Skip to main content
skill CX Codex official · Anthropic

tres-report-analyzer — Claude Code skill for TRES Finance reports

tres-report-analyzer — a Claude Code skill that parses TRES Finance XLSX exports and surfaces anomalies, key metrics, and action items automatically.

MIT ★ 4,931 updated 2026-10-24

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add anthropics/claude-plugins-community
/plugin install tres-finance-plugin@claude-community
Open on GitHub

What tres-report-analyzer does

The skill identifies which of the fifteen-plus TRES Finance report formats it is dealing with by reading tab names and column headers — Ledger Reconciliation, Asset Balances, Realized Gains & Losses, Cost Basis Stack, ERP Pre-Sync, and others. When the tab signature does not match any known pattern, it asks for confirmation before proceeding.

Extraction runs through scripts/analyze_report.py; if that script cannot handle a particular format, the skill falls back to reading the file with openpyxl directly. Checks are report-specific: reconciliation formats count pass/fail rows and sum discrepancies by asset and wallet, balance formats flag zero and negative entries, transaction formats pull the largest moves and any unclassified records, ERP formats list missing account mappings and sync failures.

Findings come back ordered by severity — red flags first, then headline numbers, then notable items, then a concrete action list. Large figures are rounded to readable values and the response stays under 500 words unless you ask for more. Python with openpyxl must be available in the environment.

What it helps with

  • detect the TRES report type from XLSX structure without manual inspection
  • count failed reconciliation checks and total the gap amounts
  • flag zero-balance and negative-balance rows in an asset export
  • compare lot movements and surface tax-loss harvesting candidates
  • verify account mapping status before an ERP sync

Example prompts for the agent

  • Load ledger_reconciliation_q1.xlsx and show me where the discrepancies are
  • Check this TRES file for realized BTC losses over the year
  • Go through the ERP Pre-Sync report and list which accounts are misconfigured

How to install tres-report-analyzer

1Plugin marketplace

/plugin marketplace add anthropics/claude-plugins-community
/plugin install tres-finance-plugin@claude-community

This installs the whole tres-finance-plugin plugin with all its skills

2Skills CLI (Vercel)

npx skills add anthropics/claude-plugins-community --skill tres-report-analyzer -a claude-code

3Manually: put the files in place

~/.claude/skills/tres-report-analyzer/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/tres-report-analyzer/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about tres-report-analyzer

How do I install tres-report-analyzer in Claude Code?

Run /plugin marketplace add anthropics/claude-plugins-community, then run /plugin install tres-finance-plugin@claude-community. The skill will be available in Claude Code after both commands complete.

What does tres-report-analyzer do?

It reads TRES Finance XLSX files, identifies the report type from the tab structure, and runs targeted checks. The output is a prioritized summary covering anomalies, key figures, and specific items to follow up on.

Does tres-report-analyzer require Python?

Yes. The skill calls scripts/analyze_report.py and relies on openpyxl. If the script fails for a given format it reads the file with openpyxl directly, but Python itself must be present in the environment.

Source text

SKILL.md · MIT
---
name: tres-report-analyzer
description: Analyze any TRES Finance report XLSX and produce an automatic findings summary. Trigger this skill whenever a user uploads a .xlsx file that came from TRES Finance and asks to "analyze", "summarize", "review", "check", "audit", "look at", "what does this show", "any issues", "anything interesting", or "walk me through" the report. Also trigger when the user uploads an Excel file and mentions TRES, reconciliation, balances, transactions, cost basis, roll forward, or ERP sync. The skill identifies the report type from the file structure, runs targeted analysis based on report-specific logic, and produces a clear findings summary highlighting anomalies, key metrics, and action items.
---

# TRES Report Analyzer

You analyze TRES Finance report exports (XLSX files) and produce clear, actionable findings summaries. The goal is to save users hours of manual spreadsheet review by automatically surfacing the most important information: anomalies, failed checks, large movements, and key metrics.

## How it works

1. **Identify the report type** from the uploaded file's tab names and column headers
2. **Run the analysis script** which performs report-specific checks
3. **Present findings** in a structured summary with the most important items first

## Step 1: Identify the report type

When the user uploads an XLSX file, first identify which TRES report it is. Use the tab names as the primary signal:

| Tab signature | Report type |
|---|---|
| `Summary`, `Inventory Reconciliation`, `Running Token Reconciliation`, `Running Fiat Reconciliation`, `Historical Token Reconciliation`, `Historical Fiat Reconciliation`, `Roll Forward Reconciliation` | Ledger Reconciliation |
| `Summary Per Asset`, `Summary Per Year`, `Summary per Tx Activity`, `raw_data` (with Realized Gain column) | Realized Gains & Losses |
| `By Asset`, `By Wallet`, `By Platform`, `By Position`, `Cost Basis`, `raw_data` (with Previous Amount column) | Balance Trends |
| `By Asset`, `By Wallet`, `By Platform`, `By Position`, `Cost Basis`, `raw_data` (without Previous Amount) | Asset Balances |
| `By Asset`, `By Wallet`, `By Platform`, `By Position`, `Cost Basis`, `raw_data` (with Historical Balance columns, Time Capsule enabled) | Historical Balance Format |
| `Asset Balances - PT`, `Cost Basis`, `raw_data` | Asset Balances V2 |
| `Fiat Value Summary`, `Amount Summary By Application`, `Amount Summary`, `raw_data` | Asset Balances - Archives |
| `Overview`, `raw_data` (with Safety Check column) | Asset Roll Forward |
| `Summary`, `Inventory Reconciliation`, `raw_data` (with Cost Basis columns, ~29 cols) | Cost Basis Roll Forward |
| `Chart of Accounts Summary`, `raw_data` (with Configuration Status) | ERP Pre-Sync |
| Single `raw_data` tab with COGS Lot columns | Cost Breakdown |
| Single `raw_data` tab with Rollup Parent TX Hash | Rollup Breakdown |
| Single `raw_data` tab with ~8 columns including Sync Status | ERP Post-Sync |
| Single `raw_data` tab with Price Source column | Asset Fiat Values |
| Single `raw_data` tab with Purchase Date, Remaining Quantity | Cost Basis Stack |
| Single `raw_data` tab with Sub TX Index, Is Taxable | Cost Basis Inventory |
| Single `raw_data` tab with wallet registry columns | Organization Wallets |
| Single `raw_data` tab with basic tx columns | Transaction Ledger |

If you cannot identify the report type, tell the user and ask them to confirm which report it is.

## Step 2: Run the analysis

Use the Python script at `scripts/analyze_report.py` to extract data from the XLSX file. Run it like this:

```bash
python /path/to/skill/scripts/analyze_report.py "/path/to/uploaded/file.xlsx" --output /path/to/output.json
```

The script outputs a JSON file with extracted metrics. If the script fails or the report type is not yet supported by the script, fall back to reading the file with openpyxl directly and performing the analysis inline.

### What to analyze per report type

Read `references/analysis-playbook.md` for the detailed analysis checklist for each report type. The general pattern is:

**For reconciliation reports** (Ledger Reconciliation, Asset Roll Forward, Cost Basis Roll Forward):
- Check columns: how many pass vs. fail?
- Which assets/wallets have the largest discrepancies?
- What is the total slippage or gap amount?
- Are there patterns (same wallet, same asset, same platform)?

**For balance reports** (Asset Balances, Historical Balance Format, V2, Archives, Balance Trends):
- Total portfolio value
- Top holdings by fiat value
- Any zero-balance or negative-balance entries?
- For Balance Trends: largest movers (biggest absolute change)
- Unverified tokens or missing prices

**For transaction reports** (Transaction Ledger, Realized Gains & Losses, Cost Breakdown):
- Total transaction count and date range
- Largest transactions by fiat value
- Total realized gains/losses (if applicable)
- Classification breakdown (how many of each type)
- Any unclassified transactions?

**For cost basis reports** (Cost Basis Stack, Cost Basis Inventory, Cost Basis Roll Forward):
- Total cost basis and unrealized gains
- Lots with largest unrealized losses (tax-loss harvesting candidates)
- Age of lots (any very old lots?)
- Impairment amounts if applicable

**For ERP reports** (Pre-Sync, Post-Sync):
- Configuration status breakdown (how many ready vs. misconfigured)
- Missing account mappings
- Failed syncs and error patterns
- Debit/credit balance check

## Step 3: Present findings

Structure your response as follows. Keep it concise -- the user wants insights, not a data dump.

### Format

Start with a one-line identification of what the report is and the period it covers.

Then present findings in order of importance:

1. **Red flags** (if any): failed checks, large discrepancies, missing data, failed syncs
2. **Key metrics**: total value, count, gains/losses -- the headline numbers
3. **Notable items**: largest transactions, top holdings, biggest movers -- things worth knowing
4. **Action items** (if any): specific things the user should investigate or fix

End with a brief note about what the user can ask as a follow-up (e.g. "I can drill into any specific asset or wallet if you want a closer look").

### Style rules

- Use actual numbers from the data, not vague descriptions
- Round large numbers sensibly ($1,234,567.89 -> $1.23M)
- No em-dashes or en-dashes (use -- instead)
- Keep the total response under 500 words unless the user asks for more detail
- If there are many findings, prioritize the top 5 and mention "N more items" the user can ask about

© Nadav Gilliam · MIT · anthropics/claude-plugins-community

Similar skills

All skills for Finance and business →
daily-production-report official anthropics daily-production-report — a skill for Claude Code and Codex that generates daily morning manufacturing reports. Runs before morning production standups using raw MES and ERP data exports. CX Codex +1 ★ 47,914repo stars report-builder official anthropics report-builder converts plain-English reporting requests into recurring reports with XLSX workbooks and chat summaries. Saves definitions to rerun metrics without repeated setup. CX Codex +1 401installs uptrend-analyzer tradermonty uptrend-analyzer scores market breadth 0–100 from Monty's Uptrend Ratio Dashboard data and suggests how much equity exposure fits the current environment. CX Codex +1 3,800installs news-reaction-failure-analyzer tradermonty The news-reaction-failure-analyzer Claude Code skill checks whether a crowded market ignored news that should have helped its position. It returns a CONFIRMED, NOT_CONFIRMED, or INSUFFICIENT_EVIDENCE verdict. CX Codex +1 2,900installs historical-cost-analyzer datadrivenconstruction historical-cost-analyzer — a skill for Claude Code and other platforms that analyzes historical construction costs. It enables project benchmarking, trend tracking, and estimate calibration. CX Codex +1 118installs excel-automation daymade excel-automation generates styled Excel reports using openpyxl, extracts data from large xlsm models with stdlib zipfile, and drives Excel on macOS. Handy for financial modeling and rebuilding paper forms. CX Codex +1 1,500installs

From the same set37

The whole set →
testdino-manual-tests testdino-manual-tests manages manual QA test cases and suites in TestDino directly from Claude Code. It lets you create tests, update steps, and browse suites without touching execution runs. CX Codex +1 ★ 4,931repo stars testdino-manual-runs Manage TestDino manual runs and case-level results from Claude Code. Use it to create runs, inspect their contents, assign cases, or record outcomes. CX Codex +1 ★ 4,931repo stars testdino-audit Runs a TestDino audit over Playwright test code through the TestDino MCP server and saves the findings as a markdown report. Only fires on an explicit request. CX Codex +1 ★ 4,931repo stars tres-upload-tx-header-validation tres-upload-tx-header-validation provides exact column headers for TRES Finance transaction CSV uploads and fixes missing column errors. CX Codex +1 ★ 4,931repo stars tres-export-3rd-party-contacts tres-export-3rd-party-contacts pulls every unnamed counterparty address out of a TRES Finance environment and writes a two-sheet XLSX: one ready to import as contacts, one with activity details. CX Codex +1 ★ 4,931repo stars tres-ledger-link tres-ledger-link turns a plain-language request into a shareable TRES Finance ledger URL with the filters already applied. CX Codex +1 ★ 4,931repo stars tres-asc845-swap-reprice-skill The tres-asc845-swap-reprice-skill skill adjusts swap inflows under ASC 845 so their value matches the outflows and the clearing account nets to zero. Use it to investigate a month-end residual. CX Codex +1 ★ 4,931repo stars tres-onboarding tres-onboarding runs a full TRES Finance onboarding for a new entity or account in eight steps, from wallet upload to rollup rules. CX Codex +1 ★ 4,931repo stars

Project sponsors

Companies that keep this analytics open