decision-brief
Skill0 starsChanged 4 months agoMITView on GitHub
One-page decision brief that passes the Simple/Surprising/Easy test. Turns a messy decision into a constraint that generates action. Based on Alex MH Smith's creative brief framework. Activates on "write a brief", "decision brief", "one-pager", "clarify the direction", "what's the constraint", or "make this simple."
8 other projects use a version of this.
Adopted by
Most recently taken up by
- parker-brown-family/agent-skillstheir own version, first seen Nov 8, 2026
- rajasdevel/outcomeboundtheir own version, first seen Nov 1, 2026
- zommuter/dotclaude-skillstheir own version, first seen Oct 28, 2026
- oswarld/notion-skillstheir own version, first seen Sep 23, 2026
- tmusser/context-to-action-skillstheir own version, first seen Sep 16, 2026
- kayspiegel/survey-insight-skillstheir own version, first seen Aug 16, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- oswarld/notion-skills★ 11same name
- ryancproduct/product-ai-toolkit★ 4same name
- zommuter/dotclaude-skills★ 4same name
- kayspiegel/survey-insight-skills★ 2same name
- tmusser/context-to-action-skills★ 2same name
- Ootto-AI/claude-reporting-skills★ 1same name
- parker-brown-family/agent-skills★ 1same name
- rajasdevel/outcomebound★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-graduationSkill
- arbitrage-auditSkill
- assumption-mapperSkill
- b2b-idea-vettingSkill
- codifySkill
- design-thinking-liteSkill
- grill-meSkill
- grill-with-docsSkill
- innovation-diagnosticSkill
- kill-goSkill
- preflightSkill
- problem-framingSkill
- pull-frameworkSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
8
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
- Distinctive: line 28
Ask: "What decision are you trying to make?
- Distinctive: line 33
If it's not a question, make it one.
- Distinctive: line 37
Every real decision has a tension — two legitimate forces pulling in opposite directions.
- Distinctive: line 39
Ask: "What makes this hard?
- Distinctive: line 47
If there's no tension, there's no real decision.
- Distinctive: line 53
Ask: "Given the tension, what's the one thing that must be true for this to succeed?"
- Distinctive: line 59
Read the constraint back to the user.
- Distinctive: line 65
If it fails any test, rewrite.
“Common” is measured: kept by at least 6 in 10 of the 7 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.
Files
The SSE Test
A brief must pass three tests. If it fails any, rewrite.
Simple — Points in one direction. Hard to go off track. If two people read it and go in different directions, it's not simple enough.
Surprising — Makes you think "I never thought of it that way." If it sounds like every other brief, it's decoration, not direction.
Easy — Anyone should immediately have rough ideas for how to act on it. If only "creatives" or "strategists" can use it, it's too abstract.
Patagonia's "cause no unnecessary harm" passes all three. It generates decisions: free repairs, organic cotton, no Black Friday. "Eco-friendly clothing" generates nothing.
Process
Step 1: What's the Decision?
Ask: "What decision are you trying to make? State it as a question."
Good: "Should we invest in building a self-serve analytics tier?" Bad: "We need to think about our analytics strategy."
If it's not a question, make it one. Decisions are questions with stakes.
Step 2: What's the Tension?
Every real decision has a tension — two legitimate forces pulling in opposite directions.
Ask: "What makes this hard? What are you torn between?"
Examples:
- Speed vs. quality
- Short-term revenue vs. long-term positioning
- Serving current users vs. attracting new ones
- Technical debt vs. feature velocity
If there's no tension, there's no real decision. It's just a task.
Step 3: What's the Constraint?
Turn the tension into a constraint. A constraint isn't a limit — it's a generator.
Ask: "Given the tension, what's the one thing that must be true for this to succeed?"
This becomes the brief. One sentence. Test it against SSE.
Step 4: Test Against SSE
Read the constraint back to the user. Apply each test:
- Simple: "If you handed this to a new team member, would they know what to do?"
- Surprising: "Does this feel obvious or does it reframe something?"
- Easy: "Can you immediately think of 3 actions that follow from this?"
If it fails any test, rewrite. Iterate until it passes all three.
Step 5: Generate 3 Actions
Prove the brief works by generating 3 concrete actions that follow directly from the constraint. If you can't generate 3, the brief isn't generative enough.
Output
# Decision Brief: [Decision Question]
Date: [date]
## The Decision
[Question form]
## The Tension
[Two forces in opposition]
## The Brief
> [One sentence — the constraint that generates action]
## SSE Check
- Simple: [Pass/Fail — evidence]
- Surprising: [Pass/Fail — evidence]
- Easy: [Pass/Fail — evidence]
## 3 Actions This Generates
1. [action]
2. [action]
3. [action]Based on Alex MH Smith's creative brief framework.
Next step
Brief done → run codify to make the record durable in decisions/.
Part of the ThinkHaven Method Kit by Kevin Holland. Full Board of Directors experience: ThinkHaven
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.

