team-analyst: Skill for Claude Code

.agents/skills/excel-formulas/SKILL.md

excel-formulas is a skill for Claude Code from cas-team-analyst/team-analyst. It costs 53 tokens per session (5,035 once invoked), scanned A, original, MIT.

Guidance for building Excel workbooks whose formulas recalculate when users change selections, using the xlsxwriter library.

In plain words
What is it for?
Use it when creating new formula-based Excel workbooks, handling cross-workbook references, or preserving formula-driven versions outside the archived scripts.
Why use it?
It explains how to include formulas together with displayed starting values and a separate JSON copy of evaluated data. The documented formula approach is archived for some main workflow scripts.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions subagents; installed under .agents/ (shared by several agents).

This is cas-team-analyst/team-analyst's own configuration. It tells Claude Code how to work on team-analyst itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything team-analyst configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is output_file = '../selections/Chain Ladder Selections - LDFs.xlsx'.

Part of the team-analyst plugin — 7 skills, 6 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to cas-team-analyst/team-analyst. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cas-team-analyst/team-analyst/main/.agents/skills/excel-formulas/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cas-team-analyst/team-analyst

Made for: Claude Code.

Or install team-analyst, the plugin that ships this one along with the rest of its 7 skills, 6 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for excel-formulas

README.md
[![agentmods](https://agentmods.dev/badge/skills/cas-team-analyst/team-analyst/excel-formulas.svg)](https://agentmods.dev/skills/cas-team-analyst/team-analyst/excel-formulas)
Your own site
<a href="https://agentmods.dev/skills/cas-team-analyst/team-analyst/excel-formulas"><img src="https://agentmods.dev/badge/skills/cas-team-analyst/team-analyst/excel-formulas.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,035 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.05035
Opus 5 $0.00026 $0.02518
Sonnet 5 $0.00011 $0.01007
Haiku 4.5 $0.00005 $0.00504

Measured 9d ago against content hash 7026c3fa618c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

excel-formulas scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/excel-formulas/SKILL.md · 508 lines

How it starts

The opening of the file, as written. The whole thing — 508 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Formula-Driven Excel Workbooks

⚠️ NOTE (April 2026): The formula-based approach described in this skill has been archived for the main workflow scripts (2a, 2d, 5a, 6-analysis). These scripts now write hard-coded values from source data for easier maintenance. The formula-based versions are preserved in .claude/skills/excel-formulas/assets/archived-formula-scripts/ and can be restored if needed. See ARCHIVE_README.md in that directory for restoration instructions.

This skill remains valid for reference or for creating new formula-based workbooks outside the main workflow.

Quick Reference

Core principle: Inject live Excel formulas (not hard-coded values) with cached values so workbooks recalculate when actuaries change selections.

Tool: Use xlsxwriter for creating new workbooks - formulas display immediately with cached values. (Historical note: We previously used openpyxl, but it creates formulas without cached values, causing blanks.)

Critical pattern: Generate formula-driven Excel + JSON replica (xlsxwriter doesn't evaluate formulas, so JSON stores evaluated data for downstream scripts).

Key utilities:

  • create_xlsxwriter_formats() from modules/xl_styles.py for consistent formatting
  • col_letter() helper to convert 0-based column index to Excel letters (A, B, C...)

xlsxwriter Approach

Basic Setup

import xlsxwriter
from modules.xl_styles import create_xlsxwriter_formats

# Enable future functions to avoid compatibility warnings for STDEV.S, etc.
wb = xlsxwriter.Workbook('output.xlsx', {'use_future_functions': True})
fmt = create_xlsxwriter_formats(wb)
fmt['wb'] = wb  # Store reference for dynamic format creation

# Get first worksheet
ws = wb.add_worksheet('Sheet1')

Key Features

  • Cached formula values: Formulas display immediately (no blanks)
  • 0-based indexing: ws.write_formula(row, col, formula, format, cached_value)
  • use_future_functions: Handles Excel 2010+ functions without compatibility warnings
  • Faster: More efficient than openpyxl for creating new files

Read the full file on GitHub · 508 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 508 lines · 53 tokens per session scan A 7026c3fa618c

Subscribe to this mod's changes

excel-formulas is a skill published in the GitHub repository cas-team-analyst/team-analyst (11 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 5,035 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.