agentleFS
ARCASSystemsARCASSystems/FounderOS/skills/decision-framework/SKILL.md

decision-framework

Skill7 starsChanged 19 days agoMITView on GitHub

Walk through a structured decision when the founder is stuck. Trigger phrases: "help me decide", "should I", "what would you do", "weigh these options", "pros and cons", "I'm stuck between", "I can't decide", "trade-offs", "which option", or any situation where the user is evaluating alternatives. Covers business decisions, personal decisions, and strategic choices.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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. Distinctive:

    If exit code is 1, read the output line and surface it to the user verbatim.

    line 19
  2. Distinctive:

    If the decision-style field is unset (file exists but field empty), default to the standard template and offer to capture decision style …

    line 23
  3. Distinctive:

    If the snapshot is missing, run:

    line 29
  4. Very specific:

    mixed or unset: - use the standard template below as written.

    line 85
  5. Distinctive:

    No filler, no padding

    line 147

≈ “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.

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

Decision Framework

Runs on: reasoning - reads your files and reasons; any capable agent can run this.

Before You Write

Run: python scripts/check-identity-ready.py

If exit code is 1, read the output line and surface it to the user verbatim. Do not walk the framework. Stop.

Then read core/identity.md. Find the line **Decision style:** (Phase 0.7 captures this as gut, data, dialogue, or mixed). Lead with the founder's preferred mode using the templates below. Then run the standard framework after the lead-with block.

If the decision-style field is unset (file exists but field empty), default to the standard template and offer to capture decision style next time.

Brain context (default)

Before producing output, read brain/.snapshot.md. If it is missing, or its date: line is more than 3 days old, run python scripts/brain-snapshot.py --write first and read the fresh one - a stale snapshot read as current presents last week's flags and must-dos as today's, which is worse than no memory at all. If Python is unavailable, proceed without it and say so.

If the snapshot is missing, run:

python scripts/brain-snapshot.py --write

Then read it. If the snapshot script is also missing (older install), proceed using only the profile files. Do not block.

The snapshot tells you what flags are open, what the user is working on this week, and what the latest staleness state is. Apply this context to your output where it is relevant. Do not surface every snapshot field in every output - use judgment. For decision framing, recent decisions tell you what is already locked in (and should not be re-debated), and open flags often surface adjacent stalls that bear on the current choice.

Lead-with templates by style

gut - open with the GUT CHECK block:

GUT CHECK
---
Which option feels right? [Option name]
Why? [One sentence on what your gut is reacting to]
What's the immediate pull? [One line on the visceral pull or aversion]
What would make you doubt this gut call? [One line]
---
Now pressure-test below:

Then run the standard template. The matrix tests whether the gut call survives analysis.

data - open with the DATA block:

DATA
---
| Option | Cost | Time | Reversibility | Expected return |
|--------|------|------|---------------|-----------------|
| [A]    |      |      |               |                 |
| [B]    |      |      |               |                 |
---
Math check: which option has the cleanest numbers?
Surfaced for further work: [Options where the math is clean]
Cut here: [Options where the math is too noisy to evaluate]
---
Now run the standard template against the surfaced options only.

dialogue - open with the DIALOGUE block. Ask one question at a time, wait for the answer, build the decision live:

DIALOGUE
---
Q1: What are you actually choosing between? (state it in one sentence)
Q2: If this works, what does the world look like in 6 months?
Q3: If this fails, what's the worst realistic outcome?
Q4: What would you lose by choosing each option?
Q5: How reversible is each option?
---
Synthesis (after all answers): one paragraph naming the obvious choice and why.

mixed or unset - use the standard template below as written.

Decision Template

DECISION: [One clear sentence - what are you actually choosing between?]

---

OPTIONS
1. [Option A - name it clearly]
2. [Option B]
3. [Option C - if applicable]
4. [Do nothing / Wait - always include this]

---

FOR EACH OPTION:

What happens if this works?
[Best realistic outcome in 6 months]

What happens if this fails?
[Worst realistic outcome. What does failure actually cost?]

What do you lose by choosing this?
[Opportunity cost. What doors close?]

What's the reversibility?
[Can you undo this in 30 days? 6 months? Never?]

---

THE FILTERS

1. TIME TEST: Which option gives you the most time back for high-value work?
2. ENERGY TEST: Which option drains you least?
3. REGRET TEST: In 5 years, which choice would you regret NOT making?
4. 10/10/10: How will you feel in 10 minutes? 10 months? 10 years?
5. REVERSIBILITY: How hard is it to undo each option?

---

RECOMMENDATION
[Only if asked. Frame as "If I were in your shoes..." not "You should..."]

Quick Decision Mode

For smaller decisions:

DECISION: [What you're choosing]
LEAN TOWARD: [Option] because [one reason]
RISK: [The thing that could go wrong]
REVERSIBLE? [Yes/No/Partially]

Formatting Rules

  • Arrows (->) for recommendations
  • Keep it scannable
  • No filler, no padding

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.