agentleFS
teodstrteodstr/workbench/skills/decision-making/SKILL.md

decision-making

Skill0 starsChanged yesterdayMITView on GitHub

Make a clear, documented decision between options: frame the problem, list real alternatives, weigh them on explicit criteria with a decision matrix, check the usual biases, decide who decides and by when, and record the decision. Use whenever someone hesitates between options in a project or in life (two quotes, two jobs, rent or buy, build or outsource, which tool, go or no-go). Triggers: "help me decide", "which option", "pros and cons", "decision matrix", "should I", "aide-moi à décider", "quelle option", "avantages et inconvénients", "matrice de décision", "ayúdame a decidir", "qué opción", "pros y contras", "matriz de decisión".

7 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. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 5

    Distinctive

    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
  1. Distinctive:

    When a project is blocked by a choice between options.

    line 21
  2. Distinctive:

    Not for small, easily reversible choices: decide quickly and move on.

    line 23
  3. Distinctive:

    Frame the problem: before comparing options: what exactly is being decided, by whom, by when, and what would make the decision good …

    line 33
  4. Distinctive:

    Set the criteria and their weights: before scoring the options, so that scoring does not bend the criteria.

    line 36
  5. Distinctive:

    Every score rests on a fact or a labeled assumption.

    line 56

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “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 making

Hesitating costs time and energy, and deciding on gut feeling hides the reasons. This skill structures a choice so that it can be explained, checked and revisited if the facts change.

When to use

  • When a project is blocked by a choice between options.
  • For decisions that cost money or are hard to reverse.
  • Not for small, easily reversible choices: decide quickly and move on.

Inputs

  1. The decision to make, and its deadline.
  2. The options already on the table.
  3. What matters to the person or the team, and the facts available.

Method

  1. Frame the problem before comparing options: what exactly is being decided, by whom, by when, and what would make the decision good (Hammond, Keeney and Raiffa's PrOACT elements: problem, objectives, alternatives, consequences, tradeoffs).
  2. Classify the decision: easy to reverse (decide fast) or hard to reverse (take the time, gather facts).
  3. Widen the options: at least three real alternatives, including "do nothing" and a combination of two options.
  4. Set the criteria and their weights before scoring the options, so that scoring does not bend the criteria.
  5. Score each option in a decision matrix, with the facts behind each score. Facts that change (prices, rules, availability) come from current sources with a date.
  6. Check the biases listed by Kahneman, Lovallo and Sibony: falling in love with one option, only looking for confirming evidence, anchoring on the first number, sunk costs, overconfidence. Ask: what would have to be true for the second-best option to win?
  7. Decide and record: the decision, the reasons, what would make us revisit it, who was consulted, and the date.

Output

### Decision: <question> (decide by <date>, decision owner: <name>)
| Criterion | Weight | Option A | Option B | Option C |
|---|---|---|---|---|
| … | …% | score (fact) | … | … |
| Weighted total | | | | |

Decision: … | Why: … | We revisit if: … | Consulted: … | Date: …

Quality bar

  • At least three real options, criteria weighted before scoring.
  • Every score rests on a fact or a labeled assumption.
  • Biases are checked explicitly, and the decision record says when to revisit it.
  • The tool supports the decision; the person still decides.
  • Written in the user's language, with the terms below.

Terminology

EnglishFrançaisEspañol
Decision matrixMatrice de décisionMatriz de decisión
Criterion, weightCritère, pondérationCriterio, ponderación
Trade-offArbitrageCompromiso, disyuntiva
Sunk costCoût irrécupérableCoste hundido
Confirmation biasBiais de confirmationSesgo de confirmación
Decision logRegistre des décisionsRegistro de decisiones

Sources

  • Hammond, J. S., Keeney, R. L., & Raiffa, H. (1999). Smart Choices: A Practical Guide to Making Better Decisions. Harvard Business School Press.
  • Kahneman, D., Lovallo, D., & Sibony, O. (2011). Before you make that big decision. Harvard Business Review, 89(6), 50–60.

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.