Decision memo

Skill stephenrogan/leadership-skills/skills/decision-memo

Agent Skills-compatible leadership and manager workflow library

Install

npx -y skills add stephenrogan/leadership-skills --skill decision-memo

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Creates a concise decision memo with context, decision required, options, tradeoffs, assumptions, dissent, recommendation, owner, and revisit criteria. Use when a leadership decision has ambiguity, cross-functional impact, material risk, or is likely to be reopened later.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

4.3 KB, as published. Nobody here has run it

Decision Memo

Overview

Use this skill to support the leader as Decision architect. A decision-ready memo that makes tradeoffs explicit and prevents decision amnesia.

This skill is human-led by design: the agent prepares the work, but the human leader owns judgment, relationship, accountability, and final decisions.

When to Use

Run this skill when:

Material decision needs to be made
Teams keep re-litigating the same choice
Options, constraints, or ownership are unclear

Do not use it as a substitute for legal, HR, finance, security, medical, or executive approval. If the workflow affects employment, compensation, customer commitments, external messaging, or sensitive personal data, prepare the packet and stop for human review.

Inputs

Ask for or gather:

Decision statement and context
Options considered
Data, constraints, risks, and dependencies
Stakeholders and dissenting views

If inputs are missing, proceed with explicit assumptions and label confidence. Do not invent private context, motives, or facts.

Workflow

Follow this sequence:

Write the decision as a question with owner and deadline
Limit options to 2-4 real choices, including status quo if relevant
For each option, state upside, downside, cost, reversibility, and second-order effect
Name assumptions and what would change the decision
Record recommendation, dissent, final decision, and revisit trigger

Before finalizing, run the boundary check: what is evidence, what is interpretation, what is a recommendation, and what must remain a human decision?

Output Format

Produce a concise, decision-ready artifact using this structure:

# Decision Memo

## Situation
[Brief context and why this workflow is being run.]

## Evidence and Signals
- Fact:
- Pattern:
- Hypothesis, confidence:

## Recommended Focus
1. [Highest leverage focus]
2. [Second focus]
3. [Third focus, optional]

## Working Artifact
[Agenda, memo, brief, plan, map, script, or tracker depending on the workflow.]

## Human Decisions Required
- [Decision/action the agent must not take.]

## Follow-Up
- Owner:
- Date:
- Success signal:

Expected deliverables:

One-page decision memo
Options/tradeoff table
Assumption and dissent log
Decision record

See assets/output-template.md for a reusable version.

Human Decision Boundary

The agent may prepare, synthesize, compare, draft, and track. The agent must not cross these boundaries:

Do not make the final decision unless explicitly asked and authorized
Do not hide uncertainty to make the memo cleaner
Human leader owns values, risk appetite, and accountability

Stop and ask for explicit approval before sending messages, changing employment status, making customer promises, publishing, sharing sensitive information, or committing budget/resources.

Quality Bar

A strong output for this skill:

Separates facts, interpretations, hypotheses, and recommendations.
Names uncertainty and missing context instead of hiding it.
Produces an artifact a busy leader can use immediately.
Reduces avoidance, ambiguity, rework, or decision drift.
Makes the human judgment boundary visible.
Includes concrete follow-up with owner, date, and success signal where applicable.

Failure Modes

Watch for these mistakes:

Overconfident claims from thin notes or sentiment.
Generic management advice with no artifact.
Automating sensitive judgment instead of preparing it.
Producing too many options without a recommended default.
Treating leadership as text generation rather than accountability.

References

Amazon narrative memo practice
Kahneman/Sibony/Sunstein, Noise: decision hygiene
Atlassian DACI decision practice

For the shared methodology spine, see ../../docs/SOURCE-SPINE.md.