agentleFS
ohanyanohanyan/adulting/skills/values-check/SKILL.md

values-check

Skill1 starsChanged 7 months agoMITView on GitHub

Quarterly values alignment review. Are you still living the values you claim? Pick 5-7 core values, rate alignment, find the one biggest gap, and commit to closing it this quarter.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If ~/adulting-data/values.md exists, load it.

    line 16
  2. Distinctive:

    Not 12. Not 3. Aim for 5-7.

    line 43
  3. Distinctive:

    Not goals. Not intentions.

    line 71
  4. Distinctive:

    Put the structural change on the calendar.

    line 81
  5. Distinctive:

    Put a calendar entry for the 45-day mark.

    line 91
  6. Distinctive:

    If values keep scoring low year after year with no movement, there are three honest possibilities:

    line 119

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/values-check

Most people will, if pressed, name 5-7 values they claim to live by. Then their calendar, their spending, and their most unguarded moments reveal a different set.

The gap between stated values and enacted values is the single most important data in self-knowledge. This skill surfaces it.

Run quarterly, 20 minutes.

Step 1: Name the values (or load them)

If ~/adulting-data/values.md exists, load it. Otherwise, walk the user through creating the list.

The prompt

"List 5-7 values you want to actually live by. Not what you'd say at a networking event. What you want your life, viewed from the outside over the next 10 years, to actually demonstrate."

Common (but personalize)

Pick from, adapt, or invent your own:

  • Courage
  • Integrity / honesty
  • Service / contribution
  • Love / presence with family
  • Health / physical stewardship
  • Curiosity / lifelong learning
  • Craftsmanship / excellence
  • Generosity
  • Stewardship (of resources, people, the planet)
  • Faith / spirituality
  • Simplicity
  • Justice
  • Humility
  • Adventure
  • Independence / self-reliance
  • Friendship / community

Not 12. Not 3. Aim for 5-7. More than 7 and you don't really have values, you have aspirations.

Step 2: Rate alignment per value

For each value, score 1 (stated but not enacted) to 5 (my life is clearly demonstrating this).

For each, give ONE piece of evidence (a specific thing from this quarter that shows your score).

Example:

ValueScoreEvidence
Health3Strength training 2x/week held. Sleep eroded. Alcohol creeping up.
Presence with family2Phone was a third party at most dinners. I canceled 2 of 3 Saturday 1:1s with Lucas.
Courage4Had the hard conversation with C. I still avoided the one with M.
Service2Intent was there; I did almost nothing externally facing this quarter.
Learning4Three books finished. Actually applied 2 ideas.

Step 3: The gap

Which value has the biggest gap between where you say it is and where your life is? That is your focus value for the quarter.

(Note: it may not be the lowest-scored value. It may be the value you SAY is most important and are scoring lowest on. "Family presence" scored 2 is a bigger gap than "courage" scored 3 if you say family is your #1 value and are behaving as though it's your #4.)

Step 4: The single commitment

For your focus value, pick ONE structural change for the next 90 days.

Not goals. Not intentions. Structural changes to how the day or week is arranged.

Examples:

  • Presence with family: phone in the kitchen drawer at 6 p.m. every weeknight.
  • Health: alcohol only on Fridays and Saturdays, no exceptions, for 90 days.
  • Service: recurring monthly slot on the calendar labeled "service act" with a specific act named each month.
  • Courage: every Sunday evening, name the hard thing for the coming week; put it on the calendar.
  • Learning: 30 minutes daily, phone in another room, with a physical book.
  • Craftsmanship: every Friday, 90 minutes to rewrite one artifact from the week.

Put the structural change on the calendar. If it does not appear on the calendar, it will not happen.

Step 5: Check in with someone

Tell one person (partner, close friend, mentor) about the focus value and the structural change.

The act of telling raises follow-through. Also, they will notice whether it's happening when you can't see.

Step 6: Mid-quarter and end-of-quarter review

Put a calendar entry for the 45-day mark. Brief check: how is the structural change holding?

At 90 days, re-run this skill. Did the gap close? What did you learn about yourself?

Output

Append to ~/adulting-data/journal/values-check-YYYY-Q.md:

# Values alignment — Q<n> <year>

## Values
<table of values, scores, evidence>

## Biggest gap (focus value)
<value>
Why this is the gap: <...>

## Structural change for this quarter
<specific change>
Put on calendar as: <...>
Told about it: <person>

## Next check: <45-day date>

The honest conversation

If values keep scoring low year after year with no movement, there are three honest possibilities:

  1. That is not actually your value. You think it should be. It isn't. Consider removing it from the list. (No shame. Better to have 4 real values than 7 pretended ones.)
  2. There is a deeper obstacle (fear, old wound, relationship dynamic) that is blocking it. May be therapy territory.
  3. Life structure is incompatible with the value. (E.g., "family presence" under a 90-hour job. The job will win. Something structural has to give.)

Name which of the three is going on. Only then can you actually close the gap.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.