margin-trend-review
Skill2 starsChanged 3 months agoMITView on GitHub
Recompute margin trends, flag material changes, and organize possible operating drivers for human investigation.
In this repository20 other files it gives its agents.
- level-open-financeSkill
- ar-integrity-reviewSkill
- cash-flow-forecastSkill
- categorization-history-healthSkill
- cfo-chart-packSkill
- cost-detail-footingSkill
- cost-rationalization-reviewSkill
- customer-margin-attributionSkill
- duplicate-billingSkill
- idle-cash-interest-reviewSkill
- month-end-close-previewSkill
- monthly-value-summarySkill
- monthly-variance-reviewSkill
- reconcile-accountSkill
- recurring-subscription-reviewSkill
- remittance-matching-reviewSkill
- revenue-leakage-reviewSkill
- spend-concentration-reviewSkill
- vendor-1099-readinessSkill
- vendor-rule-auditSkill
The file
Files
Review margin trends
Require consistent revenue and direct-cost definitions across periods. Recompute gross profit and margin rather than trusting displayed percentages. Flag threshold movements and separate arithmetic from causal explanations. Return period values, percentage-point change, data limitations, and driver questions covering labor, materials, price, callbacks, and mix. Human judgment determines the supported cause.
Attribution
Level Open Finance by Level. MIT licensed. Preserve the included copyright notice when redistributing.
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.