cowork-expense-audit
Cowork-style sweep of a folder of receipts, statements, and expense exports -- categorizes every transaction, matches receipts to statement lines, flags policy violations and anomalies, and outputs a clean expense report plus a findings memo.
git clone --depth 1 https://github.com/OneWave-AI/claude-skills /tmp/cowork-expense-audit && cp -r /tmp/cowork-expense-audit/cowork-expense-audit ~/.claude/skills/cowork-expense-auditSKILL.md
# Cowork Expense Audit Process an expense folder the way a careful controller does: reconcile receipts against statements, categorize consistently, and separate what is provably documented from what is missing. Input is a directory of receipts (PDF, images), card/bank statements, and any expense exports (.csv/.xlsx). Never invent an amount -- every number in the output traces to a source file. ## Workflow 1. **Inventory.** Catalog every file: receipts, statements, exports, and unclassifiable items. Note date ranges covered. If statements and receipts cover different periods, say so up front. 2. **Extract transactions.** Build a master ledger from the statements/exports: date, merchant, amount, currency. From each receipt: merchant, date, total, tax, payment method, line items when legible. 3. **Reconcile.** Match receipts to statement lines (exact amount+date first, then fuzzy within 3 days and small tip/FX variance). Output three lists: matched, statement lines with no receipt, receipts with no statement line. 4. **Categorize** every transaction (meals, travel, software, equipment, client entertainment, etc.). Use the company's category list if provided; otherwise propose one and apply it consistently. Tag anything client-billable separately. 5. **Flag.** Apply the policy if provided; otherwise apply defaults and label them as defaults: duplicate charges, weekend/holiday spend on business cards, round-number amounts, per-transaction limits exceeded, subscriptions appearing monthly with no owner, personal-looking merchants, and split transactions that dodge an approval threshold. 6. **Report.** Write `expense-report.xlsx`-ready CSV (or .xlsx if the xlsx skill is available) with the full categorized ledger, plus `audit-findings.md`: totals by category, reconciliation gaps, flagged items each with severity and the specific source file cited, and a missing-documentation list to chase. ## Rules - Never fabricate or estimate amounts. An unreadable receipt is logged as unreadable, not guessed. - Flags are questions, not accusations. Write "no receipt located for..." not "unauthorized spend." - Keep personal card statements strictly scoped: extract only lines the user identifies as business expenses; do not summarize personal activity. - Show your matching: every matched pair cites both source files; every unmatched item says what was searched. - Currency: preserve the original currency and note the statement's settled amount; never silently convert. - If more than 20% of transactions lack receipts, lead the findings memo with that fact -- it is the finding. ## Scheduled Mode As a monthly Cowork scheduled task pointed at a receipts inbox folder: process new files, append to the running ledger, and deliver the month's report and findings without re-litigating prior months. ## Quick Commands - "Audit [folder]" -- full workflow - "Reconcile only" -- steps 1-3, the matching report - "What's missing?" -- unmatched statement lines and the chase list - "Billable pull" -- client-billable transactions grouped by client
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.