decision-maker
Skill6 starsChanged 8 months agoMITView on GitHub
Use this skill when you face a complex or high-stakes decision and need a structured framework to evaluate options objectively. Ideal for career choices, product prioritization, vendor selection, or any multi-criteria trade-off. Not for trivial daily decisions or situations that require licensed professional advice.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- molly-diversifiedfun/claude-skillstheir own version, first seen Sep 16, 2026
- qingxuantang/Lennys-to-sop-and-skillstheir own version, first seen Jan 19, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- qingxuantang/Lennys-to-sop-and-skills★ 16same name
- molly-diversifiedfun/claude-skills★ 1same 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 repository68 other files it gives its agents.
- dataset-curatorSkill
- eval-designerSkill
- model-comparatorSkill
- prompt-engineerSkill
- business-analystSkill
- competitor-analystSkill
- market-researcherSkill
- meeting-facilitatorSkill
- okr-plannerSkill
- pitch-deck-writerSkill
- product-managerSkill
- ux-researcherSkill
- api-designerSkill
- architecture-designerSkill
- code-reviewerSkill
- debuggerSkill
- documentation-writerSkill
- refactorerSkill
- regex-masterSkill
- security-auditorSkill
- sql-expertSkill
- test-writerSkill
- chart-builderSkill
- dashboard-designerSkill
- data-analystSkill
- data-cleanerSkill
- excel-expertSkill
- sql-analystSkill
- color-paletteSkill
- design-critiquerSkill
- frontend-designSkill
- ux-writerSkill
- ci-cd-helperSkill
- docker-expertSkill
- kubernetes-helperSkill
- monitoring-setupSkill
- flashcard-makerSkill
- lesson-plannerSkill
- quiz-creatorSkill
- tutorSkill
- docxSkill
- pdfSkill
- pptxSkill
- xlsxSkill
- budget-plannerSkill
- financial-analystSkill
- invoice-generatorSkill
- contract-reviewerSkill
- legal-summarizerSkill
- terms-of-serviceSkill
- habit-builderSkill
- journalingSkill
- note-takerSkill
- task-plannerSkill
- citation-formatterSkill
- fact-checkerSkill
- literature-reviewerSkill
- summarizerSkill
- web-researcherSkill
- academic-essaySkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
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 105
Always score options blind (fill in scores before revealing which option you prefer) to reduce anchoring bias
- Distinctive: line 108
Use the Eisenhower matrix daily/weekly.
- Distinctive: line 109
When stakes are very high, run both a weighted scoring matrix AND a pre-mortem before committing
- Distinctive: line 110
Document your reasoning even if you ultimately go with intuition — you'll learn from the outcome
- Distinctive: line 121
If two options score within 5% of each other, flip a coin — the framework has told you they're essentially equal, so other factors (gut …
- Distinctive: line 123
Use a "regret minimization" sanity check (Bezos): imagine yourself at 80 looking back — which option would you regret NOT trying?
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Decision Maker
Overview
This skill applies proven decision-making frameworks—pros/cons analysis, weighted scoring matrices, RICE prioritization, the Eisenhower urgency-importance matrix, and pre-mortem analysis—to help you cut through ambiguity and make defensible, well-reasoned choices. By externalizing the decision into a structured format you reduce cognitive bias, surface hidden trade-offs, and create a record of your reasoning that can be revisited or shared with stakeholders.
When to Use
- You have two or more meaningful options and are unsure which to choose
- The decision has significant, lasting consequences (career, finances, product roadmap, hiring)
- Multiple stakeholders need to align around a shared rationale
- You feel emotionally stuck and want an objective framework to cut through the noise
- You need to prioritize a backlog of features, tasks, or projects
- You want to stress-test a decision you've already leaned toward
When NOT to Use
- The decision is low-stakes and reversible (where any choice is fine)
- You need licensed advice (legal, medical, financial) — frameworks support, not replace, professionals
- The situation requires immediate crisis action with no time for structured analysis
- Data needed to score criteria is completely unavailable or unknowable
- You simply want validation for a decision already firmly made
Quick Reference
| Framework | Best For | Output |
| Pros / Cons | Simple binary choices, fast gut-check | Two-column list |
| Weighted Scoring Matrix | Multi-option, multi-criteria trade-offs | Ranked score table |
| RICE | Feature or project prioritization | Priority-ranked backlog |
| Eisenhower Matrix | Task triage and time management | 4-quadrant urgency/importance grid |
| Pre-Mortem | Risk identification before committing | List of failure modes and mitigations |
Instructions
- Clarify the decision — State the decision in one clear sentence. Define what "success" looks like and the deadline by which you must decide.
- Enumerate options — List every realistic option, including "do nothing" or "defer." Aim for at least two, no more than six manageable choices.
- Choose a framework — Match the framework to the decision type: use Pros/Cons for simple binary choices; Weighted Scoring for multi-criteria comparisons; RICE for backlog prioritization; Eisenhower for task triage; Pre-Mortem for risk stress-testing.
- Define criteria (Weighted Scoring) — Identify 3–7 criteria that matter most (e.g., cost, time-to-value, strategic fit, risk). Assign each a weight from 1–5 reflecting its relative importance.
- Score each option — Rate every option against each criterion on a 1–10 scale. Multiply by weight. Sum the totals. Higher scores indicate better overall fit.
- Apply RICE (if prioritizing work) — For each item calculate: Reach × Impact × Confidence ÷ Effort. Reach = users affected; Impact = 1–3 scale; Confidence = percentage (0–100); Effort = person-weeks.
- Map urgency vs. importance (Eisenhower) — Plot tasks on a 2×2 grid: Do Now (urgent + important), Schedule (important, not urgent), Delegate (urgent, not important), Eliminate (neither).
- Run a pre-mortem — Imagine it is 12 months from now and the chosen option has failed spectacularly. Brainstorm every plausible cause. Use this list to add mitigations or re-weight criteria.
- Check for bias — Review the analysis for sunk-cost fallacy, status-quo bias, and confirmation bias. Ask: "Would I choose this if I were starting fresh?"
- Document and decide — Write a one-paragraph decision summary: chosen option, top three reasons, top two risks and their mitigations, and a review date.
Examples
Example 1: Career Choice — Stay at Current Job vs. Accept Startup Offer
Input: "I have a stable senior engineer role at a Fortune 500 paying $160k. A Series B startup offered me a staff engineer role at $140k base + 0.4% equity. I have a mortgage and two kids. Help me decide."
Output:
Weighted Scoring Matrix
| Criteria | Weight | Fortune 500 (score) | Fortune 500 (weighted) | Startup (score) | Startup (weighted) |
| Financial security | 5 | 9 | 45 | 5 | 25 |
| Career growth | 4 | 5 | 20 | 9 | 36 |
| Compensation upside | 3 | 4 | 12 | 8 | 24 |
| Work-life balance | 4 | 7 | 28 | 5 | 20 |
| Mission alignment | 2 | 4 | 8 | 8 | 16 |
| Total | 113 | 121 |
Pre-Mortem (Startup): Startup runs out of runway (mitigate: verify 18+ months runway, ask for accelerated vesting cliff), role scope shrinks post-hire (mitigate: get title and scope in writing).
Recommendation: The startup scores marginally higher, but the margin is within noise given your dependence on financial stability. Negotiate: request a $150k base, 12-month cliff vesting, and written role definition before accepting. If negotiation fails, the stability of the Fortune 500 warrants staying.
Example 2: Product Prioritization — RICE Scoring a Feature Backlog
Input: "We have 5 features to prioritize for Q3: (A) SSO login, (B) CSV export, (C) Mobile app, (D) Audit logs, (E) Bulk delete. We serve 2,000 enterprise users."
Output:
RICE Scores
| Feature | Reach | Impact | Confidence | Effort (wks) | RICE Score |
| A – SSO Login | 1,800 | 3 | 90% | 3 | 1,620 |
| D – Audit Logs | 1,500 | 2 | 80% | 2 | 1,200 |
| B – CSV Export | 1,200 | 2 | 95% | 1 | 2,280 |
| E – Bulk Delete | 800 | 1 | 90% | 0.5 | 1,440 |
| C – Mobile App | 600 | 3 | 60% | 12 | 90 |
Recommended Priority: B → A → E → D → C. CSV Export delivers the highest RICE score at low effort. Mobile App scores last due to high effort and low confidence — defer to Q4 or a dedicated mobile initiative.
Best Practices
- Always score options blind (fill in scores before revealing which option you prefer) to reduce anchoring bias
- Involve at least one dissenting voice in the criteria-weighting step to stress-test your priorities
- Revisit your decision at a predetermined date — decisions are hypotheses, not facts
- Use the Eisenhower matrix daily/weekly; reserve weighted scoring for quarterly or life decisions
- When stakes are very high, run both a weighted scoring matrix AND a pre-mortem before committing
- Document your reasoning even if you ultimately go with intuition — you'll learn from the outcome
Common Mistakes
- Weighting criteria after scoring options (this introduces confirmation bias into the weights)
- Using too many criteria (>7) which dilutes meaningful differentiation between options
- Treating RICE scores as precise — they are directional estimates, not exact measurements
- Skipping the pre-mortem step when you're excited about a preferred option — that's exactly when it's most needed
- Equating a higher score with a guaranteed good outcome — the framework improves odds, not certainty
- Forgetting to include "do nothing" as an explicit option with its own score
Tips & Tricks
- If two options score within 5% of each other, flip a coin — the framework has told you they're essentially equal, so other factors (gut feel, optionality) should break the tie
- Timebox the analysis: 30 minutes for a pros/cons, 2 hours for a full weighted matrix — decisions don't improve linearly with analysis time
- Use a "regret minimization" sanity check (Bezos): imagine yourself at 80 looking back — which option would you regret NOT trying?
- For team decisions, have each person score independently before sharing results to avoid groupthink
- Export your scoring matrix to a shared doc so stakeholders can see and challenge the inputs, not just the conclusion
Related Skills
- task-planner
- note-taker
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.

