Skill
Security
Skill
/finance-analysis-analyst
Drive repeatable finance variance analysis with clear assumptions, reconciliations, and executive summaries.
Install
$ npx -y skills add frumu-ai/tandem --skill finance-analysis-analyst --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/finance-analysis-analyst
Context preview
The summary Claude sees to decide when to auto-load this skill.
Drive repeatable finance variance analysis with clear assumptions, reconciliations, and executive summaries.
SKILL.md
finance-analysis-analyst.SKILL.mdname: finance-analysis-analyst description: "Drive repeatable finance variance analysis with clear assumptions, reconciliations, and executive summaries." version: "0.1.0" author: tandem compatibility: tandem tags: - finance - analysis - reporting requires: - python triggers: - variance analysis - financial summary - budget vs actual
Finance Analysis Skill
Mission
Turn financial inputs into reliable variance analysis and executive-ready recommendations.
Inputs To Use First
- inputs/sample_financial_data.csv
- emplates/income_statement_generator.py
- emplates/variance_analysis_template.py
- equirements.txt
Workflow
1. Validate schema, period coverage, and currency consistency. 2. Reconcile totals and isolate material variances. 3. Explain key drivers by category and period. 4. Generate concise management commentary. 5. Publish report artifacts for review.
Required Outputs
- outputs/data_reconciliation_notes.md
- outputs/variance_analysis.md
- outputs/executive_finance_summary.md
- outputs/finance_dashboard.html
Quality Bar
- Variances are quantified with clear baselines.
- Assumptions and data gaps are disclosed.
- Recommendations are specific and measurable.
- Summary is ready for leadership consumption.
Ships withtandem
Tandem is the authority layer between AI agents and company tools: runtime policy for tools, memory, approvals, and audit trails.
Get the whole plugin
Stats
125
Stars
13
Forks
Active
Maintenance
Rust
Language
23d ago
Last commit
9mo ago
Created
2h ago
Added