Codex: $invoices-billing – then describe the task you want done.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/invoices-billing-1d450.tgz | tar xz -C ~/.hermes/skills
Call it in Hermes Agent: /invoices-billing – then describe the task you want done.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/invoices-billing-1d450.tgz | tar xz -C ~/.deepcode/skills
Call it in DeepSeek: /invoices-billing – then describe the task you want done.
SKILL.md content
Invoices & Billing
What it is: Invoices from billable time or fixed fees, with tax, due dates and aging.
Overview
Works out the smallest useful Invoices & Billing setup for the business in front of it, then
builds it only when asked. The default output is a short recommendation, not a
spreadsheet. Artifacts - CSV, SQL DDL, JSON Schema, Notion mapping - are produced on
request, from one field list so they cannot drift apart.
Layer: Layer 8: Operate. Fits: Starter stage. Table code: n/a.
When to Use This Skill
- invoice tracker
- billing spreadsheet
- invoice register
- accounts receivable aging
Also use it when the user says "invoices from billable time or fixed fees, with tax, due dates and aging", or describes the same process happening in a
spreadsheet, a document or someone inboxes.
Do not use it for: payroll calculation, tax filing, or legal advice. This skill produces
empty templates only - it never holds or processes real employee or customer data.
How It Works
The upstream shared contract is not bundled; follow the explicit intent, artifact and authorization rules below. The module-specific rules below define only domain fields, decisions, calculations, and safety constraints.
Step 1 - Identify intent
Read the request and pick the intent before asking anything.
- "set up" or "build" or "create" -> the user wants artifacts; go to Step 2.
- "our process is ..." or "it is in a sheet" -> the user wants to move an existing process; capture it, then Step 2.
- "is this right" or "review" or "audit" -> the user wants a check, not a build; answer from what they share.
- "how do I ..." -> advice question; answer directly and offer the build only if it helps.
Ask only if this is the highest-value missing fact; otherwise proceed without an opener:
> Q: How do you bill clients today?
Step 2 - Ask only what is missing
Skip anything the user already answered, in any earlier message. Ask the rest one at a
time, and stop as soon as the remaining answers would not change the output.
- Billing - How many clients? / Monthly, milestone or hourly? / Invoices raised by whom?
- Terms - Payment terms? / Retainer or one-off? / Any late fees?
- Tracking - How is status tracked? / Sent, due or overdue? / Who chases?
- Current process - What tool today? / Accounting package or sheet? / What gets missed?
- Outcome - What do you need? / An invoice record, a template or both?
Never invent an answer. If the user does not know, record it as unknown and carry on.
Step 3 - Hold the internal context
Hold the answers in this shape. It stays internal - it is not shown to the user unless
they ask, and it never carries a value the user did not give.
module: invoices-billing
intent: null # setup | advice | review | fix | build | convert | export
scale: null # Starter | Growth | Scale, only if the answer changes it
areas:
"Billing": null
"Terms": null
"Tracking": null
"Current process": null
"Outcome": null
requested_outputs: [] # csv | sql | json | notion | xlsx - requested formats only
confirmed_facts: [] # only what the user actually said
open_questions: [] # the unanswered ones, in the order worth askingStep 4 - Recommend the smallest workflow
If an artifact was requested, build it after resolving essential missing facts. Otherwise give a short recommendation and offer the relevant artifact.
Recommended approach: One invoice record with the client, the amount, the due date and the status, and let the accounting package handle the actual invoice document.
Why this one: Billing problems are chasing problems. A due date and a status per invoice is the minimum that makes chasing possible.
Workflow: Work recorded → Invoice raised → Status tracked → Chased → Paid or overdue
Step 5 - Build only on request
Once the user asks for it, derive the fields from the confirmed context and emit the
requested artifacts. For machine-readable text, keep prose outside the data; for files,
provide a usable link. Report material validation failures or limitations separately.
**A selected Notion output is rendered by notion-manual-import, so route the
Notion step there.** When the user selects Notion, hand that step to
@notion-manual-import: it holds the CSV, the property
mapping, the import steps and the verification checklist, and it renders the Field
Reference below instead of defining a table of its own. Do not restate the mapping
here and do not improvise the import steps. Manual CSV and mapping outputs need no
connection. For requested workspace changes, follow the shared contract: verify actual
tool access and the target before writing. A user saying "connected" is not tool evidence.
Never ask for a Notion password or token.
For an Excel-compatible CSV, use UTF-8 with a byte order mark so Excel opens the
text correctly. A CSV is not an .xlsx workbook; create .xlsx only when the user
requests a workbook.
A CSV carries no types, so after it, name the columns
that need a number, date or currency format applied.
Invoice Number,Client,Project,Issue Date,Payment Terms (Days),Due Date,Currency,Time Entries,Subtotal,Discount,Tax Rate %,Tax Amount,Withholding Tax,Total,Payments,Amount Paid,Balance,Days Overdue,Aging,Payment Status,Status,Sent Date,Prepared By,Approved By,Notes,Invoice ID
INV-1041,Northwind Traders,Website Redesign,2026-08-15,30,2026-09-14,INR,"TIME-2026-011, TIME-2026-012",118000.00,4720.00,18,20390.40,20000.00,133670.40,PAY-2210,100000.00,13670.40,12,0-30 days,Part Paid,Issued,2026-08-15,Ananya Rao,Vikram Singh,"Follow-up sent in September; the client queried the retainer line, not the hours.",INVREC-1041CREATE TABLE invoices_billing (
invoice_number VARCHAR(255),
client VARCHAR(255),
project VARCHAR(255),
issue_date DATE NOT NULL,
payment_terms_days NUMERIC NOT NULL,
due_date DATE NOT NULL,
currency VARCHAR(255),
time_entries VARCHAR(255), -- relation -> target record
subtotal NUMERIC(14,2) NOT NULL,
discount NUMERIC(14,2) NOT NULL,
tax_rate_pct NUMERIC NOT NULL,
tax_amount NUMERIC(14,2) NOT NULL,
withholding_tax NUMERIC(14,2) NOT NULL,
total NUMERIC(14,2) NOT NULL,
payments VARCHAR(255), -- relation -> target record
amount_paid NUMERIC(14,2) NOT NULL,
balance NUMERIC(14,2) NOT NULL,
days_overdue NUMERIC NOT NULL,
aging VARCHAR(255),
payment_status VARCHAR(100) NOT NULL,
status VARCHAR(100) NOT NULL,
sent_date DATE NOT NULL,
prepared_by VARCHAR(255),
approved_by VARCHAR(255),
notes TEXT,
invoice_id VARCHAR(255) PRIMARY KEY,
created_at TIMESTAMP DEFAULT NOW(),
updated_at TIMESTAMP DEFAULT NOW()
);
CREATE INDEX idx_invoices_billing_status ON invoices_billing (status);{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "Invoices & Billing",
"type": "object",
"additionalProperties": false,
"properties": {
"Invoice Number": { "type": "string" },
"Client": { "type": "string" },
"Project": { "type": "string" },
"Issue Date": { "type": "string", "format": "date" },
"Payment Terms (Days)": { "type": "number" },
"Due Date": { "type": "string", "format": "date" },
"Currency": { "type": "string" },
"Time Entries": { "type": "string" },
"Subtotal": { "type": "number" },
"Discount": { "type": "number" },
"Tax Rate %": { "type": "number" },
"Tax Amount": { "type": "number" },
"Withholding Tax": { "type": "number" },
"Total": { "type": "number" },
"Payments": { "type": "string" },
"Amount Paid": { "type": "number" },
"Balance": { "type": "number" },
"Days Overdue": { "type": "number" },
"Aging": { "type": "string" },
"Payment Status": { "type": "string" },
"Status": { "type": "string" },
"Sent Date": { "type": "string", "format": "date" },
"Prepared By": { "type": "string" },
"Approved By": { "type": "string" },
"Notes": { "type": "string" },
"Invoice ID": { "type": "string" }
},
"required": [
"Issue Date",
"Payment Terms (Days)",
"Due Date",
"Subtotal",
"Discount",
"Tax Rate %",
"Tax Amount",
"Withholding Tax",
"Total",
"Amount Paid",
"Balance",
"Days Overdue",
"Payment Status",
"Status",
"Sent Date"
]
}| CSV column | Notion property | Set after import |
|---|---|---|
| Invoice Number | Title | Use as the database title |
| Client | Text | Leave as Text |
| Project | Text | Leave as Text |
| Issue Date | Date | Convert to Date |
| Payment Terms (Days) | Number | Convert to Number |
| Due Date | Date | Convert to Date |
| Currency | Text | Leave as Text |
| Time Entries | Relation (link to the target database) | Convert to Relation, link to the target database |
| Subtotal | Number (format: currency) | Convert to Number, set format … (full content is in the download package)
Related skills
- ios-redteam-pipeline – End-to-end iOS red-team pipeline
- ios-screens – Build iPhone app screens that feel native: navigation, sheets, Dynamic Type, dark mode…
- issue-grievance-tracker – Grievance register: issue type, raised by or anonymous, person or team concerned…
- it-manager-hospital – World-class Hospital IT Management Advisor specializing in clinical safety, digital…
- itil-expert – Expert advisor for ITIL 4 and ITIL 5 (2026 digital product paradigm), specialized in…
- jq – Expert jq usage for JSON querying, filtering, transformation, and pipeline integration…
- julia-pro – Master Julia 1.10+ with modern features, performance optimization, multiple dispatch…
- keyword-clustering-tool – Keyword Clustering Tool. Use when working with keyword list.