Variance Analysis logo

Variance Analysis

Community
davekilleen
variance-analysis

Use when explaining a dated actual-versus-budget or actual-versus-forecast variance for a comparable finance period. Not for tracking close checklist completion; use close-status.

Overview

Publisherdavekilleen
RepositoryDex
Skill namevariance-analysis
Stars
481
Forks
130
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by davekilleen on GitHub. Read the source before you install it.

Installation

Install the Variance Analysis AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/davekilleen/Dex.git /tmp/Dex
mkdir -p .claude/skills
cp -r /tmp/Dex/packages/dex-agent-plugin/skills/_available/finance/variance-analysis .claude/skills/variance-analysis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Variance Analysis in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Variance Analysis on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Variance Analysis is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

When to use

Use when a finance or leadership user needs an evidence-backed explanation of actuals against an approved budget or forecast for a named period, category, or total. Confirm the comparison period and basis before calculating.

Do not use this skill to post or reclassify ledger entries, change a budget or forecast, approve corrective action, or provide audit sign-off. Not for close-status tracking, tax advice, or a financial decision made on behalf of a human owner.

Inputs and source discipline

  1. Capture the period, comparison basis, metric definition, actual source, budget/forecast source, source dates, date checked, and explicit as-of date. Record unit, currency, sign convention, and time window for every input; never invent a missing date or denominator.
  2. Prefer reconciled ledger or close-package actuals, then an approved budget or forecast, then dated operational reports, then dated context in meeting notes. A narrative explanation is not evidence of a number. Preserve source hierarchy and contradictory inputs.
  3. Validate that actual and comparison values measure the same category, period, unit, currency, accounting basis, and aggregation. Convert only with a cited rate or rule and date; otherwise mark the comparison not comparable rather than forcing a result.

Method

  1. Work read-only and state the formula before computing: for example, dollar variance as actual - comparison, and percentage variance as variance / absolute comparison only when the denominator is non-zero and that convention is authorized. Preserve the sign and state how favorable/unfavorable is determined for revenue versus expense; never flip signs to make a result look better.
  2. Recalculate each category and reconcile the category variances to the supplied total, allowing only documented rounding. Investigate missing categories, scope differences, and duplicate rows; if totals cannot reconcile, report the total as unknown or contradictory.
  3. Apply the supplied materiality threshold in both amount and percentage terms when available. If no threshold is supplied, state that materiality was not assessed; do not invent a cutoff or call a result material solely because it is visually large.
  4. For each material or requested variance, classify the cause as timing or permanent only when dated evidence supports it. Label a plausible but unverified explanation hypothesized, and use unknown when evidence does not establish a cause. Keep corrective actions as recommendations for human review.

Truth and uncertainty rules

Use observed for a value or event directly supported by a cited source, inferred for an interpretation, unknown for missing evidence or an untestable cause, stale for evidence outside the requested period or freshness, and contradictory when credible sources disagree. Show confidence and its basis. Never invent dates, metrics, owners, intent, money, percentages, causes, status, or evidence. A recommendation is not a human decision.

Output contract

Return an analysis containing:

  • period, comparison basis, as-of date, units, currency, formula, denominator, and sign rule;
  • a category table with actual, comparison, dollar variance, percentage when valid, source/date, confidence, and comparability status;
  • the materiality rule or an explicit not-assessed state;
  • reconciled totals with rounding/scope differences called out;
  • each cause labeled observed, inferred/hypothesized, timing, permanent, unknown, stale, or contradictory, with supporting source evidence; and
  • source register, unknowns, contradictions, limits, and recommendations clearly separate from facts. Do not present an unverified cause as the explanation.

Safety and write boundaries

Remain read-only by default. Do not edit ledgers, budgets, forecasts, source notes, or reports. If a write, export, shared artifact, or other action is requested, preview the exact target, changes, and side effects; redact secrets or unapproved personal/confidential content; wait for explicit confirm from the responsible human authority; then perform only the approved action.

Verification and recovery

Read back every input and calculated row, recompute the formula independently, and reconcile category totals to the supplied total. Check sign, units, currency, period, denominator, source dates, and as-of scope; fail closed on any mismatch. If a source read or calculation fails, preserve the draft, mark the affected result unknown or blocked, record the failure, and rerun after correction. Never silently overwrite a contradictory total or promote a hypothesis to fact.

Frequently asked questions

What does the Variance Analysis AI skill do?

Use when explaining a dated actual-versus-budget or actual-versus-forecast variance for a comparable finance period. Not for tracking close checklist completion; use close-status.

Why use Variance Analysis on TypingMind?

Because you install it once and use it with any model. Variance Analysis is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Variance Analysis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/davekilleen/Dex/tree/main/packages/dex-agent-plugin/skills/_available/finance/variance-analysis. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Variance Analysis?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Variance Analysis?

As many as you like. As long as a model supports skills, you can use Variance Analysis with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Variance Analysis AI skill free?

It is published on GitHub by davekilleen. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇