financeskills
CLAUDE.md47 starsChanged 6 months agoMITView on GitHub
In this repository50 other files it gives its agents.
- AGENTS.mdAGENTS.md
- llms.txtllms.txt
- ai-anomaly-detectionSkill
- aro-computationSkill
- audit-checklistSkill
- automated-reconciliationSkill
- banking-complianceSkill
- budget-forecastSkill
- close-managementSkill
- company-valuationSkill
- corporate-consolidationSkill
- credit-analysisSkill
- crypto-accountingSkill
- cvp-breakevenSkill
- debt-payoffSkill
- debt-restructuringSkill
- deferred-taxSkill
- earned-value-mgmtSkill
- ecl-computationSkill
- esg-reportingSkill
- financial-analysisSkill
- fixed-asset-accountingSkill
- forensic-accountingSkill
- insurance-reservingSkill
- intercompany-accountingSkill
- inventory-costingSkill
- investment-analysisSkill
- journal-entrySkill
- lbo-modelingSkill
- lease-accountingSkill
- net-worth-trackerSkill
- nlp-earnings-sentimentSkill
- oil-gas-valuationSkill
- personal-budgetingSkill
- predictive-burn-rateSkill
- product-profitabilitySkill
- retirement-planningSkill
- revenue-recognitionSkill
- risk-assessmentSkill
- sox-complianceSkill
- startup-valuationSkill
- statement-preparationSkill
- tax-efficient-investingSkill
- tax-planningSkill
- three-statement-modelingSkill
- treasury-managementSkill
- variance-analysisSkill
- venture-debtSkill
- wacc-computationSkill
- working-capital-analysisSkill
The file
We split this CLAUDE.md into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Financial Accuracy: Always verify calculations using code (Python/Pandas) rather than mental math.
- Distinctive: line 8
Data Privacy: Never hardcode sensitive financial data.
- Very specific: line 9
Documentation: Every skill must follow the SKILL.md template structure.
- Distinctive: line 12
Python: Use type hints for all financial functions.
- Distinctive: line 14
Formatting: Use Black for Python formatting and Prettier for Markdown.
- Very specific: line 17
Before executing a skill, perform the "Initial Assessment" defined in the SKILL.md.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CLAUDE.md - FinanceSkills Rules
Project Overview
FinanceSkills is a repository designed to enable AI agents to perform complex financial tasks with high precision and reliability.
Style Guidelines
- Financial Accuracy: Always verify calculations using code (Python/Pandas) rather than mental math.
- Data Privacy: Never hardcode sensitive financial data. Use environment variables or mock data for examples.
- Documentation: Every skill must follow the
SKILL.mdtemplate structure.
Technical Standards
- Python: Use type hints for all financial functions.
- Testing: Include unit tests for any data transformation logic in
evals/folders. - Formatting: Use Black for Python formatting and Prettier for Markdown.
Execution Rules
- Before executing a skill, perform the "Initial Assessment" defined in the
SKILL.md. - Report confidence levels if a financial inference is ambiguous.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

