decision-doc
Skill2 starsChanged 7 months agoMITView on GitHub
Produce a structured decision document with explicit tradeoffs, weighted criteria, scored options, a recommendation, and a flip condition. Use whenever the user is choosing between options, comparing approaches, evaluating vendors or frameworks, or deciding between architecture patterns. Triggers on "help me decide", "compare X vs Y", "which should I pick", "should I use A or B", framework or vendor decisions, architecture choices, or any decision where a structured tradeoff would be more useful than a casual opinion. Always use this skill rather than free-form pros and cons lists when the user is making a real decision.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- talgacapri/pm-ostheir own version, first seen May 23, 2026
- nbirkner/digital-braintheir own version, first seen Apr 12, 2026
- Mehdibargach/claude-code-pm-skillstheir own version, first seen Mar 18, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- Mehdibargach/claude-code-pm-skills★ 97same name
- nbirkner/digital-brain★ 0same name
- talgacapri/pm-os★ 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 repository4 other files it gives its agents.
- brand-voiceSkill
- code-reviewerSkill
- csv-cleanerSkill
- one-pagerSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
1
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 32
If the user provided criteria, use those.
“Common” is measured: kept by at least 6 in 10 of the 3 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
Decision Doc
Produces a structured decision document. Forces a recommendation with confidence and a flip condition, instead of hedging.
When to use
- Two or more options under consideration
- The user wants a recommendation, not just a comparison
- The decision has stakes (money, time, lock-in, reversibility)
When NOT to use
- The user is exploring a topic without a specific decision in front of them.
- One option has a hard disqualifier. Just say so, no need for the full doc.
- The user explicitly asks for a casual opinion.
Process
Step 1: Restate the decision
One sentence in your own words. Flag any ambiguity that would change the answer. If ambiguity is severe, ask one clarifying question before proceeding.
Step 2: Define criteria
List 4 to 7 evaluation criteria. Assign each a weight from 1 to 5. Total weights must sum to a number between 15 and 25. This constraint prevents flattening the criteria with all-equal weights.
If the user provided criteria, use those. If not, derive them from the decision context.
Step 3: Score each option
Score each option from 1 to 5 against each criterion. Compute a weighted total per option. Show the work.
Step 4: State the tradeoff for each option
One sentence per option describing what you give up by choosing it. No option escapes this step. Even the best option has a cost.
Step 5: Recommend
State the recommendation. Cite the weighted score, but do not let the score override clear qualitative concerns. If a lower-scoring option is the right answer for a reason the score cannot capture, say so.
Step 6: Flip condition
State one specific change in inputs or context that would make a different option win. This is the most important field. If you cannot articulate a flip condition, the analysis is not done.
Step 7: Confidence
1 (coin flip) to 5 (clear winner).
Output format
## Decision
<restated decision>
## Ambiguities
<list, or "none">
## Criteria
| Criterion | Weight | Why it matters |
|---|---|---|
## Scoring
| Option | <criterion 1> | <criterion 2> | ... | Weighted Total |
|---|---|---|---|---|
## Tradeoffs
- <Option A>: <what you give up>
- <Option B>: <what you give up>
## Recommendation
<option name>
<2 to 4 sentences explaining why>
## Flip Condition
If <specific input change>, the recommendation becomes <other option>.
## Confidence
<1 to 5> / 5Stability check
For high-stakes decisions, run the analysis twice with the options listed in opposite order. If the recommendation flips between runs purely from ordering, the analysis is unstable. Widen the criteria or get more information before committing.
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.

