Split Decision

When facing architectural decisions, technology choices, or strategic trade-offs, present options as a structured comparison and require explicit trade-off acknowledgment before proceeding. Triggers on words like "should we", "which approach", "what's the best way", or when Claude is about to recommend one approach over alternatives. Never present a single recommendation without showing viable alternatives first.

62 stars 2 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add ElliotJLT/Claude-Skill-Potions --skill split-decision
Manual install
git clone --depth 1 https://github.com/ElliotJLT/Claude-Skill-Potions.git /tmp/Claude-Skill-Potions
mkdir -p ~/.claude/skills
cp -r /tmp/Claude-Skill-Potions/skills/split-decision ~/.claude/skills/split-decision

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Split Decision

<purpose>
Claude has a tendency to present "the best approach" as if there's only one right
answer. In reality, most significant decisions involve trade-offs. This skill
forces multi-option analysis before committing to any architectural, technology,
or strategic choice. No more single-option recommendations dressed up as
obvious conclusions.
</purpose>

## When To Activate

Trigger when you see:

- User asks "should we X or Y"
- User asks "what's the best approach for..."
- User asks "which is better..."
- Claude is about to recommend an architectural choice
- Claude is about to recommend a technology/library/tool
- Any decision with meaningful trade-offs (not trivial choices)
- Refactoring approaches with multiple valid paths
- Database, framework, or infrastructure decisions

Do NOT trigger for:

- Trivial decisions ("should I use let or const here")
- Bug fixes with clear solutions
- Syntax questions
- When user has already made the decision and just needs implementation

## Instructions

### Step 1: Identify Viable Options

Generate 2-4 genuinely viable options. These must be:

- Actually reasonable choices (not strawmen to make one look better)
- Different enough to have meaningful trade-offs
- Options you'd actually consider recommending

If there's truly only one viable option, state why alternatives don't apply.

### Step 2: Assess Each Option

For each option, evaluate:

| Dimension | What to assess |
|-----------|----------------|
Read the full skill on GitHub

Details

Skill name
split-decision
Path
skills/split-decision/SKILL.md
License
MIT
Repo updated
12 February 2026

FAQ

What does the Split Decision skill do?

When facing architectural decisions, technology choices, or strategic trade-offs, present options as a structured comparison and require explicit trade-off acknowledgment before proceeding. Triggers on words like "should we", "which approach", "what's the best way", or when Claude is about to recommend one approach over alternatives. Never present a single recommendation without showing viable alternatives first.

How do I install the Split Decision skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ElliotJLT/Claude-Skill-Potions --skill split-decision. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Split Decision popular?

It lives in ElliotJLT/Claude-Skill-Potions, which has 62 GitHub stars and 2 forks.

Related skills

Agent Audit

62

ElliotJLT/Claude-Skill-Potions

When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft. Instruments usage, ablates components, and strips the agent to minimum viable form. Answers: "What can we remove without degrading quality?" The goal is the leanest agent that still works.

AI, LLMs & Agents

Battle Plan

62

ElliotJLT/Claude-Skill-Potions

Before ANY significant development task (new feature, refactor, integration, migration), run a complete planning ritual by orchestrating other skills in sequence: rubber-duck (clarify scope) -> pre-mortem (assess risks) -> eta (estimate time) -> final confirmation. Do not start coding until the battle plan is approved.

Software Development

Breadcrumbs

62

ElliotJLT/Claude-Skill-Potions

Leaves notes for future Claude sessions in .claude/breadcrumbs.md. At session end or after significant work, records what was tried, what worked, what failed, and context for next time. On session start, reads breadcrumbs to understand history. Session-to-session memory without manual updates.

Productivity & Notes

Subagent Driven Development

43

obra/clank

Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks

AI, LLMs & Agents26

Installing Skills System

43

obra/clank

Fork, clone to ~/.clank, run installer, edit CLAUDE.md

AI, LLMs & Agents26

Survey Experiment Eval

36

dariia-m/my_claude_skills

Evaluates survey experiment designs for economics research. Produces a structured diagnostic report covering identification, randomization, power, survey instrument quality, demand effects, ethics, pre-registration, and analysis plan. Use this skill whenever the user describes a survey experiment, shares a pre-analysis plan, uploads a survey instrument or Qualtrics file, asks "does this design work", "review my experiment", "what's wrong with this RCT", "check my survey experiment", "evaluate my experimental design", "audit my design", or discusses any planned or ongoing survey-based randomize

AI, LLMs & Agents11

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.