cowork-invoice-chaser
Point Cowork at your invoices and payments records -- builds an AR aging report, drafts escalating follow-up emails matched to each invoice's age and the client relationship, and runs as a weekly scheduled task so nothing slips past 30 days unnoticed.
git clone --depth 1 https://github.com/OneWave-AI/claude-skills /tmp/cowork-invoice-chaser && cp -r /tmp/cowork-invoice-chaser/cowork-invoice-chaser ~/.claude/skills/cowork-invoice-chaserSKILL.md
# Cowork Invoice Chaser Chase receivables the way a firm-but-warm operator does: know exactly who owes what and for how long, escalate on a schedule, and never send a dunning email to someone who already paid. Inputs: a folder of issued invoices (PDF/.docx) and payment evidence (bank exports, remittance emails, a payments .csv, or a paid-list the user maintains). ## Workflow 1. **Build the ledger.** Extract from every invoice: number, client, contact, issue date, due date, amount, terms. From payment records: date, amount, payer. Reconcile -- match payments to invoices (exact amount first, then partial payments, then aggregated payments covering multiple invoices). 2. **Age the book.** Produce the AR aging report: current, 1-30, 31-60, 61-90, 90+ days past due, by client. Include total outstanding, weighted average days late, and the three largest exposures. 3. **Flag before chasing.** List invoices with ambiguous payment status (partial matches, unidentified deposits near the amount) separately. These get a human decision, not a chaser. 4. **Draft the chasers.** For each confirmed-unpaid invoice, draft an email matched to its escalation stage -- drafts only, never send: - Due in 3 days: friendly heads-up with invoice attached reference - 1-14 late: polite nudge, assume oversight, restate amount and payment details - 15-45 late: direct, reference prior contact, ask for a payment date - 46-90 late: firm, propose a call, mention terms (late fees only if the invoice/contract actually states them) - 90+: final notice tone, next-steps language, flag to the human for a collections/legal decision 5. **Digest.** One summary per run: total outstanding and change since last run, payments received, drafts queued by stage, ambiguous items needing a decision, and clients whose pattern changed (reliable payer suddenly 30 days late is a relationship signal, not just an AR line). ## Rules - Never send -- drafts only. A wrong dunning email costs more than a late invoice. - Never chase an ambiguous invoice. Unmatched payment evidence near the amount means human review first. - Match tone to relationship: the user can tag clients (`key account`, `standard`, `problem`); key accounts never get form-letter tone regardless of age. - One email per client per run, covering all their overdue invoices -- three separate nudges in one morning reads as automation and burns goodwill. - State late fees only when the underlying invoice or contract specifies them. Never invent penalty terms. - Keep the escalation memory: track what stage each invoice last received so a resent nudge escalates rather than repeats. ## Scheduled Mode As a weekly Cowork scheduled task: re-scan the folders, reconcile new payments, advance escalation stages, and deliver the digest with drafts ready for approval. The run is idempotent -- no invoice is double-chased within its stage window. ## Quick Commands - "Age my receivables" -- steps 1-2 only - "Chase everything overdue" -- full workflow - "Who pays late?" -- client payment-behavior profile from the ledger history - "Draft the 90+ letters" -- final-notice drafts only
Audit websites for accessibility issues and WCAG compliance. Use when checking accessibility, fixing a11y issues, or ensuring WCAG compliance.
Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.
Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.
Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized agent roles, tool access, communication protocols, and handoff rules.
Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and multi-agent conversations.
Assesses how ready a business is for AI adoption across six dimensions. Evaluates data maturity, tech stack, team skills, process documentation, budget, and culture. Generates a comprehensive ai-readiness-report.md with scores, gap analysis, and recommended starting points. Aligned with OneWave AI's audit methodology.
Generate animated videos and motion graphics from natural language descriptions. Creates a standalone Vite + React project with Framer Motion scenes that auto-play in the browser. Use when the user wants to create animations, motion graphics, video intros, animated presentations, or product demos.
Generate comprehensive API documentation including endpoint descriptions, request/response examples, authentication guides, error codes, and SDKs. Creates OpenAPI/Swagger specs, REST API docs, and developer-friendly reference materials. Use when users need to document APIs, create technical references, or write developer documentation.