virtue-review
Skill1 starsChanged 7 months agoMITView on GitHub
Weekly Stoic cardinal virtues audit. Courage, discipline, justice, wisdom. Score 1-5 per virtue, name a specific example, and commit to one virtue to rehearse next week. Complements weekly-review; run either embedded or standalone.
In this repository34 other files it gives its agents.
- accountability-mirrorSkill
- annual-physicalSkill
- bills-and-subsSkill
- brotherhoodSkill
- conscious-spendingSkill
- date-nightSkill
- decision-journalSkill
- discomfort-doseSkill
- emotion-coachSkill
- enough-checkSkill
- errand-batchSkill
- evening-examenSkill
- father-reviewSkill
- friend-reach-outSkill
- gratitudeSkill
- hard-conversationSkill
- home-maintenanceSkill
- kid-oneononeSkill
- love-map-refreshSkill
- mentor-touchSkill
- money-dateSkill
- morning-resetSkill
- parent-checkinSkill
- partner-checkinSkill
- partner-reviewSkill
- repairSkill
- resetSkill
- screwupSkill
- shutdown-ritualSkill
- sleep-protocolSkill
- training-planSkill
- values-checkSkill
- weekly-reviewSkill
- weekly-serviceSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 10
Run this in 5 to 10 minutes.
- Distinctive: line 62
Ask: "For the coming week, what is one specific action that would rehearse this virtue?"
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
/virtue-review
The Stoics named four cardinal virtues. They are not abstract. They are practices that you have either rehearsed this week or let atrophy.
Run this in 5 to 10 minutes.
The audit
For each virtue, the user gives:
- A score from 1 (didn't show up at all) to 5 (paid the price willingly).
- A single specific example, positive or negative.
Courage
The virtue of moving toward fear, danger, and truth.
- Where did I say the hard thing this week?
- Where did I ask the uncomfortable question?
- Where did I back down or sugarcoat?
- Score (1-5): ___
- Example: ___
Discipline
The virtue of self-mastery. Doing the harder right.
- Where did I pick hard over easy this week?
- Where did I keep a promise to myself?
- Where did I break one?
- Score (1-5): ___
- Example: ___
Justice
The virtue of treating others well. Fairness, service, fidelity.
- Who did I serve well this week?
- Who did I fail? What is the repair?
- Did I speak about absent people the way I would if they were in the room?
- Score (1-5): ___
- Example: ___
Wisdom
The virtue of seeing clearly. Rethinking, updating, humility.
- What did I see more clearly this week than I did last week?
- Where was I wrong and admitted it?
- What am I still fooling myself about?
- Score (1-5): ___
- Example: ___
The weakest virtue
Identify the lowest-scored virtue.
Ask: "For the coming week, what is one specific action that would rehearse this virtue?"
Examples:
- Courage → "I will have the conversation with
<person>about<topic>by Thursday." - Discipline → "I will not drink alcohol this week." Or "I will get up at 6am every day."
- Justice → "I will write the thank-you note I have been putting off. I will call my mom Sunday."
- Wisdom → "I will name one opinion I hold strongly and argue the opposite side for 20 minutes in writing."
Output
Append to ~/adulting-data/journal/virtue-log.md:
# <date>
Courage: <score>/5 — <example>
Discipline: <score>/5 — <example>
Justice: <score>/5 — <example>
Wisdom: <score>/5 — <example>
Focus virtue next week: <one>
Rehearsal: <specific action, due date>Then print a one-line summary. Not a lecture. The scoring is the teacher.
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.

