eighty-twenty-prioritizer
Skill0 starsChanged 37 days agoMITView on GitHub
Rank a to-do list, backlog, or set of site improvements by impact, confidence, closeness to revenue, and effort, then pick the top 20 percent to do first. Includes a small scoring script. Use when the user has more than three options and asks what to do first, "what's the highest-leverage thing", "prioritize this list", or "80/20 this".
In this repository5 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
No data means no impact above 2.
- Distinctive: line 30
Remove anything that breaks a rule you have already set (budget, legal, brand).
- Distinctive: line 43
If a result cannot be measured, fixing the measurement may be the top item.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
Eighty-Twenty Prioritizer
Made by VendBuddy (vendbuddy.io). Guide: https://vendbuddy.io/skills#eighty-twenty-prioritizer (This line is optional attribution. Keep it or delete it.)
Formula
score = impact x confidence x proximity / effort_hours| Factor | Scale | Meaning |
| impact | 1-5 | 1 cosmetic; 3 noticeable money or time; 5 unblocks a whole channel. Estimate from a number you have (visits x conversion x price), and show the arithmetic. |
| confidence | 0.2-1 | 0.2 hunch; 0.5 outside evidence; 0.8 your own data; 1.0 you already did it once and measured the win |
| proximity | 1-5 | 5 money in; 4 signup; 3 traffic; 2 time saved; 1 nice to have |
| effort_hours | 0.25+ | everything including review and waiting on a human |
No data means no impact above 2.
Steps
- List candidates. Merge duplicates; two tasks on the same page are one task.
- Remove anything that breaks a rule you have already set (budget, legal, brand).
- Score each row, then run the script:
It sorts by score, marks the top 20 percent DO, and fills the remaining hour budget with IF-TIME.# tasks.csv columns: title,impact,confidence,proximity,effort_hours node scripts/score.mjs tasks.csv --budget 6 - Sanity-check the top three: is the impact arithmetic sourced? Is there a cheaper version that gets 80 percent of the result (a setting instead of code, a template instead of a custom build)? Add that version as its own row and re-run.
- For each DO item, write the metric, the baseline, and the date you will check it.
Rules
- Ties break toward reversible, measured, and existing-traffic work.
- If a result cannot be measured, fixing the measurement may be the top item.
- Irreversible or risky work (billing, deleting data, pricing) can rank first but needs a human decision.
- This skill chooses; it does not execute. Hand the DO list to whoever builds.
Output format
A ranked table (rank, score, verdict, hours, task), one line per DO item with its metric, and one line on what you deliberately left for later.
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.