AgentStack
SKILL verified MIT Self-run

Variance Analysis

skill-m-binimran-finance-pack-variance-analysis · by m-binimran

Run budget-vs-actual / forecast-vs-actual variance analysis (FP&A) - compute variances, find drivers, and recommend actions. Use for monthly/quarterly close, business reviews, or reforecasts.

No reviews yet
0 installs
3 views
0.0% view→install

Install

$ agentstack add skill-m-binimran-finance-pack-variance-analysis

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Variance Analysis? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

variance-analysis

Explain the gap between plan and reality, then say what to do about it.

Process

  1. Compare actual vs. budget (and vs. prior/forecast) by line item: revenue, COGS, opex, EBITDA. Compute

the variance ($ and %) and flag material ones.

  1. Decompose drivers: price vs. volume vs. mix on revenue; rate vs. usage on costs; one-offs vs. structural.
  2. Favorable vs. unfavorable - and is it timing (will reverse) or permanent?
  3. Root cause + owner for each material variance.
  4. Action / reforecast: what changes for the rest of the year; update the outlook.

Output

  • A variance table (actual / budget / variance $ / variance % / driver / timing-vs-permanent / action) and a

short narrative on the material movers, plus any reforecast.

Guardrails

  • Actuals from the GL/close (sourced); don't fabricate a variance or driver.
  • Materiality threshold stated; reforecast figures labeled as estimates (projections-assumptions).
  • Confidential internal data stays internal (confidentiality-mnpi).

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.