decision-matrix
Skill4 starsChanged 49 days agoMITView on GitHub
Structure a choice between concrete options: elicit the real criteria and their weights, score each option honestly, run a sensitivity check on the weights, and separate what the numbers say from what the gut says. Use when choosing between 2–6 named alternatives (jobs, tools, vendors, apartments, strategies).
16 other projects use a version of this.
Adopted by
Most recently taken up by
- calvyntwh/karu-custom-skillstheir own version, first seen Nov 15, 2026
- jaskirat1616/grok-skillstheir own version, first seen Nov 1, 2026
- vijaysuperpositionist/skillstheir own version, first seen Nov 1, 2026
- vredin/vredin-CC-Harnesstheir own version, first seen Nov 1, 2026
- varelaia/claude-skills-publictheir own version, first seen Oct 26, 2026
- JayRHa/agent-skillstheir own version, first seen Oct 15, 2026
Other versions16 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 16
- jaskirat1616/grok-skills★ 22same name
- Hongyu-yu/matsci-ai-skills★ 19same name
- JayRHa/agent-skills★ 12same name
- JayRHa/AgentSkills★ 12same name
- vredin/vredin-CC-Harness★ 9same name
- fzfclee/consulting-skills★ 6same name
- The-Utopia-Studio/skills★ 6same name
- markusbegerow/board-of-directors★ 5same name
- 53able/skills★ 4same name
- itzcull/thinking-skills★ 3same name
6 more not listed
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 repository48 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/AGENTS.mdAGENTS.md
- .agents/skills/assumption-audit/AGENTS.mdAGENTS.md
- .agents/skills/decision-matrix/AGENTS.mdAGENTS.md
- .agents/skills/direct-setup/AGENTS.mdAGENTS.md
- .agents/skills/direct-verify/AGENTS.mdAGENTS.md
- .agents/skills/first-principles-thinking/AGENTS.mdAGENTS.md
- .agents/skills/percolate-kb/AGENTS.mdAGENTS.md
- .agents/skills/percolate-reading/AGENTS.mdAGENTS.md
- .agents/skills/phase-final-reviewer/AGENTS.mdAGENTS.md
- .agents/skills/phase-implementer/AGENTS.mdAGENTS.md
- .agents/skills/phase-orchestrator/AGENTS.mdAGENTS.md
- .agents/skills/phase-reviewer/AGENTS.mdAGENTS.md
- .agents/skills/plan-kb/AGENTS.mdAGENTS.md
- .agents/skills/pr-cleanup/AGENTS.mdAGENTS.md
- .agents/skills/query-kb/AGENTS.mdAGENTS.md
- .agents/skills/question-forge/AGENTS.mdAGENTS.md
- .agents/skills/reclaim-disk-space/AGENTS.mdAGENTS.md
- .agents/skills/refresh-kb/AGENTS.mdAGENTS.md
- .agents/skills/riff/AGENTS.mdAGENTS.md
- .agents/skills/save-pdf-kb/AGENTS.mdAGENTS.md
- .agents/skills/save-url-kb/AGENTS.mdAGENTS.md
- .agents/skills/write-phase-plan/AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- kb/AGENTS.mdAGENTS.md
- personal-website/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- assumption-auditSkill
- direct-setupSkill
- direct-verifySkill
- first-principles-thinkingSkill
- percolate-kbSkill
- percolate-readingSkill
- phase-final-reviewerSkill
- phase-implementerSkill
- phase-orchestratorSkill
- phase-reviewerSkill
- plan-kbSkill
- pr-cleanupSkill
- query-kbSkill
- question-forgeSkill
- reclaim-disk-spaceSkill
- refresh-kbSkill
- riffSkill
- save-pdf-kbSkill
- save-url-kbSkill
- write-phase-planSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
3
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 27
Use this concise structure unless the user asks otherwise:
- Distinctive: line 55
No bare scores — every cell gets a reason, or the matrix is numerology.
- Distinctive: line 57
If two options are within ~5% after sensitivity analysis, say the matrix cannot decide and name the tiebreaker question.
“Common” is measured: kept by at least 6 in 10 of the 13 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 Matrix
Use this skill when the user faces a choice between concrete, named options and wants the tradeoffs made explicit. The matrix is not an oracle — its value is forcing criteria and weights into the open, then revealing whether the decision is robust or hinges on one contestable weight.
Purpose
Unstructured option comparison lets the mind double-count favorite criteria and quietly ignore inconvenient ones. A weighted matrix forces every criterion to be named, weighted once, and applied consistently. The most important output is often not the winning score but the sensitivity analysis — discovering that the choice flips on a single weight is the real insight. And when the user feels disappointed by the winner, that feeling is data.
Procedure
- List the options (2–6). If more, cluster or pre-filter first.
- Elicit criteria — what actually matters. Probe for hidden criteria: status, fear, reversibility, optionality, who else is affected. Aim for 4–8.
- Weight criteria (must sum to 100). Force tradeoffs — no "everything is important."
- Score each option per criterion (1–10), citing a reason per cell — no bare numbers.
- Compute weighted totals.
- Sensitivity check: which single weight change would flip the winner? Is the margin robust or fragile?
- Gut check: tell the user the winner and watch the reaction. If the numbers say A but the gut sinks, the matrix is missing a criterion — find it and re-run.
- State the recommendation with its condition: "A wins unless you actually weight X more than you claimed."
Output format
Use this concise structure unless the user asks otherwise:
## Options
...
## Criteria and weights
| Criterion | Weight | Why it matters |
|---|---|---|
## Scores
| Criterion (weight) | Option A | Option B | Option C |
|---|---|---|---|
| ... | 7 — reason | 4 — reason | 9 — reason |
| **Weighted total** | ... | ... | ... |
## Sensitivity
...
## Gut check
...
## Recommendation
...Guardrails
- No bare scores — every cell gets a reason, or the matrix is numerology.
- Include reversibility/optionality as a candidate criterion; irreversible choices deserve extra weight scrutiny.
- If two options are within ~5% after sensitivity analysis, say the matrix cannot decide and name the tiebreaker question.
- The matrix ranks given options; if all options are bad, say so rather than crowning the least bad.
Canonical questions
- "Should I take the Google offer, the startup offer, or stay?"
- "Postgres vs. DynamoDB vs. SQLite for this service?"
- "Which of these 3 apartments should we rent?"
- "Pick a city for the new office: Austin, Denver, or Raleigh."
- "Which vendor should we go with for payroll?"
Poor fits: yes/no decisions with one option (use assumption-audit or inversion), choices with unlistable criteria ("who should I marry"), and questions where the real task is generating options, not ranking them.
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.

