reconciliation

by google-gemini

Reconcile loaded expenses against the pre-parsed invoice database, flagging discrepancies like amount mismatches, missing invoices, and merchant mismatches…

npx skills add https://github.com/google-gemini/gemini-managed-agents-templates --skill reconciliation

Download ZIP GitHub

Reconciliation

Reconcile expenses from expenses.csv against the pre-parsed invoice database (parsed_invoices.json) completely locally (offline). It compares records, performs fuzzy merchant matching, and generates a detailed discrepancies report.

Embedded Script

python3 skills/reconciliation/scripts/reconcile.py --workspace .agents/workspace

Arguments

Argument	Default	Description
`--workspace`	`.agents/workspace`	Workspace directory containing expenses.csv and parsed_invoices.json
`--tolerance`	`0.01`	Amount match tolerance in dollars

What it does

Loads expenses.csv from .agents/workspace/ (columns: date, employee, merchant, category, amount, memo).
Loads parsed_invoices.json from .agents/workspace/ (generated by the pdf-parsing skill).
Performs local fuzzy matching between expenses and invoice records (normalized merchant names, amount tolerance).
Flags discrepancies: Amount Mismatch, Missing Invoice, Unmatched Invoice, Merchant Mismatch.
Generates .agents/workspace/reconciliation_report.md with summary stats and discrepancy tables.
Generates .agents/workspace/reconciliation_data.json with machine-readable matched results.

Dependencies

None! This script runs 100% locally with zero external API calls.

Discrepancy Types

Type	Description
Amount Mismatch	Expense and invoice matched by merchant but amounts differ beyond tolerance
Missing Invoice	Expense record exists with no matching invoice document
Unmatched Invoice	Invoice document exists with no matching expense record
Merchant Mismatch	Expense and invoice matched by amount but merchant names differ significantly

Output

File	Path	Description
Reconciliation Report	`.agents/workspace/reconciliation_report.md`	Human-readable markdown report with summary stats, discrepancy table, and matched items
Reconciliation Data	`.agents/workspace/reconciliation_data.json`	Structured JSON with expenses, invoices, matches, and discrepancies

More skills from google-gemini

Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent. Drive terminal UI (TUI) applications…

Guide for using the Gemini API CLI tool. Use when you need to interact with the Gemini API via the command line, manage agents, or generate media (images,…

behavioral-evals

Guidance for creating, running, fixing, and promoting behavioral evaluations. Use when verifying agent decision logic, debugging failures, debugging prompt…

gemini-live-api-dev

Real-time bidirectional streaming with Gemini over WebSockets for audio, video, and text conversations. Supports audio input/output (16 kHz PCM), video frames, text, and automatic transcriptions with voice activity detection for interruption handling Includes native audio features: affective dialog, proactive audio, and thinking mode; function calling for synchronous and asynchronous tool use; and Google Search grounding Offers session management with context compression, resumption, and...

gemini-omni-flash-api

Use this skill for generative video editing, text-to-video, image-referenced video generation, and first-frame-to-video transition animations using the…

Build applications with Google's Gemini models, supporting multimodal content, function calling, and structured outputs across Python, JavaScript, Go, and Java. Access current Gemini 3 models (Pro, Flash, Pro Image) with 1M token context; legacy Gemini 2.x and 1.5 models are deprecated Supports text generation, image/audio/video understanding, function calling, structured JSON output, code execution, context caching, and embeddings Official SDKs available: google-genai (Python),...

gemini-interactions-api

Unified interface for Gemini models and agents with server-side state, streaming, and tool orchestration. Supports multiple current models (gemini-3-flash-preview, gemini-3-pro-preview, gemini-2.5-flash/pro) and the Deep Research agent; automatically substitute deprecated model IDs with current alternatives Offload conversation history to the server via previous_interaction_id for stateful multi-turn interactions without manual history management Built-in tool orchestration including...

Posts a condensed version of the briefing to a Google Chat or Slack incoming webhook, so the daily run delivers itself — skips silently when no webhook is…