pareto

Ranks causes by outcome and spends a fifth of the effort on the highest-leverage interventions.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/azborgonovo/ai-skills --skill pareto-azborgonovo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pareto
Source: https://github.com/azborgonovo/ai-skills/tree/main/skills/drafts/pareto
Command: npx skills add https://github.com/azborgonovo/ai-skills --skill pareto-azborgonovo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Large tasks often hide a small set of causes that generate most of the outcome. This Skill applies the Pareto Principle to a request: it ranks the causes behind the work, spends roughly a fifth of the full effort on the interventions that address the top causes, and reports what that effort bought, so you can decide whether to fund the rest. ## Core Features & Use Cases - Cause ranking: Ranks causes by effect size using visible signals like error rates, coverage gaps, or file churn, and flags flat distributions where no vital few exist. - Budgeted execution: Spends about 20% of the full job's effort on the highest outcome-per-effort interventions, keeping the work coherent and the build unbroken. - Cut reporting: Reports the vital few causes, what the budget bought, and what remains, separating minor leftovers from unaffordable root causes. - Use Case: Ask for an 80/20 pass over a module with scattered bug reports; the Skill identifies the one confused component behind most failures, fixes what fits the budget, and prices the proper fix it could not afford. ## Quick Start Invoke /pareto with a request such as asking for an 80/20 pass over the test coverage gaps in the billing module.

Frequently Asked Questions about pareto

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I apply the 80/20 rule to a large coding task?▼

Invoke /pareto with your request. The Skill ranks the causes behind the work by effect size, spends roughly a fifth of the full effort on the interventions addressing the top causes, and reports what that effort bought and what remains.

How do I find what matters most in a codebase with many issues?▼

The Skill ranks causes rather than tasks, using visible signals like error rates, coverage gaps, and file churn. This surfaces patterns such as one confused module behind many scattered bug reports instead of a flat to-do list.

When should I not use a Pareto or 80/20 approach?▼

Avoid it for completeness-critical work: security fixes, compliance changes, migrations, or specific reported bugs. A partial migration or partial security fix has negative value, so the Skill declines the framing and does the work in full or asks the user.

Can the Pareto skill run automatically without being invoked?▼

No. The Skill is user-only with model invocation disabled, so it runs only when you explicitly call /pareto with a request. It will not trigger automatically on matching tasks.

What happens if the biggest cause is too expensive to fix?▼

An unaffordable root cause is reported as a finding with its estimated price, not silently skipped. The report separates minor leftover items from unaffordable ones so you can make the next funding decision.